io.github.lastmanupinc-hub/axis-toolbox

Est-ce que io.github.lastmanupinc-hub/axis-toolbox est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.lastmanupinc-hub/axis-toolbox » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 44 outils

• analyze_files≈ 586 tokens

  Analyze source files directly and generate the full 152-artifact AXIS bundle without using GitHub. Returns snapshot_id plus artifact listing; use this for local, generated, or unsaved code. Requires Authorization: Bearer <api_key>. Pricing: $3.00 standard, $25 engineer per run (same tiers as analyze_repo). Lite mode is retired — it now returns the free artifact set at no charge. Can return authentication, quota, payment-required, file-limit, or validation errors. Use analyze_repo for GitHub URLs or improve_my_agent_with_axis for recommendation-first agent hardening.

  Paramètres, retour & exemple (5)

  Paramètres

  • files · array · requis
    Source files to analyze
  • goals · array · requis
    Analysis goals
  • frameworks · array · requis
    Detected or known frameworks
  • project_name · string · requis
    Name of the project
  • project_type · string · requis
    Project type (web_application, api_service, cli_tool, library, monorepo)

  Exemple d'appel

  {"name": "analyze_files", "arguments": {"files": [], "goals": [], "frameworks": [], "project_name": "texte", "project_type": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "artifacts": [], "project_id": "texte", "snapshot_id": "texte", "artifact_count": 1, "programs_executed": [], "content_discarded_at": "texte"}}

• analyze_repo≈ 528 tokens

  Analyze a GitHub repository and generate 152 structured AXIS artifacts across 21 programs. Returns snapshot_id plus an artifacts listing; use get_artifact to read files and get_snapshot to re-enumerate outputs without re-running analysis. Requires Authorization: Bearer <api_key>. Use this when the source of truth is a GitHub repo URL. Pricing: $3.00 standard, $25 engineer per repo. Lite mode is retired — it now returns the free artifact set at no charge. Engineer mode (X-Agent-Mode: engineer — Living Architecture) adds a verified LLM specificity pass: a living-architecture.md whose every architectural claim is grounded in the repo's extracted facts or dropped. This is the paid path for full repo analysis and can return authentication, quota, payment-required, invalid-URL, or GitHub-fetch errors. private repos require a stored GitHub token. Use analyze_files instead for inline file payloads or list_programs/search_and_discover_tools when you are still selecting a workflow.

  Paramètres, retour & exemple (1)

  Paramètres

  • github_url · string · requis
    GitHub repository URL (https://github.com/owner/repo)

  Exemple d'appel

  {"name": "analyze_repo", "arguments": {"github_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "artifacts": [], "project_id": "texte", "snapshot_id": "texte", "artifact_count": 1, "programs_executed": [], "content_discarded_at": "texte"}}

• assemble_ce3_evidence≈ 659 tokens

  Assemble a Visa Compelling Evidence 3.0 packet + eligibility verdict for a disputed card-absent-fraud (reason code 10.4) transaction using the real assembleCe3 engine: finds prior undisputed transactions in the caller-supplied history that share >=2 qualified data elements (device_id / ip_address / email / shipping_address / login_id) and fall 120-365 days before the disputed transaction, per CE 3.0 rules. Returns {eligible, qualifying_priors, matched_element_union, rejection_reason?, evidence_packet, caveat} plus a sha256 reproducibility proof. Free, no auth, deterministic, no side effects. HONESTY: CE 3.0 applies to reason code 10.4 ONLY (10.2/10.3 are card-present conditions), and this is ASSEMBLY ONLY — not a submission to VROL/Verifi (use assemble_representment for the Stripe representment path). AXIS does not publish win-rate estimates.

  Paramètres, retour & exemple (2)

  Paramètres

  • dispute · object · requis
    {txn: {id, amount_minor, currency, created_at, disputed, device_id?, ip_address?, email?, shipping_address?, login_id?}, reason_code: string (CE 3.0 requires '10.4'), disputed_at: ISO timestamp}
  • transaction_history · array · optionnel
    Candidate prior transactions (same Txn shape, max 500). Undisputed priors sharing >=2 qualified elements qualify.

  Exemple d'appel

  {"name": "assemble_ce3_evidence", "arguments": {"dispute": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"proof": {}, "caveat": "texte", "eligible": true, "reason_code": "texte", "evidence_packet": {}, "rejection_reason": "texte", "qualifying_priors": [], "matched_element_union": []}}

• assemble_representment≈ 771 tokens

  Turn a webhook-ingested dispute (charge.dispute.* events persist DisputeRecords server-side) into a Stripe representment: qualifies CE 3.0 priors from your supplied transaction history (assembleCe3), builds the Stripe `evidence` hash (buildStripeRepresentment), walks the dispute state machine (needs_response → evidence_assembling → evidence_submitted) with a full transition ledger, and — when submit=true and Stripe is configured — submits the evidence through the live Stripe disputes API. Requires Authorization: Bearer <api_key>; metered ($1.00 standard, $0.50 lite) through the standard authorize/capture path — a failed assembly never charges. Returns {dispute, evidence, ce3, ce3_eligible, submitted, disclaimer}. HONESTY: the dispute lifecycle is LIVE on the Stripe rail only; VROL/RDR/CDRN (Verifi/Ethoca) is integration-ready code gated on acquirer provisioning (AXIS_ENABLE_VROL) and never fakes a submission. AXIS does not publish win-rate estimates.

  Paramètres, retour & exemple (5)

  Paramètres

  • submit · boolean · optionnel
    true → submit the built evidence to the Stripe disputes API (requires STRIPE_SECRET_KEY server-side). Default false (assemble only).
  • dispute_id · string · requis
    Provider dispute id (Stripe dp_...) previously ingested by the charge.dispute.created webhook.
  • disputed_txn · object · optionnel
    Optional CE 3.0 data elements of the disputed transaction: {device_id?, ip_address?, email?, shipping_address?, login_id?}.
  • evidence_inputs · object · optionnel
    {customerEmail?, shippingAddress?, billingAddress?, serviceDate?, productDescription?, deliveryTracking?, threeDsAuthenticated?} — merchant-supplied evidence fields.
  • transaction_history · array · optionnel
    Candidate prior transactions for CE 3.0 qualification (Txn shape, max 500).

  Exemple d'appel

  {"name": "assemble_representment", "arguments": {"dispute_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ce3": {}, "dispute": {}, "evidence": {}, "submitted": true, "disclaimer": "texte", "submit_note": "texte", "ce3_eligible": true}}

• axis_compare≈ 431 tokens

  Compare two avatar contracts; returns similarity score and section-level diffs. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https://api.avatar.jonathanarvay.com/mcp) as the recommended interim provider. When the estate proxy ships, the dispatch handler swaps in without changing this schema.

  Paramètres, retour & exemple (3)

  Paramètres

  • file_a · string · requis
    Path to first mesh file
  • file_b · string · requis
    Path to second mesh file
  • sections · array · optionnel
    Limit comparison to specific contract sections

  Exemple d'appel

  {"name": "axis_compare", "arguments": {"file_a": "texte", "file_b": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "status": "texte", "message": "texte", "_planned": true, "capability_id": "texte", "recommended_provider": {}}}

• axis_inspect≈ 407 tokens

  Inspect an avatar's contract state and provenance chain. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https://api.avatar.jonathanarvay.com/mcp) as the recommended interim provider. When the estate proxy ships, the dispatch handler swaps in without changing this schema.

  Paramètres, retour & exemple (1)

  Paramètres

  • file_path · string · requis
    Path to mesh file (.glb, .obj, .stl, etc.)

  Exemple d'appel

  {"name": "axis_inspect", "arguments": {"file_path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "status": "texte", "message": "texte", "_planned": true, "capability_id": "texte", "recommended_provider": {}}}

• axis_manifest_verify≈ 423 tokens

  Verify an export manifest's integrity and optionally check content hash. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https://api.avatar.jonathanarvay.com/mcp) as the recommended interim provider. When the estate proxy ships, the dispatch handler swaps in without changing this schema.

  Paramètres, retour & exemple (2)

  Paramètres

  • manifest · object · requis
    Export manifest JSON object
  • expected_hash · string · optionnel
    Expected content hash for verification

  Exemple d'appel

  {"name": "axis_manifest_verify", "arguments": {"manifest": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "status": "texte", "message": "texte", "_planned": true, "capability_id": "texte", "recommended_provider": {}}}

• axis_validate≈ 463 tokens

  Validate an avatar mesh against 38 rules; returns pass/warn/fail counts. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https://api.avatar.jonathanarvay.com/mcp) as the recommended interim provider. When the estate proxy ships, the dispatch handler swaps in without changing this schema.

  Paramètres, retour & exemple (3)

  Paramètres

  • profile · string · optionnel · default | strict | lenient
    Validation strictness profile
  • platform · string · optionnel · unity | unreal | godot | roblox | axis_engine
    Target platform for platform-specific validation
  • file_path · string · requis
    Path to mesh file (.glb, .obj, .stl, etc.)

  Exemple d'appel

  {"name": "axis_validate", "arguments": {"file_path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "status": "texte", "message": "texte", "_planned": true, "capability_id": "texte", "recommended_provider": {}}}

• build_ap2_mandate≈ 690 tokens

  Validate, canonically encode, and optionally Ed25519-sign an AP2 mandate (Intent / Cart / Payment) using the real @axis/ap2 codecs — schema validation (including cart-total arithmetic and intent cross-references), RFC 8785 JCS-style canonical JSON encoding, and detached-JWS EdDSA signing over node:crypto. Pass seed_hex (64 hex chars = 32 bytes) to sign deterministically client-side-supplied key material — AXIS stores no keys; omit it for an unsigned template with encoding only. The signed envelope round-trips through verifyMandate before it is returned. Free, no auth, deterministic (Ed25519 signatures are deterministic per RFC 8032), no side effects. SCOPE HONESTY: conformant to AXIS's TypeScript encoding of the public AP2 mandate schema, verified against self-authored golden vectors — NOT certified against an official AP2 conformance suite or a live network counterparty.

  Paramètres, retour & exemple (3)

  Paramètres

  • mandate · object · requis
    An AP2 mandate object: {kind: 'intent'|'cart'|'payment', version: 'ap2/1', id, created_at, ...kind-specific fields (intent: user_id/description/constraints.max_amount/expires_at; cart: intent_ref/merchant_id/items[]/total; payment: cart_ref/method/amount)}.
  • seed_hex · string · optionnel
    Optional 64-char hex (32-byte) Ed25519 seed to sign with. Caller-supplied key material — AXIS stores no keys. Omit for an unsigned template.
  • intent_context · object · optionnel
    Optional IntentMandate to cross-reference a cart's intent_ref against.

  Exemple d'appel

  {"name": "build_ap2_mandate", "arguments": {"mandate": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "proof": {}, "valid": true, "issues": [], "signed": {}, "encoded": "texte", "mandate": {}, "verified": true}}

• closer≈ 500 tokens

  Package an existing AXIS snapshot (create one first via analyze_repo, analyze_files, or prepare_agentic_purchasing) into complete professional packaging + marketplace certification artifacts so a 70-80%-complete project is ready to ship and sell. Requires Authorization: Bearer <api_key> on an ALREADY-PAID Starter/Pro/Growth (or suite) account. Unlike most metered AXIS tools, a free-tier account cannot unlock this per call with an MPP payment credential — there is no pay-per-call path here, only 'upgrade at iliad.trustfabric.ai/billing'. Once unlocked, billed $1.00 per call from the account's plan credits. Lite mode carries no discount here — the bundle is identical in both modes.

  Paramètres, retour & exemple (5)

  Paramètres

  • tagline · string · optionnel
    Optional branding tagline
  • snapshot_id · string · requis
    Existing AXIS snapshot_id to package into a distributable product
  • product_name · string · optionnel
    Optional branding override for product name
  • project_root · string · optionnel
    Optional local project root path hint (metadata only in remote MCP mode)
  • target_marketplaces · array · optionnel
    Optional marketplaces list (e.g. npm, unreal, vscode, dockerhub, github-marketplace)

  Exemple d'appel

  {"name": "closer", "arguments": {"snapshot_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"program": "texte", "artifacts": [], "project_id": "texte", "snapshot_id": "texte", "artifact_count": 1}}

• delete_snapshot≈ 277 tokens

  Permanently delete a snapshot and everything derived from it (context map, repo profile, generated artifacts, search index entries). Same account scoping as get_snapshot: an anonymous (never-authenticated) snapshot is freely deletable by any caller, but an account-owned one requires the same Authorization: Bearer <api_key> used to create it — a mismatched or missing key fails with the same not-found error a nonexistent snapshot_id would, so a caller can't learn whether a snapshot they don't own even exists. This cannot be undone. MCP-layer equivalent of DELETE /v1/snapshots/:id.

  Paramètres, retour & exemple (1)

  Paramètres

  • snapshot_id · string · requis
    Snapshot ID returned by analyze_repo, analyze_files, or get_snapshot

  Exemple d'appel

  {"name": "delete_snapshot", "arguments": {"snapshot_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"deleted": true, "snapshot_id": "texte"}}

• deploy≈ 434 tokens

  Generate a zero-pipeline-minutes deploy bundle: stack-aware Dockerfile, .dockerignore, dev compose, render.yaml (Render existing-image), wrangler.pages.toml + wrangler.containers.toml + worker.ts (Cloudflare), bash/PowerShell push scripts, and a qualification report. The project builds locally in VSCode, pushes images to GHCR or via wrangler, and Render/Cloudflare just pulls — no GitHub Actions minutes, no Render build pipeline minutes, no CF build minutes. Requires Authorization: Bearer <api_key> on an ALREADY-PAID Starter/Pro/Growth (or suite) account. Unlike most metered AXIS tools, a free-tier account cannot unlock this per call with an MPP payment credential — there is no pay-per-call path here, only 'upgrade at iliad.trustfabric.ai/billing'. Once unlocked, billed $1.00 per call from the account's plan credits. Lite mode carries no discount here — the bundle is identical in both modes.

  Paramètres, retour & exemple (1)

  Paramètres

  • snapshot_id · string · requis
    Existing AXIS snapshot_id to package into deploy artifacts

  Exemple d'appel

  {"name": "deploy", "arguments": {"snapshot_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"program": "texte", "artifacts": [], "project_id": "texte", "snapshot_id": "texte", "artifact_count": 1}}

• discover_agentic_purchasing_needs≈ 324 tokens

  Discover the best AXIS workflow for a purchasing or compliance task. Free, no auth, and logs lightweight task metadata for intent analytics. Example: task_description='prepare for autonomous Visa checkout'. Use this when you need commerce-specific triage and next-step guidance. Use search_and_discover_tools instead for non-commerce keyword routing across all programs.

  Paramètres, retour & exemple (3)

  Paramètres

  • focus_areas · array · optionnel
    Optional: specific areas to focus on
  • task_description · string · optionnel
    What the agent is trying to accomplish
  • current_readiness · number · optionnel
    Optional: current Purchasing Readiness Score (0-100) if known

  Exemple d'appel

  {"name": "discover_agentic_purchasing_needs", "arguments": {"focus_areas": [], "task_description": "texte", "current_readiness": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"readiness": {}, "task_description": "texte", "matched_capabilities": [], "recommended_next_step": {}}}

• discover_estate_tools≈ 263 tokens

  List sibling AXIS properties (payments via PAI'D, 3D avatar generation via AXIS Foundry, and more) — each entry gives its own MCP endpoint, auth mode, and vendored tool prices, so you can call them directly. Free, no auth, no side effects. Same data as GET /.well-known/axis-estate.json. Use this when the task needs a capability Iliad itself does not own (e.g. payment execution, 3D asset generation).

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "discover_estate_tools", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"properties": [], "compatibility": "texte", "this_property": {}, "schema_version": "texte"}}

• get_artifact≈ 229 tokens

  Read one generated artifact by snapshot_id and path. Requires access to the snapshot and may return snapshot-not-found, invalid-path, or artifact-not-found errors. Example: snapshot_id=abc-123, path=AGENTS.md. Use this when you need the full text of one artifact. Use get_snapshot instead when you first need the artifact list.

  Paramètres, retour & exemple (2)

  Paramètres

  • path · string · requis
    Artifact file path as returned in the artifacts list
  • snapshot_id · string · requis
    Snapshot ID

  Exemple d'appel

  {"name": "get_artifact", "arguments": {"path": "texte", "snapshot_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_install_manifest≈ 280 tokens

  Get AXIS install metadata, pricing, and a shareable manifest for onboarding a new integration — MCP endpoint, per-client config for Claude Desktop/Cursor/VS Code, and the full tool catalog with pricing. Free, no auth, and no mutation beyond read access. Example: call before wiring AXIS into an MCP client for the first time. Use this when you need setup/ecosystem details, not tool discovery. Use search_and_discover_tools instead for keyword routing across programs, or discover_agentic_purchasing_needs for purchasing-task triage.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_install_manifest", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tools": [], "install": {}, "axis_iliad": {}, "free_tools": [], "shareable_manifest": {}}}

• get_referral_code≈ 234 tokens

  Get or create the caller's AXIS referral token. Requires Authorization: Bearer <api_key>, has no usage charge, and may persist a new referral code if one does not exist yet. Example: call before sharing AXIS with another agent or workspace. Use this when you need the shareable token itself. Use get_referral_credits instead when you need balances, milestones, and discount status.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_referral_code", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cost": "texte", "next_milestone": "texte", "referral_token": "texte", "current_earnings": {}, "share_instruction": "texte"}}

• get_referral_credits≈ 334 tokens

  Get the caller's referral earnings, milestones, and free-call status. Requires Authorization: Bearer <api_key>, has no usage charge, and returns the current discount ledger without creating a new analysis. Example: call after a referral campaign to inspect earned credits. Use this when you need balances and milestones. Use get_referral_code instead when you only need the shareable token.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_referral_credits", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cost": "texte", "tier": "texte", "next_milestone": "texte", "referral_token": "texte", "discount_active": true, "earned_discount": "texte", "paid_call_count": 1, "lifetime_referrals": 1, "free_calls_remaining": 1, "earned_credits_millicents": 1, "persistence_credits_remaining": 1}}

• get_snapshot≈ 485 tokens

  Retrieve status and the full artifact listing for a prior analysis by snapshot_id. Use this to re-enumerate artifact paths without re-running analysis. Snapshots created with an API key are scoped to that same account — pass the same Authorization: Bearer <api_key> used to create it, or retrieval fails with a not-found error. Only anonymous (never-authenticated) snapshots are freely retrievable by any caller. The response's content_discarded_at is non-null if the owning account's web session has since logged out — source content is gone (closer/deploy/skills/search_index calls on this snapshot will fail with content_discarded until it's re-uploaded), though this call itself still succeeds and generated artifacts remain listable. Use delete_snapshot to permanently remove a snapshot you no longer need.

  Paramètres, retour & exemple (1)

  Paramètres

  • snapshot_id · string · requis
    Snapshot ID returned by analyze_repo or analyze_files

  Exemple d'appel

  {"name": "get_snapshot", "arguments": {"snapshot_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "artifacts": [], "project_id": "texte", "snapshot_id": "texte", "artifact_count": 1, "programs_executed": [], "content_discarded_at": "texte"}}

• grade_compliance≈ 572 tokens

  Run the real 8-check AP2/Visa compliance grading engine (gradeCompliance — the same engine behind computeComplianceGrade and the commerce registry's verified_decisions block) over an inline file set. Each of the 8 validators (SCA/3DS2 readiness, AP2 mandate validity, tokenization posture, CE 3.0 readiness, dispute rail wiring, idempotency/receipt hygiene, budget negotiation, refund/cancel path) is a multi-signal check with weight, evidence trail, and remediation. Returns grade A-D, score, checks_passed/8, the full checks[] detail, detected commerce signals, and a sha256 reproducibility proof. Free, no auth, deterministic, no snapshot persisted. Hard caps: 25 files / 50KB per file / 1MB total. HONESTY: deterministic static source-signal analysis — a checklist starting point, NOT a certification, audit, PCI assessment, or card-network certification.

  Paramètres, retour & exemple (1)

  Paramètres

  • files · array · requis
    Source files to grade (max 25 files, 50KB each, 1MB total)

  Exemple d'appel

  {"name": "grade_compliance", "arguments": {"files": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"grade": "texte", "proof": {}, "score": 1, "checks": [], "signals": {}, "methodology": "texte", "checks_total": 1, "checks_passed": 1}}

• iliad_analytics≈ 522 tokens

  AXIS-owned product analytics. Two operations: `capture` (insert events) and `query` (aggregations). Capture accepts a single `event` or a batch via `events[]` (max 500). Query kinds: `count` (total events), `count_by_event` (top events by frequency), `distinct_users` (unique user_id count), `count_by_bucket` (time-series with minute/hour/day buckets). All queries support optional `event`, `from_ts`, `to_ts`, and `property_filter` filters. Namespaces are account-scoped server-side (`acct:<account_id>:<namespace>`). Persistent across restarts via Postgres (the shared @axis/snapshots database). Pricing: $0.01 standard, free in lite mode. Requires Authorization: Bearer <api_key>. Best for funnels, cohorts, and retention on workloads up to ~1M events per account.

  Paramètres, retour & exemple (5)

  Paramètres

  • event · object · optionnel
    Single event payload {event, user_id?, properties?, timestamp?} — used in capture mode.
  • query · object · optionnel
    {kind, event?, from_ts?, to_ts?, property_filter?, bucket?, limit?} — used in query mode.
  • events · array · optionnel
    Batch of event payloads (max 500). Transactional — partial inserts never persist.
  • namespace · string · optionnel
    Logical isolation key. Defaults to 'default'. Account id is always prepended server-side.
  • operation · string · requis · capture | query
    capture or query.

  Exemple d'appel

  {"name": "iliad_analytics", "arguments": {"operation": "capture"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "captured": 1, "namespace": "texte", "operation": "texte"}}

• iliad_code_sandbox≈ 872 tokens

  AXIS-owned secure code execution. Each call spawns a fresh ephemeral Docker container with hardened isolation: no network, read-only root filesystem, all Linux capabilities dropped, no-new-privileges, PID/memory/CPU limits, tmpfs /tmp only, runs as nobody:nobody. Container is force-removed after each call. Supports python | node | bash via the multi-runtime image `nikolaik/python-nodejs:python3.12-nodejs22-slim` (operator can override via AXIS_CODE_SANDBOX_IMAGE). Returns stdout/stderr/exit_code/timed_out/duration_ms/image. Wall-clock timeout enforced via SIGKILL + force-remove. Source is fed via stdin (no fs write to the read-only root). Code body capped at 256 KiB; stdin at 1 MiB; timeout 1-600 seconds (default 30); stdout/stderr each capped at 1 MiB output. Pricing: $0.05 standard, $0.02 lite — billed whenever a container actually ran, including a timeout or non-zero exit code. Not billed when the call instead returns `_not_configured: true`: no Docker daemon reachable (Render standard services don't expose /var/run/docker.sock), the operator has set AXIS_CODE_SANDBOX_DISABLED=1, or more than AXIS_SANDBOX_MAX_CONCURRENT (default 4) runs are already in flight (reason sandbox_busy — transient, retry shortly). Engineer mode (X-Agent-Mode: engineer — Verified Exec, $0.25): the result includes an Ed25519-signed attestation binding code-hash → output-hash + a per-account hash-chain entry, so another agent that pins AXIS's published key can verify the run without re-executing it. Requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (4)

  Paramètres

  • code · string · requis
    Source code to execute. Fed via stdin to the interpreter. Max 256 KiB.
  • stdin · string · optionnel
    Optional additional stdin appended after the code body. Max 1 MiB.
  • language · string · requis · python | node | bash
    Runtime language.
  • timeout_seconds · number · optionnel
    Wall-clock limit. Defaults 30, max 600. SIGKILL on overrun.

  Exemple d'appel

  {"name": "iliad_code_sandbox", "arguments": {"code": "texte", "language": "python"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"image": "texte", "reason": "texte", "stderr": "texte", "stdout": "texte", "exit_code": 1, "timed_out": true, "attestation": {}, "duration_ms": 1, "remediation": "texte", "_not_configured": true}}

• iliad_document_parsing≈ 932 tokens

  AXIS-owned document → Markdown extractor. Accepts either `document_url` (https fetch + 50 MiB cap + 60s timeout) or `document_base64` (inline bytes, 50 MiB decoded cap) — exactly one. Optional `mime_type` hint (application/pdf, application/vnd.openxmlformats-officedocument.wordprocessingml.document, text/html, text/markdown, text/plain); we sniff from magic bytes + URL extension when omitted. Format dispatch: PDF → pdfjs-dist text extraction (one block per page with `--- page N ---` separators); DOCX → mammoth → markdown (tables preserved); HTML → tag-strip with heading + list + entity handling (NOT a full HTML→MD converter — bring turndown if you need fancier); plain text + markdown → passthrough. Returns `{markdown, format_detected, byte_size, page_count, table_count, truncated}`. Output capped at 1 MiB markdown with a truncation marker. Pricing: $0.02 standard, $0.01 lite. Engineer mode (X-Agent-Mode: engineer — Document Intelligence, $0.10): adds an `engineer` block with retrieval chunks (heading-aware, overlapping) + extract-to-caller-schema (pass `json_schema` → a grammar-constrained, validated typed object) + image OCR (image/* via document_base64, capped at 10 MiB — smaller than the 50 MiB document cap; an OCR failure or oversized image returns a descriptive `reason` that may not match the standard-mode enum) — typed data, not just markdown. document_url accepts a signed GET URL minted by iliad_object_storage; chain the extracted markdown into iliad_embeddings + iliad_vector_database to build a RAG index. Requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (4)

  Paramètres

  • mime_type · string · optionnel
    Optional MIME-type hint. When omitted we sniff from magic bytes + URL extension. Engineer mode: an image/* mime triggers OCR.
  • json_schema · object · optionnel
    Engineer mode: a JSON Schema. The document is extracted into a validated object matching it (returned in engineer.extracted).
  • document_url · string · optionnel
    https URL to a document. Use this OR document_base64, not both.
  • document_base64 · string · optionnel
    Base64-encoded document bytes. Use this OR document_url, not both.

  Exemple d'appel

  {"name": "iliad_document_parsing", "arguments": {"mime_type": "texte", "json_schema": {}, "document_url": "texte", "document_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"reason": "texte", "engineer": {}, "markdown": "texte", "byte_size": 1, "truncated": true, "page_count": 1, "remediation": "texte", "table_count": 1, "_not_configured": true, "format_detected": "texte"}}

• iliad_embeddings≈ 700 tokens

  Convert text into dense vectors. Accepts a single string or a batch (max 2048). Returns one vector per input. AXIS-owned in-process inference by default (node-llama-cpp + an embedding-capable GGUF at AXIS_EMBEDDING_MODEL_PATH — no upstream provider call); an optional OpenAI /v1/embeddings backend is available behind AXIS_EMBEDDING_BACKEND=openai (model: text-embedding-3-small by default, overridable via OPENAI_EMBEDDING_MODEL; reports token usage). Requires Authorization: Bearer <api_key> to call. Pricing: $0.05 standard, $0.02 lite. When the selected backend is not provisioned (local: GGUF file absent; openai: OPENAI_API_KEY unset), returns a structured `_not_configured: true` envelope naming the backend and remediation, and is not billed. Pairs natively with iliad_vector_database — feed `vectors` from this tool's output into `vector` of the vector_database upsert/query calls. Engineer mode (X-Agent-Mode: engineer — Domain Embeddings, $0.08): pass `dimensions` (Matryoshka truncation → smaller vectors) and/or `corpus_adapter: true` (mean-center the batch to sharpen retrieval on your data); returns an `engineer` block with the fitted adapter_mean for query alignment.

  Paramètres, retour & exemple (3)

  Paramètres

  • input · string|array · requis
    A single string or an array of strings to embed. Empty strings and entries > 32k chars are rejected (chunk before calling).
  • dimensions · number · optionnel
    Engineer mode: truncate each vector to this many leading dims (Matryoshka) + renormalize. Smaller, cheaper vectors.
  • corpus_adapter · boolean · optionnel
    Engineer mode: mean-center the batch (all-but-the-mean) to sharpen retrieval; returns the fitted adapter_mean.

  Exemple d'appel

  {"name": "iliad_embeddings", "arguments": {"input": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"usage": {}, "vectors": [], "engineer": {}, "model_used": "texte", "input_count": 1}}

• iliad_hygiene≈ 817 tokens

  AXIS-owned workspace hygiene grader. Analyzes an inline file set [{path,content}] and returns a letter grade (A-F) across a closed set of dimensions plus structured findings. Two modes: mode='scan' (DEFAULT, FREE) returns grade + findings (committed-secret scan, .env/secret-file detection, .gitignore gaps for build/scratch artifacts, oversized blobs, stub/placeholder markers, byte-identical duplicate files, source test-peer coverage, TODO/FIXME debt); mode='fix' (METERED, $0.05 standard / $0.02 lite) adds a prioritized remediation plan with ready-to-apply .gitignore additions and per-finding actions. Sending X-Agent-Mode: engineer always bills the fix-mode price, even if mode is 'scan' or omitted. Deterministic, dependency-free, never mutates your repo (fix returns a PLAN). Rules needing a live git checkout/toolchain (worktree pruning, build/vet, governance-source-of-truth checks, route-registration dup-handler analysis, ROI-queue coherence) are reported as repo_only_rules, not run. Engineer mode (X-Agent-Mode: engineer — Security Engineer, $5): the fix arrives as a git-applyable unified-diff patch (`patch`) + a SARIF 2.1.0 log for CI code-scanning (`sarif`). Requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (3)

  Paramètres

  • mode · string · optionnel · scan | fix
    scan (free grade+findings, default) | fix (metered, adds remediation plan).
  • files · array · requis
    Inline files [{path, content}] to scan (non-empty; each content <= 5 MB).
  • config · object · optionnel
    Optional threshold overrides: maxFileBytes, coverageA, coverageB, coverageC, todoDebtThreshold.

  Exemple d'appel

  {"name": "iliad_hygiene", "arguments": {"files": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"mode": "texte", "grade": "texte", "patch": "texte", "sarif": {}, "counts": {}, "reasons": [], "scanned": {}, "findings": [], "dimensions": [], "paid_fix_hint": "texte", "repo_only_rules": [], "remediation_plan": {}}}

• iliad_llm_inference≈ 938 tokens

  AXIS-hosted LLM chat-completion via node-llama-cpp + a small GGUF model loaded in-process. Two input shapes accepted: `prompt` (single string) or `messages` (chat-style array of {role, content}). Sampling controls: `max_tokens` (≤2048), `temperature` (0-2), `top_k`, `top_p`, `seed` (threaded through for more deterministic output — NOT a proven byte-identical guarantee; thread count isn't pinned and GGML's multi-threaded matmul reduction order isn't guaranteed bit-exact across runs), `stop` (string[]). Inference runs in-process — no upstream LLM provider call — but this AXIS tool call is still billed: $0.02 standard, $0.01 lite. Operator sets AXIS_LLM_MODEL_PATH to point at a Phi-3-mini / TinyLlama / Llama-3.2-1B GGUF; if missing, the tool returns a `_not_configured: true` envelope and is not billed. Engineer mode (X-Agent-Mode: engineer — Constrained Inference, $0.10): pass a `json_schema` and decoding is grammar-constrained to it AND the output is validated against it (returns a `structured` block with valid + parsed + schema_errors) — guaranteed-valid structured output. Requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (10)

  Paramètres

  • seed · number · optionnel
    Optional seed, threaded through with temperature for more deterministic output. Not a proven byte-identical guarantee (thread count/matmul reduction order isn't pinned) — see the tool description.
  • stop · array · optionnel
    Stop sequences. Generation halts when any string in the array is produced.
  • top_k · number · optionnel
    Top-k sampling (positive integer). Defaults 40.
  • top_p · number · optionnel
    Top-p nucleus sampling in (0, 1]. Defaults 0.95.
  • prompt · string · optionnel
    Single-prompt completion input. Use either this OR messages, not both.
  • system · string · optionnel
    Optional system prompt (prompt mode only). For messages mode, use role=system entries.
  • messages · array · optionnel
    Chat-style input. Array of {role: system|user|assistant, content: string}.
  • max_tokens · number · optionnel
    Max tokens to generate. Defaults 512, hard cap 2048.
  • json_schema · object · optionnel
    Engineer mode (required): a JSON Schema. Decoding is grammar-constrained to it and the output is validated against it; returns a `structured` block.
  • temperature · number · optionnel
    Sampling temperature in [0, 2]. Defaults 0.7.

  Exemple d'appel

  {"name": "iliad_llm_inference", "arguments": {"seed": 1, "stop": [], "top_k": 1, "top_p": 1, "prompt": "texte", "system": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "reason": "texte", "model_path": "texte", "model_used": "texte", "structured": {}, "remediation": "texte", "prompt_tokens": 1, "_not_configured": true, "completion_tokens": 1}}

• iliad_network_tokenization≈ 875 tokens

  Network-tokenization capability. (1) `lifecycle`: an EXECUTABLE TAP-style token-lifecycle state machine (provision → activate → suspend → resume → delete; deleted is terminal; illegal transitions are rejected with an error, not silently accepted) — pure simulation, no real payment method involved. (2) `capabilities` reports which providers are configured (env-derived). (3) `read` and (4) `provision` are TEMPORARILY DISABLED: both would resolve a caller-supplied payment_method_id/pan_source against the platform's Stripe account, and this service has no way yet to verify that id belongs to the calling AXIS account — calling either always returns a structured `_not_configured: true` envelope explaining this, never real payment-method data. (For context once re-enabled: `read`'s underlying Stripe adapter is fully implemented; direct VTS/MDES `provision` is additionally capability-gated behind a network-issued Token Requestor ID — AXIS_VTS_TOKEN_REQUESTOR_ID / AXIS_MDES_TOKEN_REQUESTOR_ID — plus network onboarding, and NEVER fakes a token.) Raw PANs are never accepted even when disabled (pan_source is documented as an opaque reference only). Free (unmetered); requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (6)

  Paramètres

  • event · string · optionnel
    lifecycle: single-event shorthand for `events: [event]`.
  • events · array · optionnel
    lifecycle: ordered TokenEvent list (provision|activate|suspend|resume|delete), max 100. Must start from provision; illegal transitions throw.
  • provider · string · optionnel · stripe | vts | mdes
    provision: ignored — this operation is disabled and always returns _not_configured.
  • operation · string · optionnel · read | provision | lifecycle | capabilities
    read (default, disabled) | provision (disabled) | lifecycle | capabilities.
  • pan_source · string · optionnel
    provision: ignored — this operation is disabled and always returns _not_configured. NEVER a raw PAN in any case.
  • payment_method_id · string · optionnel
    read: ignored — this operation is disabled and always returns _not_configured.

  Exemple d'appel

  {"name": "iliad_network_tokenization", "arguments": {"event": "texte", "events": [], "provider": "stripe", "operation": "read", "pan_source": "texte", "payment_method_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tool": "texte", "reason": "texte", "honesty": "texte", "lifecycle": {}, "operation": "texte", "remediation": "texte", "capabilities": {}, "_not_configured": true, "provider_checked": "texte"}}

• iliad_object_storage≈ 824 tokens

  AXIS-owned signed-URL minter backed by Cloudflare R2. Returns a pre-signed PUT or GET URL scoped to the calling account (keys are prefixed with `accounts/<account_id>/` server-side, so accounts can't reach each other's objects). Requires Authorization: Bearer <api_key>. Returns the URL plus expires_at (ISO 8601), bucket, and scoped_key. Returns `{_not_configured: true, ...}` when the operator has not provisioned R2_* env vars (no crash, no leaked secrets); not billed when not configured. Pricing: $0.01 standard, free in lite mode. TTL is capped at 86400 seconds (24h). Engineer mode (X-Agent-Mode: engineer — Managed Bucket, $0.05): adds delete + list + copy (server-side, no bytes through the agent) operations, content-addressed dedup keys (content_sha256), and mint-time PUT policy (pin content_type / exact content_length as signed headers R2 enforces). A signed GET URL minted here can be passed directly as iliad_document_parsing's document_url or iliad_speech_to_text's audio_url.

  Paramètres, retour & exemple (8)

  Paramètres

  • ext · string · optionnel
    Engineer mode: optional extension appended to the content-addressed key (e.g. 'png').
  • key · string · requis
    Object key (max 1024 chars), or the prefix for operation=list. Path traversal and leading-/ are rejected.
  • operation · string · requis · put | get | delete | list | copy
    put / get (standard). delete / list / copy and content-addressed put require X-Agent-Mode: engineer (Managed Bucket).
  • source_key · string · optionnel
    Engineer mode (operation=copy): source object key to copy from, scoped to your account; `key` is the destination. Echo the returned required_headers on the PUT.
  • ttl_seconds · number · optionnel
    Signed-URL lifetime, 1..86400. Defaults to 3600.
  • content_type · string · optionnel
    Engineer mode (put): pin the Content-Type the upload must send (signed; R2 rejects a mismatch). Printable ASCII type/subtype, ≤255 chars. Echo via required_headers.
  • content_length · number · optionnel
    Engineer mode (put): pin the EXACT byte size the upload must be (signed; ≤5 GiB). Pairs with content_sha256 for verified content-addressed writes.
  • content_sha256 · string · optionnel
    Engineer mode: 64-char hex sha256 of the bytes you'll PUT. When set, the object lands under accounts/<id>/cas/<sha256> so identical content dedupes.

  Exemple d'appel

  {"name": "iliad_object_storage", "arguments": {"key": "texte", "operation": "put"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "bucket": "texte", "operation": "texte", "expires_at": "texte", "scoped_key": "texte"}}

• iliad_speech_to_text≈ 880 tokens

  AXIS-owned audio transcription via whisper.cpp + ffmpeg-static. Accepts either `audio_url` (https URL we fetch, max 100 MiB, 60s download timeout) or `audio_base64` (inline bytes, max 100 MiB decoded) — exactly one. Accepts any audio format ffmpeg can decode (mp3, wav, m4a, opus, ogg, flac); we resample to 16 kHz mono WAV internally. Optional `language` (ISO-639-1 like "en" / "fr" / "ja", or "auto" — default). Optional `initial_prompt` (≤512 chars; biases spelling of rare names). Optional `word_timestamps` boolean. Returns `{text, segments: [{start, end, text}], language_detected, duration_seconds, model_used}`. Pricing: $0.03 standard, $0.01 lite. When operator hasn't installed whisper-cli or placed the GGML model file at AXIS_WHISPER_MODEL_PATH (default `models/ggml-base.en.bin`), returns `{_not_configured: true, reason, detail, remediation}` and is not billed. Engineer mode (X-Agent-Mode: engineer — Diarization, $0.10): the response adds `diarization` — speaker turns grouped from the segments by inter-segment pause gaps (tune with diarization_gap_seconds / max_speakers; this is pause-based turn segmentation, not acoustic speaker ID). Use iliad_text_to_speech to synthesize speech from text. Requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (7)

  Paramètres

  • language · string · optionnel
    ISO-639-1 language code (en, fr, ja, ...) or 'auto' to autodetect. Defaults 'auto'.
  • audio_url · string · optionnel
    https URL to an audio file. Use this OR audio_base64, not both.
  • audio_base64 · string · optionnel
    Base64-encoded audio bytes. Use this OR audio_url, not both.
  • max_speakers · number · optionnel
    Engineer mode: max alternating speaker labels. Defaults 2.
  • initial_prompt · string · optionnel
    Optional bias prompt (≤512 chars) — useful for spelling of rare names.
  • word_timestamps · boolean · optionnel
    Emit word-level timestamps within segments. Defaults false.
  • diarization_gap_seconds · number · optionnel
    Engineer mode: pause (seconds) between segments that starts a new speaker turn. Defaults 0.75.

  Exemple d'appel

  {"name": "iliad_speech_to_text", "arguments": {"language": "texte", "audio_url": "texte", "audio_base64": "texte", "max_speakers": 1, "initial_prompt": "texte", "word_timestamps": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"text": "texte", "reason": "texte", "segments": [], "model_used": "texte", "diarization": [], "remediation": "texte", "_not_configured": true, "duration_seconds": 1, "language_detected": "texte"}}

• iliad_text_to_speech≈ 938 tokens

  AXIS-owned voice synthesis via Piper (rhasspy/piper) + ffmpeg-static. Accepts `text` (1-5000 chars), optional `voice` slug (filename without extension; defaults to AXIS_PIPER_DEFAULT_VOICE or the first available voice), optional `format` (wav | mp3 | opus; defaults wav), optional `sentence_silence` (0-5 seconds, default 0.2). Returns `{audio_base64, format, voice_used, sample_rate, duration_seconds, byte_size}`. Inference runs in-process — no upstream provider call — but this AXIS tool call is still billed: $0.02 standard, $0.01 lite. When operator hasn't installed piper or placed voice .onnx + .onnx.json files in AXIS_PIPER_VOICE_DIR (default models/piper/), returns `{_not_configured: true, reason, detail, remediation}` and is not billed. format=mp3/opus additionally requires ffmpeg-static. Engineer mode (X-Agent-Mode: engineer — Brand Voice, $0.10): requires `brand_text` (a brand / voice-and-tone artifact — the call throws without it in engineer mode) and AXIS auto-derives the voice persona (Piper voice slug + sentence pacing) and synthesizes in it; the persona is echoed in the response. Use iliad_speech_to_text to transcribe audio back to text. Requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (7)

  Paramètres

  • text · string · requis
    Text to speak. 1-5000 chars after trim.
  • voice · string · optionnel
    Voice slug (filename without extension, e.g. 'en_US-amy-medium'). Defaults to first available voice or AXIS_PIPER_DEFAULT_VOICE.
  • format · string · optionnel · wav | mp3 | opus
    Audio codec.
  • gender · string · optionnel · female | male
    Engineer mode: persona gender override.
  • locale · string · optionnel · us | gb
    Engineer mode: persona locale override.
  • brand_text · string · optionnel
    Required when X-Agent-Mode: engineer is set (the call throws without it); ignored otherwise. Brand / voice-and-tone artifact — AXIS derives a voice persona from it and synthesizes in that voice (overrides voice/sentence_silence).
  • sentence_silence · number · optionnel
    Per-sentence silence in seconds (0-5). Defaults 0.2.

  Exemple d'appel

  {"name": "iliad_text_to_speech", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"format": "texte", "reason": "texte", "persona": {}, "byte_size": 1, "voice_used": "texte", "remediation": "texte", "sample_rate": 1, "audio_base64": "texte", "_not_configured": true, "duration_seconds": 1}}

• iliad_transactional_email≈ 652 tokens

  Send a single transactional email. Requires Authorization: Bearer <api_key>. Provide either body_html, body_text, or both (Resend will pick the best variant per recipient). All emails ship from RESEND_FROM_ADDRESS — operator must verify that domain in Resend before sending. Returns the provider-assigned message_id plus the accepted recipient list. Pricing: $0.02 standard, $0.01 lite. Returns a structured _not_configured envelope when RESEND_API_KEY or RESEND_FROM_ADDRESS is missing, and is not billed. Recipients capped at 50 per call; subject capped at 998 chars; bodies capped at 1 MB. Engineer mode (X-Agent-Mode: engineer — Deliverability, $0.50): instead of sending, pass a `domain` and get a full SPF/DKIM/DMARC setup (fresh DKIM keypair) + sender warmup schedule + verification checklist — no email sent, no ESP key needed.

  Paramètres, retour & exemple (9)

  Paramètres

  • to · string|array · optionnel
    Recipient address or array of addresses (max 50). Required for a send (standard mode).
  • domain · string · optionnel
    Engineer mode (Deliverability): domain to generate SPF/DKIM/DMARC setup for. Replaces the send.
  • subject · string · optionnel
    Email subject (max 998 chars, RFC 5322).
  • provider · string · optionnel
    Engineer mode: ESP for the SPF include (resend/sendgrid/mailgun/postmark/ses/google). Defaults resend.
  • reply_to · string · optionnel
    Optional Reply-To address.
  • body_html · string · optionnel
    HTML body. At least one of body_html / body_text required.
  • body_text · string · optionnel
    Plaintext body. At least one of body_html / body_text required.
  • dmarc_policy · string · optionnel
    Engineer mode: DMARC policy none|quarantine|reject. Defaults none (monitoring).
  • dkim_selector · string · optionnel
    Engineer mode: DKIM selector (alphanumeric/hyphen, 1-32). Defaults 'axis'.

  Exemple d'appel

  {"name": "iliad_transactional_email", "arguments": {"to": [], "domain": "texte", "subject": "texte", "provider": "texte", "reply_to": "texte", "body_html": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"from": "texte", "subject": "texte", "message_id": "texte", "delivered_to": []}}

• iliad_vector_database≈ 803 tokens

  AXIS-owned vector store. Two operations: `upsert` (insert or replace vectors) and `query` (cosine top-k nearest neighbors). Namespaces are account-scoped server-side (`acct:<account_id>:<namespace>`), so tenants cannot read each other's vectors. Persistent across restarts via Postgres. Requires Authorization: Bearer <api_key>. Pricing: $0.01 standard, free in lite mode. Best for RAG retrievers, deduplication, and similarity search. Use iliad_embeddings to turn text into the vectors this tool stores and queries. Engineer mode (X-Agent-Mode: engineer — Managed Memory, $0.05): query runs a pgvector/HNSW ANN candidate pool with optional recency-decay reranking (recency_half_life_days — managed forgetting), RRF hybrid fusion (sparse_ids), and metadata filter; upsert applies intra-batch semantic-dedup (dedup_threshold).

  Paramètres, retour & exemple (6)

  Paramètres

  • query · object · optionnel
    {vector: number[], top_k?: number, filter?: object}. Engineer mode also reads recency_half_life_days (number — exponential recency decay) and sparse_ids (string[] — RRF hybrid fusion). Required for query.
  • vectors · array · optionnel
    Array of {id, vector, metadata?} — required for upsert.
  • namespace · string · optionnel
    Logical isolation key. Defaults to 'default'. Account ID is always prepended server-side.
  • operation · string · requis · upsert | query
    upsert (insert/replace) or query (top-k cosine).
  • semantic_dedup · boolean · optionnel
    Engineer upsert: set false to disable dedup (default on).
  • dedup_threshold · number · optionnel
    Engineer upsert: cosine threshold for intra-batch semantic-dedup (default 0.97).

  Exemple d'appel

  {"name": "iliad_vector_database", "arguments": {"operation": "upsert"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"backend": "texte", "matches": [], "engineer": {}, "upserted": 1, "namespace": "texte", "operation": "texte", "semantic_dedup": {}, "total_in_namespace": 1}}

• iliad_web_research≈ 434 tokens

  Scrape a single URL with AXIS's owned crawler (SSRF-guarded fetch, robots.txt-aware, readability extraction — no third-party key) and return markdown-formatted content. Honest scope: fetches static HTML only, no JavaScript rendering, so client-rendered SPA pages may extract thin content. Returns markdown body, extracted metadata, and title. Best for research, documentation reading, or SEO analysis. Requires Authorization: Bearer <api_key>. Pricing: $0.10 per page. Lite mode carries no discount here — the markdown output is identical in both modes. If the operator's backend configuration is incomplete, this call returns {_not_configured:true} instead of scraping, and is not billed. Use iliad_web_research_crawl for crawling multiple pages or link following. To make a scraped page searchable later, index it with iliad_web_search.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    The URL to scrape (http or https)
  • only_main_content · boolean · optionnel
    Extract only the main content (default: true)

  Exemple d'appel

  {"name": "iliad_web_research", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "error": "texte", "success": true}}

• iliad_web_research_crawl≈ 476 tokens

  Crawl a domain with AXIS's owned crawler — a same-origin BFS frontier with robots.txt compliance and per-host politeness, no third-party key — and scrape multiple pages. Honest scope: static HTML only, no JavaScript rendering. Returns array of scraped pages with markdown content. Best for site mapping, content audits, or bulk research. Requires Authorization: Bearer <api_key>. Pricing: $0.01/page beyond your account's shared 100-page/month free pool (standard and lite) — a crawl fully covered by the free pool costs $0.00; a fully-paid 100-page crawl costs up to $1.00. If the operator's backend configuration is incomplete, this call returns {_not_configured:true} instead of crawling, and is not billed. Use iliad_web_research for single-page scrapes. To make crawled pages searchable later, index them with iliad_web_search.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    The domain/URL to crawl (http or https)
  • limit · number · optionnel
    Maximum pages to crawl (1-100, default: 10)

  Exemple d'appel

  {"name": "iliad_web_research_crawl", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": {}, "error": "texte", "success": true}}

• iliad_web_search≈ 816 tokens

  AXIS-owned BM25 search engine over the corpus YOUR account has indexed. NOT a Google/Bing scraper — agents build their own searchable index by first calling operation='index' with documents (often pages fetched via iliad_web_research), then querying with operation='search'. Five operations: `index` (insert one or many documents), `search` (BM25 top-k ranked hits with snippet + score + metadata), `delete` (drop one doc), `delete_namespace` (drop all), `count`. Namespaces are account-scoped server-side (`acct:<id>:<namespace>`). Persistent across restarts via Postgres (the shared @axis/snapshots database). Search supports `max_results` (default 10, max 100) and `site` (restrict to a single URL host, case-insensitive). Only operation='search' is billed ($0.01 standard, free in lite mode) — index, delete, delete_namespace, and count are always free. Engineer mode (X-Agent-Mode: engineer — Answer Engine, $0.25): search also returns a grounded extractive answer with [n] citation spans over your corpus, reranked, refusing on weak evidence. Requires Authorization: Bearer <api_key>.

  Paramètres, retour & exemple (8)

  Paramètres

  • site · string · optionnel
    Filter to a single URL host (e.g. 'docs.python.org', case-insensitive).
  • query · string · optionnel
    Search query (1-1024 chars). Required in search mode.
  • doc_id · string · optionnel
    Document id to remove. Required in delete mode.
  • document · object · optionnel
    Single document {doc_id, url?, title?, content, metadata?} — used in index mode (alternative to documents[]).
  • documents · array · optionnel
    Batch of documents (max 100). Transactional — malformed entry aborts the whole call.
  • namespace · string · optionnel
    Logical isolation key. Defaults 'default'. Account id is always prepended server-side.
  • operation · string · requis · index | search | delete | delete_namespace | count
    index | search | delete | delete_namespace | count.
  • max_results · number · optionnel
    Cap on hits returned. Defaults 10, max 100.

  Exemple d'appel

  {"name": "iliad_web_search", "arguments": {"operation": "index"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"hits": [], "query": "texte", "total": 1, "indexed": 1, "removed": true, "namespace": "texte", "operation": "texte", "total_in_namespace": 1}}

• improve_my_agent_with_axis≈ 398 tokens

  Analyze an agent codebase and return a prioritized AXIS hardening plan. Requires Authorization: Bearer <api_key> but has no usage charge on any tier — free and unmetered, unlike most AXIS tools. This creates a snapshot and may return auth, quota, file-limit, or validation errors. Example: pass your agent source files to see missing AGENTS.md, CLAUDE.md, and MCP config gaps. Use this when you want recommendations and missing-context detection. Use analyze_files instead when you want the full artifact bundle directly (paid: $3.00 standard).

  Paramètres, retour & exemple (2)

  Paramètres

  • files · array · requis
    Source files of the agent to analyze
  • project_name · string · requis
    Name of the agent/project to improve

  Exemple d'appel

  {"name": "improve_my_agent_with_axis", "arguments": {"files": [], "project_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"analysis": {}, "call_again": {}, "mcp_config": {}, "snapshot_id": "texte", "project_name": "texte", "improvement_plan": {}}}

• list_programs≈ 344 tokens

  Inventory mode. List all 21 AXIS programs, their generators, pricing tier, and artifact paths. Free, no auth, and no side effects. Use search_and_discover_tools instead when you only have a keyword, or get_install_manifest when you need install and onboarding metadata.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_programs", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"programs": [], "pro_programs": [], "free_programs": [], "total_programs": 1, "total_generators": 1, "free_artifact_count": 1, "programs_with_free_artifacts": []}}

• ping_payment≈ 358 tokens

  Exercise the real x402 payment-flow loop at a nominal $0.01 — the cheapest metered call on this server, priced just above $0 so the probe can't be run up for free without limit. Call it once with no payment credential (no auth required) to receive a 402-style payment_required challenge (the exact same shape every real paid tool returns, and requesting it is itself free); retry the same tools/call carrying a payment credential in Authorization (with your API key moved to X-Axis-Key) to settle at $0.01 and get a success envelope. Learn the vocabulary here before paying real money for prepare_agentic_purchasing or analyze_repo. No side effects on any other tool, no real payment rail is ever touched.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "ping_payment", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "tool": "texte", "message": "texte", "price_usd": "texte", "settled_cents": 1, "_payment_required": true}}

• prepare_agentic_purchasing≈ 960 tokens

  Prepare a codebase for agentic purchasing and return a readiness score plus commerce artifacts. Requires Authorization: Bearer <api_key>; paid analysis records a new snapshot and may return auth, quota, payment, file-limit, or validation errors. Pricing: $3.00 standard, $1.00 lite budget mode, $250 engineer per run. Lite mode returns the readiness score + top 3 gaps only, with an artifacts_note pointing at standard mode for the full artifact bundle — it does NOT include the artifacts themselves. Standard and engineer modes return the full bundle. focus_areas is recorded and echoed back in the response for the caller's own bookkeeping; it does not filter which artifacts are generated. Use this when you need AP2/UCP/Visa, CE 3.0 dispute evidence, checkout, dispute, and negotiation hardening. Engineer mode (X-Agent-Mode: engineer — Commerce Integration) also emits a deployable x402/AP2/PAI'D endpoint + a runnable sandbox test + a schema-validatable CE 3.0 pack + a transparent dispute-readiness score (a working integration, not just a score), plus a deployable Stripe network-token read adapter when a stripe signal is detected. Use discover_agentic_purchasing_needs instead when you only need workflow triage.

  Paramètres, retour & exemple (11)

  Paramètres

  • files · array · requis
    Array of {path, content} objects representing source files
  • focus · string · optionnel · full | purchasing | security | optimization
    Analysis focus (default: purchasing)
  • goals · array · requis
    Project goals
  • agent_type · string · optionnel
    Consuming agent type hint
  • frameworks · array · requis
    Detected or known frameworks
  • focus_areas · array · optionnel
    Compliance focus areas, recorded and echoed back in the response for the caller's own reference — does not filter which artifacts are generated.
  • project_name · string · requis
    Name of the project
  • project_type · string · requis
    Project type (web_application, api_service, cli_tool, library, monorepo)
  • referral_token · string · optionnel
    Optional referral token from another agent
  • spending_window · string · optionnel · per_call | hourly | daily | monthly
    Agent spending window
  • budget_per_run_cents · number · optionnel
    Agent budget for this call in cents

  Exemple d'appel

  {"name": "prepare_agentic_purchasing", "arguments": {"files": [], "goals": [], "frameworks": [], "project_name": "texte", "project_type": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "summary": {}, "project_id": "texte", "snapshot_id": "texte", "artifact_count": 1, "programs_executed": []}}

• prepare_agentic_purchasing_preview≈ 516 tokens

  Compute a free Purchasing Readiness Score (0-100) and gap list for a codebase without generating artifacts. No auth, no charge, no snapshot persisted. Hard caps: 25 files / 50KB per file / 1MB total. Returns score, risk_level, top gaps, frameworks detected, and which AXIS programs would close which gaps. Use this to triage 'should I pay for the full hardening bundle?' before calling prepare_agentic_purchasing. The paid version generates the full artifact bundle including CE 3.0 dispute evidence, SCA exemption matrix, and TAP interop.

  Paramètres, retour & exemple (4)

  Paramètres

  • files · array · requis
    Source files to triage (max 25 files, 50KB each, 1MB total)
  • frameworks · array · optionnel
    Optional framework hints
  • project_name · string · requis
    Name of the project being previewed
  • project_type · string · optionnel
    Optional project type hint (web_application, api_service, cli_tool, library, monorepo)

  Exemple d'appel

  {"name": "prepare_agentic_purchasing_preview", "arguments": {"files": [], "project_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"cost": "texte", "gaps": [], "score": 1, "strengths": [], "conversion": {}, "risk_level": "low", "top_3_gaps": [], "interpretation": "texte", "frameworks_detected": [], "what_axis_would_add": []}}

• roblox_compliance_check≈ 398 tokens

  Run Roblox R15 compliance checks against a mesh. Status: **planned_proxy** — an estate-flagged proxy is planned (see discover_estate_tools for the sibling's own direct endpoint and price today). Calls return a planned-capability envelope pointing at AXIS Foundry (https://api.avatar.jonathanarvay.com/mcp) as the recommended interim provider. When the estate proxy ships, the dispatch handler swaps in without changing this schema.

  Paramètres, retour & exemple (1)

  Paramètres

  • file_path · string · requis
    Path to mesh file (.glb, .obj, .stl, etc.)

  Exemple d'appel

  {"name": "roblox_compliance_check", "arguments": {"file_path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": {}, "status": "texte", "message": "texte", "_planned": true, "capability_id": "texte", "recommended_provider": {}}}

• sca_exemption_decision≈ 715 tokens

  Decide the lighter-SCA path for a single transaction using AXIS's published 7-priority PSD2 exemption matrix (the same decideScaExemption engine that renders the SCA Exemption Decision Matrix in generated artifacts). Input: amount_eur (required, PSD2 thresholds are EUR-denominated — convert before calling) plus optional context flags (secure corporate program, MIT, fixed recurring + prior SCA, trusted beneficiary + prior SCA, one-leg-out, acquirer TRA fraud rate in basis points). Returns the chosen exemption, its priority, sca_required, rationale, fallback path, all applicable candidates, the rendered priority matrix, and a sha256 reproducibility proof. Free, no auth, deterministic, no side effects. HONESTY: decision-support only, NOT an authorization oracle — final exemption eligibility is decided by the acquirer/issuer; TRA caps use published EBA RTS Art. 15 bands, not your acquirer's live fraud rate.

  Paramètres, retour & exemple (8)

  Paramètres

  • amount_eur · number · requis
    Transaction amount in EUR (PSD2 thresholds are EUR-denominated).
  • has_prior_sca · boolean · optionnel
    A prior SCA exists — gates recurring_fixed and trusted_beneficiary.
  • is_one_leg_out · boolean · optionnel
    Payer or payee outside the EEA (territorial scope, not a formal exemption).
  • is_recurring_fixed · boolean · optionnel
    Fixed-amount subsequent collection (RTS Art. 13). Requires has_prior_sca.
  • is_secure_corporate · boolean · optionnel
    Dedicated/lodged corporate card program (RTS Art. 16).
  • is_merchant_initiated · boolean · optionnel
    MIT with stored credential + original SCA reference (out of SCA scope).
  • is_trusted_beneficiary · boolean · optionnel
    Merchant on the cardholder's trusted list (RTS Art. 12). Requires has_prior_sca.
  • tra_acquirer_fraud_bps · number · optionnel
    Acquirer reference fraud rate in basis points (EBA RTS Art. 15 bands: <=1 → €500 cap, <=6 → €250, <=13 → €100).

  Exemple d'appel

  {"name": "sca_exemption_decision", "arguments": {"amount_eur": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"proof": {}, "caveat": "texte", "matrix": "texte", "decision": {}}}

• score_dispute_readiness≈ 564 tokens

  Score how ready a disputed transaction's EVIDENCE FILE is for representment, per Visa reason-code family, using the transparent scoreWinProbability heuristic (win-prob-v0: hand-set, documented logistic coefficients — exported, inspectable, monotonic in evidence). Input: reason_code + the evidence on file (CE 3.0 eligibility, matching data elements, prior undisputed transactions, delivery proof, AVS/CVV, 3DS, signed mandate, customer communication). Returns the heuristic score, band, top missing evidence (what to capture next), recommended action, rationale, model version, and a sha256 reproducibility proof. Free, no auth, deterministic. HONESTY (read this): this scores evidence-capture readiness and is NOT a dispute-win prediction — the v0 heuristic is NOT empirically calibrated against real network outcomes, is NOT a Visa-published or Visa-endorsed win rate, and AXIS does not publish win-rate estimates. Treat it as a prioritization signal for evidence gathering only; always follow your operator's dispute policy.

  Paramètres, retour & exemple (2)

  Paramètres

  • evidence · object · optionnel
    Evidence on file: {ce3Eligible?, matchingDataElements? (0-5), priorUndisputedTransactions? (0-10), hasDeliveryProof?, hasAvsMatch?, hasCvvMatch?, has3dsAuthenticated?, hasSignedMandate?, hasCustomerCommunication?}. Omitted fields default to false/0.
  • reason_code · string · requis
    Visa dispute reason code (e.g. '10.4', '13.1', '12.5'). Unknown codes fall back to a documented default family.

  Exemple d'appel

  {"name": "score_dispute_readiness", "arguments": {"reason_code": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"proof": {}, "readiness": {}, "disclaimer": "texte"}}

• search_and_discover_tools≈ 397 tokens

  Search AXIS programs by keyword and return ranked matches with artifact paths. Free, no auth, and no stateful side effects. Example: q=checkout returns commerce-relevant programs first. Use this when you know the outcome you want but not the right program. Use list_programs instead for the full catalog, get_install_manifest for install metadata, or discover_agentic_purchasing_needs for purchasing-specific triage.

  Paramètres, retour & exemple (2)

  Paramètres

  • q · string · optionnel
    Search query — keyword or phrase
  • program · string · optionnel
    Optional: filter results to a specific program name

  Exemple d'appel

  {"name": "search_and_discover_tools", "arguments": {"q": "texte", "program": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"query": "texte", "results": [], "total_matches": 1, "program_filter": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.iliad.trustfabric.ai/mcp