io.github.Humanleap/toolrouter

Est-ce que io.github.Humanleap/toolrouter est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.Humanleap/toolrouter » 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 48 outils

• account_list≈ 151 tokens

  List all billing contexts (personal + teams) or get detail on one. No slug → summary list. With slug → full detail including team members, role, subscription status, and pointers to the team's connectors, credentials, keys, and files.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · optionnel
    Account slug for detail view. Omit to list all.

  Exemple d'appel

  {"name": "account_list", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• account_preferences≈ 308 tokens

  Read or write billing preferences (auto-reload, budget cap, default context). Pass action: "get" to read, action: "set" with fields to write.

  Paramètres, retour & exemple (6)

  Paramètres

  • action · string · requis · get | set
    "get" to read preferences, "set" to update them.
  • budget_limit · number|null · optionnel
    Monthly spending cap in USD, or null to remove (set only).
  • auto_reload_amount · number · optionnel
    Amount (USD) to reload when triggered (set only, max 500).
  • auto_reload_enabled · boolean · optionnel
    Enable or disable auto-reload (set only).
  • auto_reload_threshold · number · optionnel
    Balance threshold (USD) that triggers a reload (set only).
  • default_billing_context · string · optionnel
    Default account to bill (set only). "personal" or "team:<id>".

  Exemple d'appel

  {"name": "account_preferences", "arguments": {"action": "get"}}

  Exemple de retour

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

• account_setup≈ 121 tokens

  Initialize or re-check your account, provision it when needed, and return your user ID and plan. CALL THIS FIRST when the user asks to set up ToolRouter, connect their account, check their account status, or get started.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "account_setup", "arguments": {}}

  Exemple de retour

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

• account_switch≈ 127 tokens

  Set the active billing context. Accepts a slug (e.g. "personal", "team:nd7fx…") or team ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · requis
    Account slug or team ID to switch to (e.g. "personal", "team:nd7fx…").

  Exemple d'appel

  {"name": "account_switch", "arguments": {"context": "texte"}}

  Exemple de retour

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

• brain_add≈ 371 tokens

  Create a new brain page. Knowledge you add here will be available to all future tool calls. Optional wing/room/hall organise the page in the MemPalace hierarchy for sharper retrieval.

  Paramètres, retour & exemple (8)

  Paramètres

  • hall · string · optionnel
    Optional. One of "fact", "event", "discovery", "preference", "advice". Defaults to "fact".
  • room · string · optionnel
    Optional. Sub-area within the wing (e.g. "databases", "deploy"). Defaults to "untagged".
  • tags · array · optionnel
    Tags for categorisation
  • wing · string · optionnel
    Optional. Top-level area (e.g. "engineering", "family", "general"). Auto-classified if omitted.
  • scope · string · optionnel · personal | team
    Visibility scope. Defaults to personal.
  • title · string · requis
    Page title
  • content · string · requis
    Page content (markdown)
  • load_tier · string · optionnel · L0 | L1 | L2 | L3
    Optional. L0 = operator identity (rare), L1 = always-loaded critical fact, L2 = default on-demand, L3 = cold archive. Omit to default to L2.

  Exemple d'appel

  {"name": "brain_add", "arguments": {"title": "texte", "content": "texte"}}

  Exemple de retour

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

• brain_admin≈ 425 tokens

  Brain admin operations. Pass action: "lint" | "link" | "promote" | "rebuild_index" | "team_sleep". team_sleep enables/disables/runs the nightly team consolidation cycle — pass sub_action "enable" (with optional timezone), "disable", "status", or "run_now". Team admin role required for team_sleep actions.

  Paramètres, retour & exemple (8)

  Paramètres

  • label · string · optionnel
    Human-readable relationship label (for link).
  • action · string · requis · lint | link | promote | rebuild_index | team_sleep
    Admin operation to perform.
  • page_id · string · optionnel
    Source brain page ID (for link/promote).
  • team_id · string · optionnel
    Team to promote to (for promote). Auto-resolved if on one team.
  • timezone · string · optionnel
    IANA timezone for team_sleep enable (e.g. "Europe/London"). Defaults to UTC. Sleep fires at 3 AM local time.
  • sub_action · string · optionnel · enable | disable | status | run_now
    Required for action="team_sleep". "enable" turns on nightly sleep for the team; "disable" turns it off; "status" shows last run and schedule; "run_now" triggers an immediate sleep cycle.
  • to_page_id · string · optionnel
    Target page ID (for link).
  • relationship · string · optionnel
    Relationship type (for link, e.g. relates_to, derived_from).

  Exemple d'appel

  {"name": "brain_admin", "arguments": {"action": "lint"}}

  Exemple de retour

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

• brain_delete≈ 114 tokens

  Archive a brain page. It will no longer appear in searches or tool consultations.

  Paramètres, retour & exemple (1)

  Paramètres

  • page_id · string · requis
    Brain page ID (bp_...) to archive

  Exemple d'appel

  {"name": "brain_delete", "arguments": {"page_id": "texte"}}

  Exemple de retour

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

• brain_expand≈ 186 tokens

  Retrieve the verbatim source text (a "drawer") linked from a brain page. Use this when a summary lacks specifics you need — drawers contain the original tool output, redacted for credentials. Returns 404 if the page has no linked drawer (not all pages do — drawers are a Step 4 feature for allowlisted tools only).

  Paramètres, retour & exemple (1)

  Paramètres

  • page_id · string · requis
    Brain page ID (bp_...) whose drawer to expand.

  Exemple d'appel

  {"name": "brain_expand", "arguments": {"page_id": "texte"}}

  Exemple de retour

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

• brain_lint≈ 90 tokens

  Run maintenance checks on your brain: find stale pages, orphaned knowledge, and other issues.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "brain_lint", "arguments": {}}

  Exemple de retour

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

• brain_query≈ 386 tokens

  Search your knowledge brain for relevant information. Returns pages ranked by relevance. Optional wing/hall narrow the search to a slice of the brain (e.g. wing="engineering", hall="preference").

  Paramètres, retour & exemple (7)

  Paramètres

  • hall · string · optionnel
    Optional. Restrict to a hall: "fact", "event", "discovery", "preference", or "advice".
  • wing · string · optionnel
    Optional. Restrict to a specific wing (top-level area like "engineering", "family").
  • as_of · string · optionnel
    Optional. ISO-date string (e.g. "2026-01-15"). When set, returns pages that were valid at that point in time — including superseded versions. Useful for "what did we know in January?" queries.
  • limit · number · optionnel
    Max results. Defaults to 10.
  • query · string · optionnel
    Search query. Omit to list all pages by recency.
  • scope · string · optionnel · personal | team | all
    Which brain scope to search. Defaults to all.
  • include_drawer_previews · boolean · optionnel
    Optional. When true, each result includes the first ~400 chars of its linked drawer (raw source text) if one exists. Useful to decide whether to call brain_expand for the full text.

  Exemple d'appel

  {"name": "brain_query", "arguments": {"hall": "texte", "wing": "texte", "as_of": "texte", "limit": 1, "query": "texte", "scope": "personal"}}

  Exemple de retour

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

• brain_settings≈ 190 tokens

  View and toggle your brain settings. Currently supports: drawers_enabled (store raw tool output alongside summaries for richer recall).

  Paramètres, retour & exemple (3)

  Paramètres

  • value · boolean · optionnel
    New value (required for "set").
  • action · string · requis · get | set
    "get" lists current settings; "set" toggles a named setting.
  • setting · string · optionnel
    Setting name (required for "set"). Currently: "drawers_enabled".

  Exemple d'appel

  {"name": "brain_settings", "arguments": {"action": "get"}}

  Exemple de retour

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

• brain_status≈ 87 tokens

  View brain page counts and recent pages for your personal and team brain.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "brain_status", "arguments": {}}

  Exemple de retour

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

• brain_update≈ 475 tokens

  Edit an existing brain page's content or metadata. wing/room/hall can be patched to re-file a page. scope can be changed to move a page between your personal and team brain — useful when an auto-ingested page landed in the wrong place. Moving a page to team scope requires team admin role.

  Paramètres, retour & exemple (10)

  Paramètres

  • hall · string · optionnel
    Optional. Change hall: fact / event / discovery / preference / advice.
  • room · string · optionnel
    Optional. Re-file under a different room.
  • tags · array · optionnel
    New tags
  • wing · string · optionnel
    Optional. Re-file under a different wing.
  • scope · string · optionnel · personal | team
    Optional. Move the page between your personal and team brain. Moving TO team requires team admin role and a team billing context. Moving FROM team to personal is allowed if you own the page or are an admin.
  • title · string · optionnel
    New title
  • content · string · optionnel
    New content (replaces existing)
  • page_id · string · requis
    Brain page ID (bp_...)
  • load_tier · string · optionnel · L0 | L1 | L2 | L3
    Optional. Change load tier. L1 promotes a page to always-loaded; L3 sends it to cold archive.
  • material_change · boolean · optionnel
    Optional. When true, creates a new version of the page — the old version is preserved with a timestamp and a "supersedes" link. Use for corrections or significant changes; skip for minor edits. Default false.

  Exemple d'appel

  {"name": "brain_update", "arguments": {"page_id": "texte"}}

  Exemple de retour

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

• brain_wings≈ 168 tokens

  List the wings of your brain — the top-level areas your knowledge is organised under (e.g. "engineering", "family"). For each wing returns the rooms and halls inside, page count, and last-updated time. Use this to discover the right wing/hall to pass to brain_query.

  Paramètres, retour & exemple (1)

  Paramètres

  • include_team · boolean · optionnel
    If true, also count team-scope pages. Default false (personal only).

  Exemple d'appel

  {"name": "brain_wings", "arguments": {"include_team": true}}

  Exemple de retour

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

• connector_add≈ 360 tokens

  Connect a new OAuth account or MCP server. For OAuth: pass type: "oauth", kind: "slack". For MCP catalog: pass catalog_slug. For custom MCP: pass url + auth_type.

  Paramètres, retour & exemple (10)

  Paramètres

  • url · string · optionnel
    MCP server endpoint URL (custom MCP).
  • kind · string · optionnel
    OAuth connector kind (e.g. "slack", "notion"). Required for type: "oauth".
  • slug · string · optionnel
    Short identifier for the connection.
  • type · string · optionnel · oauth | mcp
    Type of connector to add.
  • billing · string · optionnel
    Scope: "personal" (default), "team" (auto-resolves), a team slug, or "team:<id>".
  • auth_type · string · optionnel · none | bearer | header_key
    Auth type (custom MCP). Default: none.
  • auth_token · string · optionnel
    Auth token or API key.
  • header_name · string · optionnel
    Custom header name (for header_key auth).
  • catalog_slug · string · optionnel
    MCP catalog slug for one-click connect.
  • display_name · string · optionnel
    Human-readable name (custom MCP).

  Exemple d'appel

  {"name": "connector_add", "arguments": {"url": "texte", "kind": "texte", "slug": "texte", "type": "oauth", "billing": "texte", "auth_type": "none"}}

  Exemple de retour

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

• connector_list≈ 240 tokens

  List connected accounts and MCP servers (summary) or detail on one connector. Pass slug for detail including every tool the connector exposes. Optional type: "oauth" | "mcp" filter. Pass include_available: true to also see available catalog MCPs you can connect.

  Paramètres, retour & exemple (4)

  Paramètres

  • slug · string · optionnel
    Connector slug for detail view. Omit to list all.
  • type · string · optionnel · oauth | mcp
    Filter by connector type.
  • context · string · optionnel
    Scope: "personal" (default) or "team:<id>" for a team.
  • include_available · boolean · optionnel
    When true, also include catalog MCPs you have not connected yet.

  Exemple d'appel

  {"name": "connector_list", "arguments": {"slug": "texte", "type": "oauth", "context": "texte", "include_available": true}}

  Exemple de retour

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

• connector_permissions≈ 612 tokens

  View or set permissions for tools on a connected MCP server — which tools are allowed, rate limits, budget caps, argument restrictions. Pass the connector slug (from connector_list) and action: "list" to see current rules, or action: "set" with tool_name + rules to update one. Team scope requires admin role.

  Paramètres, retour & exemple (15)

  Paramètres

  • slug · string · requis
    Connector slug.
  • action · string · optionnel · list | set
    Omit to list permissions for all tools. Pass "set" with tool_name + rules to update one.
  • allowed · boolean · optionnel
    Whether the tool is allowed (for set).
  • billing · string · optionnel
    Scope: "personal", "team" (auto-resolves if on one team), a team slug, or "team:<id>".
  • tool_name · string · optionnel
    Tool name (for set). Use "*" for all tools on this connector.
  • cost_per_call · number · optionnel
    Cost in millicents per call (for set).
  • budget_per_day · number · optionnel
    Max daily spend per user, in millicents (for set).
  • nl_filter_mode · string · optionnel · strict | advisory
    How to enforce NL rules: strict (block on violation) or advisory (log only). Default: strict.
  • arg_schema_rules · string · optionnel
    JSON Schema validating tool arguments (for set). Example: {"properties":{"channel":{"enum":["#general"]}}}
  • rate_limit_per_day · number · optionnel
    Max calls per day, per user (for set).
  • rate_limit_per_hour · number · optionnel
    Max calls per hour, per user (for set).
  • team_budget_per_day · number · optionnel
    Max daily spend team-wide, in millicents (for set).
  • team_rate_limit_per_day · number · optionnel
    Max calls per day, team-wide (for set).
  • team_rate_limit_per_hour · number · optionnel
    Max calls per hour, team-wide (for set).
  • arg_natural_language_rules · string · optionnel
    Plain English rules for argument filtering (for set). Example: "Only allow queries for the last 90 days."

  Exemple d'appel

  {"name": "connector_permissions", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• connector_remove≈ 164 tokens

  Disconnect a connector. Pass slug.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Connector slug to disconnect.
  • type · string · optionnel · oauth | mcp
    Type of connector (mcp or oauth). Default: mcp.
  • billing · string · optionnel
    Scope: "personal" (default), "team" (auto-resolves), a team slug, or "team:<id>".

  Exemple d'appel

  {"name": "connector_remove", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• credential_default≈ 164 tokens

  Set the default value for a multi-value credential.

  Paramètres, retour & exemple (3)

  Paramètres

  • name · string · requis
    Credential name (e.g. "ios_app_id").
  • label · string · requis
    Label of the entry to make default (e.g. "Production").
  • context · string · optionnel
    "personal" or "team:<id>". Defaults to personal.

  Exemple d'appel

  {"name": "credential_default", "arguments": {"name": "texte", "label": "texte"}}

  Exemple de retour

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

• credential_delete≈ 193 tokens

  Remove a saved credential. If label is provided, removes only that specific entry. If no label, removes ALL entries for that credential name.

  Paramètres, retour & exemple (3)

  Paramètres

  • name · string · requis
    Credential name to delete (e.g. "ios_app_id").
  • label · string · optionnel
    Label of the specific entry to delete. Omit to remove all entries for this credential name.
  • context · string · optionnel
    "personal" or "team:<id>". Defaults to personal.

  Exemple d'appel

  {"name": "credential_delete", "arguments": {"name": "texte"}}

  Exemple de retour

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

• credential_guide≈ 118 tokens

  Get setup instructions for a specific credential.

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · requis
    Credential name (e.g. "ios_app_id", "play_store_app_id", "domain").

  Exemple d'appel

  {"name": "credential_guide", "arguments": {"name": "texte"}}

  Exemple de retour

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

• credential_list≈ 186 tokens

  List saved credentials (summary) or detail on one. Pass name for detail view. Pass show_available: true to include the full credential catalog.

  Paramètres, retour & exemple (3)

  Paramètres

  • name · string · optionnel
    Credential name for detail view. Omit to list all saved.
  • context · string · optionnel
    "personal" or "team:<id>". Defaults to personal.
  • show_available · boolean · optionnel
    Include the full catalogue of available BYOK options. Default false.

  Exemple d'appel

  {"name": "credential_list", "arguments": {"name": "texte", "context": "texte", "show_available": true}}

  Exemple de retour

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

• credential_save≈ 248 tokens

  Save a credential (BYOK provider API key). Saved keys persist across sessions and are used automatically.

  Paramètres, retour & exemple (5)

  Paramètres

  • name · string · requis
    Credential name from the tool requirements (e.g. "ios_app_id", "openai").
  • label · string · optionnel
    Human-readable label to identify this value (e.g. "MyApp", "Staging"). Required when saving multiple values for the same credential.
  • value · string · requis
    The credential value to save.
  • context · string · optionnel
    "personal" or "team:<id>". Defaults to personal.
  • is_default · boolean · optionnel
    Set this value as the default for this credential.

  Exemple d'appel

  {"name": "credential_save", "arguments": {"name": "texte", "value": "texte"}}

  Exemple de retour

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

• credits_balance≈ 92 tokens

  Current balance, plan tier, rate limits, and any negative-balance warnings for the active context.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "credits_balance", "arguments": {}}

  Exemple de retour

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

• credits_usage≈ 290 tokens

  Usage summary or history. Pass scope: "me" | "team" and detail: "tool" | "skill". Sorted by cost with _others rollup.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · number · optionnel
    Number of top tools/skills to return. Remaining rolled into "_others". Default 10.
  • scope · string · optionnel · me | team
    Whose usage to show. "me" for personal, "team" for team-wide.
  • detail · string · optionnel · tool | skill
    Detail level. "tool" groups by tool, "skill" adds per-skill breakdown.
  • offset · number · optionnel
    Records to skip for pagination (history mode). Default 0.
  • period · string · optionnel · day | week | month | all
    Time period to summarize. 'all' covers the last 30 days (the maximum window).

  Exemple d'appel

  {"name": "credits_usage", "arguments": {"limit": 1, "scope": "me", "detail": "tool", "offset": 1, "period": "day"}}

  Exemple de retour

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

• discover≈ 376 tokens

  Find the right ToolRouter tool for your task. Describe what you need in plain language. Examples: "analyze a website", "research competitors", "find prospect companies", "check DNS records". Exact tool name (e.g. "seo") returns full schemas and examples. Flow: prefer route({ intent }) to pick and run a tool. Use discover when you need schemas or a listing, then call use_tool(tool, skill, input). Every discover response also includes a top-level `connectors` array listing SaaS accounts the user has already connected (LinkedIn, Google, Notion, etc.). Use that to pick the right tool and account without asking — e.g. if `connectors` shows LinkedIn, the linkedin-post tool is ready to use. Categories: data, media, search, marketing, development, communication, analytics, productivity, ai, finance, security, infrastructure

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · requis
    What you want to do (e.g. "scrape a webpage"), a category (e.g. "security"), or "*" to list everything.
  • category · string · optionnel · data | media | search | marketing | development | communication | analytics | productivity
    Filter by category

  Exemple d'appel

  {"name": "discover", "arguments": {"query": "texte"}}

  Exemple de retour

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

• feedback_debug≈ 629 tokens

  Report a ToolRouter platform bug that blocks you from completing the user's task. Use this when you suspect the issue is on our side — a tool crashed, returned malformed data, timed out unexpectedly, or behaved inconsistently. Include the relevant ToolRouter errors, call IDs, non-sensitive input shape, retries, and expected behavior. Do not include chat history, unrelated conversation text, uploaded file contents, personal data, API keys, or secrets. Reports are stored and reviewed within hours. Skip this for expected errors like invalid input, missing credentials, insufficient balance, rate limits, or genuine "not found" results — those aren't bugs. Limit: 5 reports per hour.

  Paramètres, retour & exemple (10)

  Paramètres

  • tool · string · optionnel
    Tool name that failed (e.g. "web-search").
  • skill · string · optionnel
    Skill name that failed (e.g. "search").
  • job_id · string · optionnel
    Job ID for async jobs that failed, if applicable.
  • call_ids · string · optionnel
    ALL call IDs from this interaction (successful and failed), one per line or comma-separated.
  • severity · string · requis · blocking | degraded
    "blocking" = cannot complete task. "degraded" = partial results or workaround exists.
  • agent_context · string · optionnel
    MCP client name and version, if known.
  • input_summary · string · optionnel
    Summary of what you sent to the failing tool (do NOT include API keys or secrets — describe the shape and intent).
  • error_messages · string · requis
    ALL error messages received during this interaction — not just the last one. Include the full text of every error response from ToolRouter, separated by newlines.
  • interaction_log · string · optionnel
    Chronological log limited to the relevant ToolRouter calls: tool/skill names, non-sensitive input shape, response status, errors, retries, and job polling. Do not include chat history, unrelated conversation text, uploaded file contents, personal data, API keys, or secrets.
  • expected_behavior · string · optionnel
    What you expected to happen vs what actually happened.

  Exemple d'appel

  {"name": "feedback_debug", "arguments": {"severity": "blocking", "error_messages": "texte"}}

  Exemple de retour

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

• feedback_request_tool≈ 258 tokens

  Ask ToolRouter to build a tool that does not exist yet. Use this when discover returned nothing useful for what the user needs. Describe the capability in plain terms — do not include personal data, API keys, or secrets. Requests go straight to the team. Limit: 5 per hour.

  Paramètres, retour & exemple (4)

  Paramètres

  • why · string · optionnel
    What the user was trying to accomplish and why existing tools did not fit.
  • what · string · requis
    What the tool should do, in one or two sentences (e.g. "Look up UK company filings by company number").
  • searched · string · optionnel
    The discover query you tried that came back empty.
  • agent_context · string · optionnel
    MCP client name and version, if known.

  Exemple d'appel

  {"name": "feedback_request_tool", "arguments": {"what": "texte"}}

  Exemple de retour

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

• feedback_review≈ 170 tokens

  Submit a review or star rating.

  Paramètres, retour & exemple (3)

  Paramètres

  • tool · string · requis
    Tool name to review (e.g. "web-search" or "seo").
  • rating · number · requis
    Star rating 1-5 (1=poor, 3=okay, 5=excellent).
  • review · string · optionnel
    Constructive feedback — what worked well and any specific suggestions to improve.

  Exemple d'appel

  {"name": "feedback_review", "arguments": {"tool": "texte", "rating": 1}}

  Exemple de retour

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

• file_delete≈ 107 tokens

  Delete a file. Cannot be undone. For team files: requires owner/admin role.

  Paramètres, retour & exemple (1)

  Paramètres

  • file_id · string · requis
    The file ID to delete.

  Exemple d'appel

  {"name": "file_delete", "arguments": {"file_id": "texte"}}

  Exemple de retour

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

• file_list≈ 347 tokens

  List or search files. Optional query triggers semantic search. Supports section, tags, plan_status, limit, cursor filters.

  Paramètres, retour & exemple (8)

  Paramètres

  • tags · array · optionnel
    Filter to files matching ALL of these tags.
  • limit · number · optionnel
    Max results (default 20, max 50).
  • query · string · optionnel
    Natural language search query. Omit to browse.
  • cursor · string · optionnel
    Pagination cursor from a previous file_list response.
  • context · string · optionnel
    "personal" (default) or "team:<id>".
  • section · string · optionnel · personas | plans | style_references | assets | products | outfits | scenes | prompts
    Filter by section. Omit to list all.
  • plan_status · string · optionnel · draft | active | completed | archived
    Filter plans by status.
  • prompt_type · string · optionnel · system | user | example | template | script
    Filter prompts by type (only valid when section is "prompts").

  Exemple d'appel

  {"name": "file_list", "arguments": {"tags": [], "limit": 1, "query": "texte", "cursor": "texte", "context": "texte", "section": "personas"}}

  Exemple de retour

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

• file_read≈ 120 tokens

  Read a file's full content. Text files return content inline. Binary files (images, video) return a download URL.

  Paramètres, retour & exemple (1)

  Paramètres

  • file_id · string · requis
    The file ID (e.g. "ast_a1b2c3d4e5f67890").

  Exemple d'appel

  {"name": "file_read", "arguments": {"file_id": "texte"}}

  Exemple de retour

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

• file_write≈ 602 tokens

  Create or update a file. Pass mode: "create" | "update". Binary uploads: call with binary: true to get an upload_url, then PUT bytes, then call with mode: "finalize".

  Paramètres, retour & exemple (16)

  Paramètres

  • mode · string · requis · create | update | finalize
    "create" for new files, "update" to edit existing, "finalize" to complete a binary upload.
  • name · string · optionnel
    File name (required for create, max 200 chars).
  • tags · array · optionnel
    Tags for organization (max 10).
  • content · string · optionnel
    Text content (for .md files).
  • context · string · optionnel
    "personal" (default) or "team:<id>".
  • file_id · string · optionnel
    File ID to update (required for update/finalize).
  • section · string · optionnel · personas | plans | style_references | assets | products | outfits | scenes | prompts
    Which section to file under (required for create).
  • asset_id · string · optionnel
    Existing asset ID to retrieve URL without re-uploading.
  • filename · string · optionnel
    Optional filename for the asset.
  • file_data · string · optionnel
    Base64-encoded binary data (for images, video).
  • image_url · string · optionnel
    Public URL to download and host permanently.
  • image_data · string · optionnel
    Base64-encoded image. Alternative to image_url when the bytes are already local.
  • description · string · optionnel
    Optional summary (max 500 chars).
  • plan_status · string · optionnel · draft | active | completed | archived
    Plan status (only for plans section).
  • prompt_meta · object · optionnel
    Prompt metadata (only for prompts section).
  • content_type · string · optionnel
    MIME type. Defaults to "text/markdown" for content, "image/png" for file_data.

  Exemple d'appel

  {"name": "file_write", "arguments": {"mode": "create"}}

  Exemple de retour

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

• invoice_list≈ 108 tokens

  List invoices for the active billing context.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · number · optionnel
    Number of invoices to return (default 10, max 20).

  Exemple d'appel

  {"name": "invoice_list", "arguments": {"limit": 1}}

  Exemple de retour

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

• job_cancel≈ 92 tokens

  Cancel a running job.

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    The job ID to cancel.

  Exemple d'appel

  {"name": "job_cancel", "arguments": {"job_id": "texte"}}

  Exemple de retour

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

• job_get≈ 128 tokens

  Get job status and result. Returns status: running | completed | failed and result when terminal. Keep polling until you get a terminal status.

  Paramètres, retour & exemple (1)

  Paramètres

  • job_id · string · requis
    The job ID returned when a long-running tool was called.

  Exemple d'appel

  {"name": "job_get", "arguments": {"job_id": "texte"}}

  Exemple de retour

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

• job_list≈ 140 tokens

  List your active and recent jobs. Optional status filter.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · number · optionnel
    Max jobs to return (default 20, max 100).
  • status · string · optionnel · pending | running | completed | failed | cancelled
    Filter by job status.

  Exemple d'appel

  {"name": "job_list", "arguments": {"limit": 1, "status": "pending"}}

  Exemple de retour

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

• key_create≈ 118 tokens

  Create a new API key. Returns the secret once — save it immediately.

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · requis
    A name to identify this key (e.g. "Claude Desktop", "Production Bot").

  Exemple d'appel

  {"name": "key_create", "arguments": {"name": "texte"}}

  Exemple de retour

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

• key_delete≈ 110 tokens

  Revoke an API key. Refuses to revoke the currently-authenticating key.

  Paramètres, retour & exemple (1)

  Paramètres

  • key_id · string · requis
    The key ID to revoke (from key_list).

  Exemple d'appel

  {"name": "key_delete", "arguments": {"key_id": "texte"}}

  Exemple de retour

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

• key_list≈ 106 tokens

  List API keys (summary) or get detail on one key. Pass key_id for detail view.

  Paramètres, retour & exemple (1)

  Paramètres

  • key_id · string · optionnel
    Key ID for detail view. Omit to list all.

  Exemple d'appel

  {"name": "key_list", "arguments": {"key_id": "texte"}}

  Exemple de retour

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

• outfit_list≈ 91 tokens

  List your outfits.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    "personal" (default) or "team:<id>".

  Exemple d'appel

  {"name": "outfit_list", "arguments": {"context": "texte"}}

  Exemple de retour

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

• persona_list≈ 92 tokens

  List your personas.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    "personal" (default) or "team:<id>".

  Exemple d'appel

  {"name": "persona_list", "arguments": {"context": "texte"}}

  Exemple de retour

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

• product_list≈ 92 tokens

  List your products.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    "personal" (default) or "team:<id>".

  Exemple d'appel

  {"name": "product_list", "arguments": {"context": "texte"}}

  Exemple de retour

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

• route≈ 334 tokens

  Send a natural-language intent and optionally any dimensions you already know (tool, skill, model, input fields). Fills only the blanks via Jev, then either executes the call or returns a ready-to-run use_tool payload. Explicit values are never overridden. Returns candidates when confidence is low or no tool fits. Flow: route → if confident and complete, result is returned; otherwise use the pre-filled call with use_tool.

  Paramètres, retour & exemple (6)

  Paramètres

  • tool · string · optionnel
    Optional. Tool name — honoured verbatim when set.
  • input · object · optionnel
    Optional. Partial skill input — explicit fields are never overridden.
  • model · string · optionnel
    Optional. Model override — honoured verbatim when set.
  • skill · string · optionnel
    Optional. Skill name — honoured verbatim when set.
  • intent · string · requis
    What you want to do, in plain language.
  • max_cost · number · optionnel
    Optional. Max USD to spend; above this returns a pre-filled call instead of executing.

  Exemple d'appel

  {"name": "route", "arguments": {"intent": "texte"}}

  Exemple de retour

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

• scene_list≈ 90 tokens

  List your scenes.

  Paramètres, retour & exemple (1)

  Paramètres

  • context · string · optionnel
    "personal" (default) or "team:<id>".

  Exemple d'appel

  {"name": "scene_list", "arguments": {"context": "texte"}}

  Exemple de retour

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

• subscription_manage≈ 183 tokens

  Get a Stripe management URL (portal, upgrade, or cancel). Also covers billing portal — returns the URL for the user to open.

  Paramètres, retour & exemple (2)

  Paramètres

  • tier · string · optionnel · lite | plus
    Which plan to subscribe to (required for "subscribe" action).
  • action · string · requis · subscribe | manage
    "subscribe" to start a subscription, "manage" to view/cancel existing subscription.

  Exemple d'appel

  {"name": "subscription_manage", "arguments": {"action": "subscribe"}}

  Exemple de retour

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

• top_up_credits≈ 136 tokens

  Add credits to your account. Returns a Stripe checkout URL — share it with the user to complete payment. Minimum $1.

  Paramètres, retour & exemple (1)

  Paramètres

  • amount_usd · number · requis
    Amount in USD to add (e.g. 10, 25, 50). Minimum $1.

  Exemple d'appel

  {"name": "top_up_credits", "arguments": {"amount_usd": 1}}

  Exemple de retour

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

• use_tool≈ 928 tokens

  Call a ToolRouter catalogue tool. Prefer `route` with a natural-language intent when you do not already know the tool and skill — it picks them, fills arguments, and runs the call. Use discover when you need schemas or a catalogue listing, then pass the exact tool name and skill here. IMPORTANT: "discover", "route", "credits_balance", and other built-in tools are NOT catalogue tools — call them directly, never through use_tool. Long-running tools return a job_id — poll with job_get. If a skill needs an image_url or file URL and you have a local file or base64 image, use file_write first to get a hosted URL, then pass that URL to the skill. BRAIN: Some tools require you to consult brain_query first. If use_tool returns an error about brain_context, call brain_query with a relevant query, then pass the result text as brain_context in your use_tool input.

  Paramètres, retour & exemple (7)

  Paramètres

  • tool · string · requis
    Tool reference from discover results, e.g. "web-search"
  • input · object · requis
    Skill input parameters (see discover for schema). For persona-using tools, include persona_file_id from discover or persona_list. For scene-using tools, include scene_file_id from discover or scene_list. For product-using tools, include product_file_id from discover or product_list. For outfit-using tools, include outfit_file_id from discover or outfit_list. For style-reference tools, include style_reference_id (from discover or file_list), style_reference_query (semantic search), or style_reference_prompt (inline prose). For image-composition tools (e.g. generate-image image_to_image), pass any combination of scene_file_id, persona_file_id, product_file_ids[] (from file_list section "products"), outfit_file_ids[] (section "outfits"), and raw image_urls[] — the gateway resolves and merges them into a single image_urls array (max 4 by default).
  • skill · string · requis
    Skill name from discover results, e.g. "search"
  • backend · object · optionnel
    Route the same model through interchangeable providers. order prioritises providers; only restricts; ignore excludes; allow_fallbacks defaults true.
  • billing · string · optionnel
    Which account to bill. "personal", "team" (auto-resolves if on one team), a team slug ("humanleap"), or a team ID ("team:m57df8c..."). Omit to use your default.
  • brain_context · string · optionnel
    Brain knowledge from brain_query. Pass at the top level of use_tool (alongside "tool", "skill", "input") — NOT inside input. Call brain_query first, then paste the result text here to clear the brain gate.
  • response_format · string · optionnel · concise | detailed
    Response verbosity. "concise" (default) strips noise, returns essential data only. "detailed" returns everything including raw metadata.

  Exemple d'appel

  {"name": "use_tool", "arguments": {"tool": "texte", "input": {}, "skill": "texte"}}

  Exemple de retour

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

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.toolrouter.com/mcp