com.dominionobservatory/observatory

Est-ce que com.dominionobservatory/observatory est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.dominionobservatory/observatory » 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 14 outils

• check_anomaly≈ 347 tokens

  Check if observed behavior from an MCP server is anomalous compared to baselines. Use this when a server seems slow, unreliable, or returns unexpected results. Returns whether the behavior deviates significantly from normal patterns.

  Paramètres, retour & exemple (3)

  Paramètres

  • server_url · string · requis
    The MCP server URL to check
  • observed_latency_ms · number · optionnel
    The latency you observed
  • observed_success_rate · number · optionnel
    Success rate you've observed (0.0 to 1.0)

  Exemple d'appel

  {"name": "check_anomaly", "arguments": {"server_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"anomalies": [], "server_url": "texte", "is_anomalous": true, "recommendation": "texte", "server_baselines": {}}}

• check_trust≈ 500 tokens

  Get the trust score and reliability metrics for any MCP server. Use this BEFORE calling an unknown MCP server to assess if it's reliable. Returns trust_score (0-100), latency stats, uptime, success rate, and how many agents have used it. Scores above 70 indicate reliable servers. Scores below 30 indicate risky servers.

  Paramètres, retour & exemple (1)

  Paramètres

  • server_url · string · requis
    The URL of the MCP server to check (e.g., https://example.workers.dev/mcp)

  Exemple d'appel

  {"name": "check_trust", "arguments": {"server_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "found": true, "metrics": {}, "category": "texte", "recent_7d": {}, "first_seen": "texte", "server_url": "texte", "trust_score": 1, "last_checked": "texte", "static_score": 1, "runtime_score": 1}}

• clawhub_skill_trust≈ 290 tokens

  Check the supply-chain trust of a ClawHub (OpenClaw) skill BEFORE installing or invoking it. After the Feb-2026 ClawHavoc supply-chain attack, third-party skills can carry malware. Returns a PASS/UNCERTAIN/FAIL badge and 0-100 score aggregating ClawHub's published security scan (VirusTotal + model), moderation verdict, and provenance. Malicious/suspicious/blocked => FAIL; unscanned => UNCERTAIN.

  Paramètres, retour & exemple (1)

  Paramètres

  • skill · string · requis
    The ClawHub skill slug, e.g. 'calendar'

  Exemple d'appel

  {"name": "clawhub_skill_trust", "arguments": {"skill": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"badge": "texte", "score": 1, "skill": "texte", "reasons": [], "signals": {}, "registry": "texte"}}

• get_baselines≈ 272 tokens

  Get behavioral baselines for a tool category. Shows what 'normal' looks like — average latency, success rates, typical call patterns. Use this to evaluate whether a specific server's performance is within normal range for its category.

  Paramètres, retour & exemple (1)

  Paramètres

  • category · string · requis
    The tool category to get baselines for (e.g., weather, finance, code, data)

  Exemple d'appel

  {"name": "get_baselines", "arguments": {"category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"message": "texte", "metrics": {}, "category": "texte", "preliminary_stats": {}, "baselines_available": true}}

• get_compliance_report≈ 326 tokens

  Export a compliance-ready audit trail of all recorded interactions. Formatted for EU AI Act Article 12 and Singapore IMDA Agentic AI Governance Framework. Filter by server, agent, or date range. Essential for enterprises that need to prove their AI agents are behaving correctly.

  Paramètres, retour & exemple (4)

  Paramètres

  • agent_id · string · optionnel
    Filter by agent ID (optional)
  • end_date · string · optionnel
    End date in YYYY-MM-DD format (optional)
  • server_url · string · optionnel
    Filter by server URL (optional)
  • start_date · string · optionnel
    Start date in YYYY-MM-DD format (optional)

  Exemple d'appel

  {"name": "get_compliance_report", "arguments": {"agent_id": "texte", "end_date": "texte", "server_url": "texte", "start_date": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"period": {}, "framework": "texte", "report_id": "texte", "generated_at": "texte", "interactions": [], "total_records": 1}}

• get_leaderboard≈ 298 tokens

  Get the top-rated MCP servers, optionally filtered by category. Use this to discover the most reliable MCP servers in the ecosystem. Categories include: weather, finance, code, data, search, compliance, transport, productivity, communication.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    Number of results (default 10, max 50)
  • category · string · optionnel
    Filter by category (optional). Leave empty for overall leaderboard.

  Exemple d'appel

  {"name": "get_leaderboard", "arguments": {"limit": 1, "category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"servers": [], "category": "texte", "generated_at": "texte", "total_results": 1}}

• get_server_history≈ 214 tokens

  Get daily trust score and performance history for a server over the last 30 days. Use this to see trends — is the server improving or degrading?

  Paramètres, retour & exemple (1)

  Paramètres

  • server_url · string · requis
    The MCP server URL

  Exemple d'appel

  {"name": "get_server_history", "arguments": {"server_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"trend": "texte", "history": [], "server_url": "texte"}}

• observatory_stats≈ 216 tokens

  Get overall statistics about the Dominion Observatory — total servers tracked, total interactions recorded, coverage by category, and data freshness. Use this to understand the scope of the trust network.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "observatory_stats", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"categories": {}, "total_servers": 1, "avg_trust_score": 1, "last_interaction": "texte", "total_interactions": 1}}

• paid_trust_verdict≈ 317 tokens

  Get the PREMIUM behavioral trust verdict for an MCP server, with a signed, citable, tamper-evident attestation receipt. This is a paid x402 service: call WITHOUT payment_tx to receive payment instructions (0.001 USDC on Base), pay, then call again WITH the payment_tx (transaction hash, single-use) to receive the full verdict + receipt. The free check_trust tool remains available for basic scores.

  Paramètres, retour & exemple (2)

  Paramètres

  • payment_tx · string · optionnel
    Base transaction hash proving 0.001 USDC was sent to the pay_to wallet (omit on the first call to get payment instructions)
  • server_slug · string · requis
    The MCP server slug/name to get a paid verdict for

  Exemple d'appel

  {"name": "paid_trust_verdict", "arguments": {"server_slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"amount": "texte", "pay_to": "texte", "receipt": {}, "verdict": "texte", "currency": "texte", "trust_score": 1, "payment_status": "texte"}}

• preflight_check≈ 298 tokens

  Run a PRE-FLIGHT due-diligence check on an MCP server BEFORE your agent invokes it. Returns a verdict (PASS/UNCERTAIN/FAIL/UNRATED) plus a SIGNED, timestamped diligence receipt you keep as proof you performed a trust check — the standard of care after the ClawHavoc/Miasma supply-chain attacks. Call this before connecting to or invoking any unfamiliar MCP server.

  Paramètres, retour & exemple (2)

  Paramètres

  • target · string · requis
    The MCP server URL/name — or a ClawHub skill slug (with registry:'clawhub') — to vet before invoking
  • registry · string · optionnel
    Optional: set to 'clawhub' to vet an OpenClaw/ClawHub skill instead of an MCP server

  Exemple d'appel

  {"name": "preflight_check", "arguments": {"target": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"verdict": "texte", "evidence": {}, "trust_score": 1, "recommendation": "texte", "diligence_receipt": {}}}

• register_server≈ 288 tokens

  Register a new MCP server in the observatory. Server owners can register their servers to start building a trust score. Registration is free.

  Paramètres, retour & exemple (5)

  Paramètres

  • name · string · requis
    Human-readable name of the server
  • category · string · optionnel
    Primary category: weather, finance, code, data, search, compliance, transport, productivity, communication, other
  • github_url · string · optionnel
    GitHub repository URL (optional, improves static score)
  • server_url · string · requis
    The MCP server URL
  • description · string · optionnel
    What the server does

  Exemple d'appel

  {"name": "register_server", "arguments": {"name": "texte", "server_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "message": "texte", "registered": true, "server_url": "texte", "initial_trust_score": 1}}

• report_interaction≈ 426 tokens

  Report the outcome of calling an MCP server. Call this AFTER you use any MCP server to contribute to the trust network. Your report helps other agents make better decisions. This is free and takes <1ms.

  Paramètres, retour & exemple (7)

  Paramètres

  • success · boolean · requis
    Did the call succeed? true = worked as expected, false = error or unexpected result
  • tool_name · string · optionnel
    Which tool you called on the server
  • error_type · string · optionnel
    If failed: timeout, auth_error, invalid_response, server_error, rate_limited, schema_mismatch
  • latency_ms · number · optionnel
    How long the call took in milliseconds
  • server_url · string · requis
    The URL of the MCP server you called
  • http_status · integer · optionnel
    HTTP status code returned (200, 429, 500, etc.)
  • error_message · string · optionnel
    If failed: brief error description

  Exemple d'appel

  {"name": "report_interaction", "arguments": {"success": true, "server_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"message": "texte", "recorded": true, "server_url": "texte", "success_rate": 1, "new_trust_score": 1, "total_interactions": 1}}

• verify_attestation≈ 242 tokens

  Cryptographically verify a Dominion signed attestation (JWS) — e.g. a trust-verdict receipt, gateway attestation, or MCP Verified badge. Stateless: checks the Ed25519 signature against Dominion's published public key (no trust in this server required). Use this to confirm a receipt another party gave you is authentic and untampered.

  Paramètres, retour & exemple (1)

  Paramètres

  • jws · string · requis
    The Dominion attestation as a JWS compact string (header.payload.signature)

  Exemple d'appel

  {"name": "verify_attestation", "arguments": {"jws": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"valid": true, "issuer": "texte", "key_id": "texte", "reason": "texte", "payload": {}}}

• verify_before_call≈ 458 tokens

  Run a signed pre-invocation verification immediately before an agent sends money, credentials, private data, or write access to an MCP server. The first 3 verifications per agent are free. After that, authenticate the MCP HTTP request with Authorization: Bearer do_<api_key> for Stripe metering ($0.01/call), or call once without payment to receive x402 instructions and retry with payment_tx. Returns PASS/UNCERTAIN/FAIL/UNRATED, evidence freshness, recommendation, and a signed diligence receipt.

  Paramètres, retour & exemple (4)

  Paramètres

  • reason · string · optionnel
    Optional reason for verification, e.g. money, credentials, private_data, write_access
  • agent_id · string · optionnel
    Stable, non-secret agent identifier used to count the 3 introductory calls. If omitted, Dominion derives a privacy-preserving hash from network metadata.
  • payment_tx · string · optionnel
    Optional Base transaction hash proving the x402 USDC payment after a payment_required response
  • server_url · string · requis
    The MCP server URL or tracked server name to verify

  Exemple d'appel

  {"name": "verify_before_call", "arguments": {"server_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"product": "texte", "verdict": "texte", "evidence": {}, "price_usd": "texte", "trust_score": 1, "payment_status": "texte", "recommendation": "texte", "diligence_receipt": {}, "free_verifications_remaining": 1}}

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://dominionobservatory.com/mcp