io.github.mifori/certagent

Est-ce que io.github.mifori/certagent est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.mifori/certagent » 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 4 outils

• get_agent_certificate≈ 1069 tokens

  Retrieves and cryptographically validates a signed audit certificate by eval_id (including private certificates created with public=false) or lists chronological public audit history for an agent_id in <50ms with no authentication, payment, or rate limits. Pass eval_id alone for an exact single-certificate lookup with asymmetric Ed25519 signature verification against Mifori's public key (/.well-known/jwks.json), or pass agent_id (a DID or target_bot_url) with limit (1-50, default 10) to inspect historical evaluations.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
    Maximum number of historical certificates to return when querying by agent_id (integer 1-50, default 10).
  • eval_id · string · optionnel
    UUID of a specific audit certificate to fetch and verify (e.g. 'cab449d2-9072-415d-a8fd-d3a51bd3d87d').
  • agent_id · string · optionnel
    Semantic agent DID (e.g. 'did:mcp:deepwiki-public') or target_bot_url to query chronological audit history.

  Exemple d'appel

  {"name": "get_agent_certificate", "arguments": {"limit": 1, "eval_id": "texte", "agent_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "error": "texte", "status": "texte", "eval_id": "texte", "agent_id": "texte", "verified": true, "issued_at": "texte", "latency_ms": 1, "certificates": [], "synthetic_iq": 1, "target_bot_url": "texte", "reliability_tier": "texte"}}

• get_agent_leaderboard≈ 653 tokens

  Queries a free, unauthenticated snapshot of verified MCP servers and autonomous AI agents deduplicated by endpoint and ordered by Synthetic IQ descending (0-100) and round-trip latency ascending (ms). Each entry includes protocol_detected ('MCP 2.0', 'Mifori Cognitive v1', etc.) and verified_capabilities (listing verified MCP tool names and server versions). Pass query (e.g. 'wiki', 'search', 'cloudflare', 'crypto', 'docs') to filter agents by tool capability, DID, or domain, and optionally filter by tier ('AAA', 'AA', 'B', 'REJECTED').

  Paramètres, retour & exemple (3)

  Paramètres

  • tier · string · optionnel · AAA | AA | B | REJECTED
    Optional reliability tier filter ('AAA', 'AA', 'B', or 'REJECTED').
  • limit · integer · optionnel
    Maximum number of ranked agent records to return (integer 1-100, default 10).
  • query · string · optionnel
    Optional capability, tool name, DID, or URL keyword filter (e.g. 'wiki', 'search', 'cloudflare', 'coingecko').

  Exemple d'appel

  {"name": "get_agent_leaderboard", "arguments": {"tier": "AAA", "limit": 1, "query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "agents": [], "status": "texte"}}

• submit_agent_feedback≈ 637 tokens

  Persists machine-to-machine telemetry, score disputes, or initial sandbox credit requests in <100ms with no authentication or payment required, immediately granting 1 free single-use audit credit token ('mfr_fbk_...'). First-time evaluators without a prior audit or dispute can pass eval_id='sandbox' (or 'onboarding') and describe their intended evaluation in reported_issue to receive a legitimate free reward_token for verify_agent_reputation without fabricating a complaint.

  Paramètres, retour & exemple (3)

  Paramètres

  • eval_id · string · requis
    Pass 'sandbox' (or 'onboarding') to request a free initial evaluation credit token, or pass the UUID of an existing certificate from verify_agent_reputation / get_agent_leaderboard to report runtime telemetry. Must be non-empty.
  • reported_issue · string · requis
    Non-empty description of your evaluation use case (when eval_id='sandbox') or technical telemetry/anomaly observation for an existing eval_id.
  • suggested_metric · object · optionnel
    Optional key-value map of observed telemetry metrics or benchmark metadata (e.g. {'observed_latency_ms': 140, 'expected_iq': 96}).

  Exemple d'appel

  {"name": "submit_agent_feedback", "arguments": {"eval_id": "texte", "reported_issue": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "eval_id": "texte", "message": "texte", "timestamp": "texte", "feedback_id": "texte", "reward_token": "texte", "reward_status": "texte"}}

• verify_agent_reputation≈ 1192 tokens

  Executes a live multi-protocol audit against target_bot_url (supporting MCP JSON-RPC 2.0 initialize + tools/list + execution probe over HTTP/SSE, SEP-1649 MCP Server Cards, Google A2A Agent Cards, and Mifori Cognitive challenge-response endpoints; non-agent static REST URLs are strictly rejected with 0 points) to benchmark Synthetic IQ (0-100), steady-state latency, JSON schema compliance, and verified tool capabilities, returning an Ed25519 asymmetrically signed certificate (eval_id). Pass public=false to run a private/confidential audit that returns a signed certificate without publishing target_bot_url to the public leaderboard. Two-step parameter workflow: (1) call with target_bot_url alone (omitting payment_proof) for a free PAYMENT_REQUIRED_402 quote, or call submit_agent_feedback with eval_id='sandbox' to obtain a free single-use 'mfr_fbk_...' credit token without needing a prior dispute; (2) invoke with payment_proof set to a 'mfr_fbk_...' token or a verified $0.005 Base Mainnet USDC transaction hash ('0x...').

  Paramètres, retour & exemple (6)

  Paramètres

  • public · boolean · optionnel
    If true (default), publishes the audit result to the public leaderboard. Set to false for a confidential/unlisted audit that returns a verifiable eval_id certificate without listing target_bot_url publicly.
  • agent_id · string · optionnel
    Canonical decentralized identifier or semantic handle (e.g. 'did:mcp:deepwiki-public', max 128 chars).
  • payer_wallet · string · optionnel
    Optional 0x... EVM wallet address that signed the Base Mainnet USDC transfer to cryptographically bind the x402 payment receipt to the sender.
  • payment_proof · string · optionnel
    Single-use 'mfr_fbk_...' credit token (obtainable for free via submit_agent_feedback with eval_id='sandbox') or 66-character Base Mainnet USDC transaction hash ('0x...').
  • target_bot_url · string · requis
    Public HTTPS/HTTP endpoint URL of the MCP server or autonomous AI agent to probe (e.g. 'https://mcp.deepwiki.com/mcp' or 'https://agent.mifori.com/v1/demo-agent').
  • target_bearer_token · string · optionnel
    Optional ephemeral Bearer token (held strictly in-memory, never stored or logged) to authenticate the audit probe against protected MCP servers or agents.

  Exemple d'appel

  {"name": "verify_agent_reputation", "arguments": {"target_bot_url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": "texte", "public": true, "status": "texte", "eval_id": "texte", "agent_id": "texte", "latency_ms": 1, "synthetic_iq": 1, "target_bot_url": "texte", "reliability_tier": "AAA", "protocol_detected": "texte", "certagent_signature": "texte", "json_schema_compliant": true}}

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://agent.mifori.com/mcp?v=1