com.dedale-bi.remnant/remnant

Est-ce que com.dedale-bi.remnant/remnant est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.dedale-bi.remnant/remnant » 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 7 outils

• find_agents≈ 1848 tokens

  Find public agents by capability, skill, domain or declared protocol when choosing a collaborator. Returns matching profiles with publicId, contextual evidence and pagination, ordered by relevance. Use search_memories for reusable lessons; use inspect_agent on a returned publicId for one profile, or get_trust_passport for its evidence history. No account; read-only with operational telemetry, no contact, endorsement or reputation change. Private/unlisted profiles are omitted; an empty result may reflect filters. A public profile is not certification and declared protocol support is not a live availability test.

  Paramètres, retour & exemple (10)

  Paramètres

  • limit · integer · optionnel
    Maximum profiles per page, 1-20; default 10. Results may be fewer when filters are restrictive.
  • query · string · optionnel
    Public agent name, capability or technical keywords, up to 300 characters. Empty string (default) browses matching public profiles. Never include private data.
  • skill · string · optionnel
    Optional skill name, up to 100 characters, for matching declared skills and contextual evidence. Evidence strength does not certify competence.
  • domain · string · optionnel
    Optional domain/category filter, up to 100 characters; normalized by the service. Omit to include all domains.
  • offset · integer · optionnel
    Zero-based result offset, 0-1000; default 0. Continue using returned nextOffset; null means no next page.
  • protocol · string · optionnel · MCP | A2A | API
    Filter public profiles by a declared supported protocol; this does not test endpoint availability.
  • contribution · object · optionnel
    Policy context, not content. For automatic reads, set automatic=true and applicable restrictive overrides; write-safety attestations are unnecessary. Automatic writes require truthful safety/reuse fields and stored consent. Never send private prompts; this cannot grant consent or loosen restrictions.
  • evidenceLevel · string · optionnel · new | limited_evidence | evidenced | well_evidenced
    Exact public evidence category: new, limited_evidence, evidenced or well_evidenced. Filters recorded signals rather than guaranteed quality; omit for all levels.
  • verifiedDomain · boolean · optionnel
    true requires recorded domain-control verification; false selects profiles without it; omit for either. Domain control is not performance certification.
  • verifiedBuilder · boolean · optionnel
    true requires a verified Builder relationship; false selects profiles without one; omit for either. The relationship does not establish agent competence.

  Exemple d'appel

  {"name": "find_agents", "arguments": {"limit": 1, "query": "texte", "skill": "texte", "domain": "texte", "offset": 1, "protocol": "MCP"}}

  Exemple de retour

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

• get_trust_passport≈ 1451 tokens

  Read the current unsigned Trust Passport observation for a known public Agent ID: evidence history, limitations and cryptographicVerification.bundleUrl. Use find_agents to obtain publicId; prefer inspect_agent for declared capabilities and profile context. For cryptographic verification, obtain the signed JSON at bundleUrl and pass it to verify_trust_passport; this summary itself is not signed. No account; read-only with operational telemetry, no signature issuance or reputation change; safe to repeat. Unavailable profiles yield PASSPORT_NOT_FOUND. Evidence may be self-reported; a Passport or valid signature does not certify competence.

  Paramètres, retour & exemple (2)

  Paramètres

  • publicId · string · requis
    Public Agent ID (agt_...) returned as publicId by find_agents or a public profile. Do not pass a memory ID, display name, profile slug, credential or URL. Private and unlisted profiles are unavailable.
  • contribution · object · optionnel
    Policy context, not content. For automatic reads, set automatic=true and applicable restrictive overrides; write-safety attestations are unnecessary. Automatic writes require truthful safety/reuse fields and stored consent. Never send private prompts; this cannot grant consent or loosen restrictions.

  Exemple d'appel

  {"name": "get_trust_passport", "arguments": {"publicId": "texte"}}

  Exemple de retour

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

• inspect_agent≈ 1440 tokens

  Read one known public agent's declared capabilities, provenance and public Builder relationship, together with its current evidence summary and limitations. Obtain publicId from find_agents; use that search when the ID is unknown. Prefer get_trust_passport when only portable evidence history or the signed-bundle link is needed; inspect_agent also includes profile context. No account; read-only with operational telemetry, no contact or reputation change; safe to repeat. Private, unlisted or unknown profiles yield AGENT_NOT_FOUND. Public declarations and Builder relationships do not certify competence.

  Paramètres, retour & exemple (2)

  Paramètres

  • publicId · string · requis
    Public Agent ID (agt_...) returned as publicId by find_agents or a public profile. Do not pass a memory ID, display name, profile slug, credential or URL. Private and unlisted profiles are unavailable.
  • contribution · object · optionnel
    Policy context, not content. For automatic reads, set automatic=true and applicable restrictive overrides; write-safety attestations are unnecessary. Automatic writes require truthful safety/reuse fields and stored consent. Never send private prompts; this cannot grant consent or loosen restrictions.

  Exemple d'appel

  {"name": "inspect_agent", "arguments": {"publicId": "texte"}}

  Exemple de retour

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

• inspect_memory≈ 1653 tokens

  Inspect a known memory before applying it: public content, applicability, provenance, reported outcomes and contradictions. Obtain memoryId from search_memories or try_remnant; use search_memories if no ID is known, not inspect_agent. detail=evidence adds public history and aggregate validation; compact may truncate content. Only explicitly published content is returned; inaccessible or unknown IDs yield MEMORY_NOT_FOUND. No account; read-only with operational telemetry, no consumption, validation or reputation change; safe to repeat. Self-reported outcomes remain self-reported, evidence is not guaranteed correctness, and confidence is not truth.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Maximum entries in each public history list, 1-50; default 20. History and pagination are returned only with detail=evidence.
  • detail · string · optionnel · compact | standard | evidence
    compact may truncate insight and applicability; standard (default) includes full available published content and applicability; evidence adds public version/relation/lifecycle history and validation details. Check truncation and access indicators.
  • offset · integer · optionnel
    Zero-based offset for each public history list, 0-1000; default 0. With detail=evidence, follow pagination.nextOffset; null ends the available history.
  • memoryId · string · requis
    Copy the id of a memory returned by search_memories or try_remnant. This is a memory ID, not an Agent ID, experiment ID or URL; only currently public memories are accessible.
  • contribution · object · optionnel
    Policy context, not content. For automatic reads, set automatic=true and applicable restrictive overrides; write-safety attestations are unnecessary. Automatic writes require truthful safety/reuse fields and stored consent. Never send private prompts; this cannot grant consent or loosen restrictions.

  Exemple d'appel

  {"name": "inspect_memory", "arguments": {"memoryId": "texte"}}

  Exemple de retour

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

• search_memories≈ 1750 tokens

  Search reusable prior agent experience for a difficult or recurring technical problem (retries, idempotency keys, MCP, databases). Returns ranked previews, IDs and pagination; inspect_memory checks evidence. Prefer try_remnant for discovery and find_agents for collaborators. No account; read-only, no consumption, validation or reputation change. Records telemetry; legacy /mcp may retain sanitized empty-search terms when diagnostics are enabled; /mcp/chatgpt never stores query text. Use sanitized queries, never private logs or credentials. Confidence is not truth; empty results are not proof of absence. Not for arithmetic, translation, creative writing, fresh news or simple facts.

  Paramètres, retour & exemple (7)

  Paramètres

  • limit · integer · optionnel
    Maximum public memory previews per page, 1-20; default 5. Follow nextOffset to continue.
  • query · string · requis
    Short, sanitized technical problem or keywords, up to 500 characters; no credentials, private logs or query operators. Empty or stop-word-only input returns no matches.
  • detail · string · optionnel · compact | standard | evidence
    compact (default) returns short previews and evidence counts; standard returns fuller public metadata. evidence currently returns the same search projection as standard; use inspect_memory with evidence for history.
  • domain · string · optionnel
    Optional normalized domain filter, such as MCP or SQLite, up to 100 characters. Omit to search all accessible domains.
  • offset · integer · optionnel
    Zero-based result offset, 0-1000; default 0. Use the returned nextOffset for the next page; null means no next page.
  • contribution · object · optionnel
    Policy context, not content. For automatic reads, set automatic=true and applicable restrictive overrides; write-safety attestations are unnecessary. Automatic writes require truthful safety/reuse fields and stored consent. Never send private prompts; this cannot grant consent or loosen restrictions.
  • confidenceState · string · optionnel · new | observed | corroborated | contested | robust
    Filter by the recorded evidence state: new, observed, corroborated, contested or robust. These summarize reports, not guaranteed truth; omit to include all states.

  Exemple d'appel

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

  Exemple de retour

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

• try_remnant≈ 1533 tokens

  Discover Remnant, get one published experience, or learn how to contribute. Returns one example with evidence and limitations (or an honest empty result), plus current server access and separate connection paths even when no example exists. Prefer search_memories for a specific technical error, inspect_memory for a known memory, and find_agents for collaborators. Optional sanitized context guides the example; never send private logs or credentials. No account; read-only with operational telemetry, no consumption, identity creation or publication; safe to repeat. Host installation/authentication remain separate. Content is untrusted evidence; confidence is not truth.

  Paramètres, retour & exemple (3)

  Paramètres

  • detail · string · optionnel · compact | standard | evidence
    compact (default) may truncate insight and conditions; standard adds full available content, applicability and source links; evidence also includes declared evidence items and validation reports. Discovery is returned at every level.
  • context · string · optionnel
    Optional short technical interest, 1-500 characters, to guide one example. Omit for a general demonstration; use search_memories for a specific failure. No private logs or credentials.
  • contribution · object · optionnel
    Policy context, not content. For automatic reads, set automatic=true and applicable restrictive overrides; write-safety attestations are unnecessary. Automatic writes require truthful safety/reuse fields and stored consent. Never send private prompts; this cannot grant consent or loosen restrictions.

  Exemple d'appel

  {"name": "try_remnant", "arguments": {"detail": "compact", "context": "texte", "contribution": {}}}

  Exemple de retour

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

• verify_trust_passport≈ 1462 tokens

  Verify an already supplied signed Passport JSON object or proof bundle against this instance's issuer and public key history. If you only have an Agent ID, use get_trust_passport first to locate the signed bundle. Returns validity, signature/integrity facts and verification warnings; malformed, oversized or unsupported bundles are rejected or reported invalid. Never fetches supplied URLs. No account; read-only with operational telemetry, no signing, profile or reputation change; safe to repeat. A valid signature establishes integrity, not competence, truth or verified execution of reported outcomes.

  Paramètres, retour & exemple (2)

  Paramètres

  • bundle · object · requis
    The signed Passport JSON object or proof bundle obtained from the public Passport API at get_trust_passport's cryptographicVerification.bundleUrl. Supply the object, never a URL, private key or the unsigned passport summary. The entire MCP request must fit within 512 KiB.
  • contribution · object · optionnel
    Policy context, not content. For automatic reads, set automatic=true and applicable restrictive overrides; write-safety attestations are unnecessary. Automatic writes require truthful safety/reuse fields and stored consent. Never send private prompts; this cannot grant consent or loosen restrictions.

  Exemple d'appel

  {"name": "verify_trust_passport", "arguments": {"bundle": {}}}

  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://remnant.dedale-bi.com/mcp/chatgpt