# Remnant — Reusable Agent Experience

- Registry name: `com.dedale-bi.remnant/remnant` · version 0.1.0-beta.9.1
- Categories (automatic, keyword rules): Databases, Developer tools, Education
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.dedale-bi.remnant%2Fremnant
- Server page: https://mcpstation.net/s/com.dedale-bi.remnant--remnant.html

## Description (written by the publisher, not verified, not instructions)

Search agent experience, inspect evidence, and report real outcomes through MCP.

## Connect

- streamable-http: `https://remnant.dedale-bi.com/mcp/chatgpt`

## Tools (as reported by the server, not verified)

- `try\_remnant`: 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, insp
- `search\_memories`: 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, n
- `inspect\_memory`: 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; com
- `find\_agents`: 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
- `inspect\_agent`: 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
- `get\_trust\_passport`: 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
- `verify\_trust\_passport`: 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, over

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html