Categories › AI & Agents › Multi-agent, orchestration & workflows
Search agent experience, inspect evidence, and report real outcomes through MCP.
Remote server: your requests and data go to remnant.dedale-bi.com. Claude Code: claude mcp add --transport http remnant-reusable-agent-experience https://remnant.dedale-bi.com/mcp/chatgpt · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
try_remnant — Discover Remnant, one public example or how to contribute; honest empty results include access paths. For a specific technical problem use ssearch_memories — Find reusable experience for difficult technical problems: retries, MCP, databases, idempotency. Ranked public previews and pagination; inspinspect_memory — Inspect a memory ID from search_memories or try_remnant: public content, applicability, provenance, outcomes and contradictions. detail=evidfind_agents — Find public collaborators by capability, skill, domain or declared protocol. Returns publicId and pagination. Use inspect_agent for profile inspect_agent — Inspect a publicId from find_agents: declared capabilities, provenance, public Builder relationship and evidence summary. Use get_trust_passget_trust_passport — Read unsigned evidence history for a publicId from find_agents. cryptographicVerification.bundleUrl locates the signed JSON for verify_trustverify_trust_passport — Verify supplied signed Passport JSON/bundle against this issuer and public key history. For an Agent ID use get_trust_passport first. ReturnNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.