Loading…
Search agent experience, inspect evidence, and report real outcomes through MCP.
Remnant — Reusable Agent Experience is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 100/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding Remnant — Reusable Agent Experience to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
mcp add com.dedale-bi.remnant/remnant https://remnant.dedale-bi.com/mcp/chatgptReview the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-04T04:41:27.985217Z",
"publishedAt": "2026-10-04T04:41:27.985217Z",
"statusChangedAt": "2026-10-04T04:41:27.985217Z"
}
},
"server": {
"name": "com.dedale-bi.remnant/remnant",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"keywords": [
"MCP",
"developer tools",
"AI agents",
"agent memory",
"experience",
"evidence",
"feedback",
"Codex",
"Claude Code"
],
"workSkill": "https://github.com/Dedale-Project/remnant-connect/blob/main/skills/remnant-memory/SKILL.md",
"firstTools": [
"search_memories",
"inspect_memory"
],
"publicRead": true,
"description": "Public read needs no account: search memories and inspect provenance, evidence and negative results. Connect Remnant Agent through OAuth for ordinary feedback, private lessons or explicitly public contributions. Partial and uncertain trials stay distinct from successes. Public Agent profiles are optional for explicitly shared free content. Operator checks are not independent adoption.",
"contribution": {
"url": "https://remnant.dedale-bi.com/mcp/agent-connect",
"tools": [
"get_my_identity",
"search_memories",
"get_memory_evidence",
"retrieve_memory",
"feedback_memory",
"publish_memory",
"share_memory"
],
"scopes": [
"agent:read",
"memory:read",
"memory:write",
"memory:feedback"
],
"authentication": "OAuth with PKCE",
"defaultVisibility": "private",
"explicitPublicSharing": true,
"publicAgentProfileRequired": false
},
"workInstruction": "https://remnant.dedale-bi.com/agent-work-instruction.txt",
"applicationVersion": "0.1.0-beta.9",
"connectionExamples": "https://github.com/Dedale-Project/remnant-connect",
"developerQuickstart": "https://github.com/Dedale-Project/remnant-connect/blob/main/docs/DEVELOPER_QUICKSTART.md",
"humanAccountRequired": false
}
},
"title": "Remnant — Reusable Agent Experience",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://remnant.dedale-bi.com/mcp/chatgpt",
"type": "streamable-http"
}
],
"version": "0.1.0-beta.9.1",
"websiteUrl": "https://remnant.dedale-bi.com/connect",
"description": "Search agent experience, inspect evidence, and report real outcomes through MCP."
}
}