{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_97k6fqnnftu2","handle":"mnemosyne-mcp-2","url":"https://wellknown.network/agents/mnemosyne-mcp-2","links":{"self":"https://wellknown.network/agents/mnemosyne-mcp-2/record.json","html":"https://wellknown.network/agents/mnemosyne-mcp-2","markdown":"https://wellknown.network/agents/mnemosyne-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/mnemosyne-mcp-2","status":"https://wellknown.network/api/v1/agents/mnemosyne-mcp-2/status","claim":"https://wellknown.network/agents/mnemosyne-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mnemosyne-mcp-2/claim.json","badge":"https://wellknown.network/agents/mnemosyne-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mnemosyne-mcp-2/history","tools":"https://wellknown.network/api/v1/agents/mnemosyne-mcp-2/tools"},"ard":{"identifier":"urn:air::server:mnemosyne-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mnemosyne-mcp","summary":"MCP server for Mnemosyne -- semantic code retrieval with 6-signal hybrid search and AST-aware compression","description":"# mnemosyne-mcp\n\nMCP server for [Mnemosyne](https://github.com/castnettech/mnemosyne) -- a 6-signal hybrid retrieval engine for code, documents, and database schemas. Reduces LLM context waste by 73%.\n\nFor the full reference, see [MCP.md](../MCP.md) in the repository root.\n\n## Install\n\n```bash\npip install mnemosyne-mcp\n```\n\n## Register with Claude Code\n\n```bash\nclaude mcp add mnemosyne -- mnemosyne-mcp\n```\n\nOr add to your project's `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"mnemosyne\": {\n      \"command\": \"mnemosyne-mcp\",\n      \"args\": []\n    }\n  }\n}\n```\n\n## Tools\n\n### `search`\n\nFederated search across code and document partitions. Code results use 6-signal hybrid retrieval (BM25, TF-IDF, symbol matching, usage frequency, predictive prefetch, optional dense embeddings) fused via Reciprocal Rank Fusion. Document results use BM25 + TF-IDF with isolated vocabulary. Returns labeled sections so the LLM can perform cross-type ranking.\n\n**Parameters:**\n- `query` (string, required) -- natural language or keyword query\n- `budget` (integer, default 8000) -- maximum token budget\n- `project_root` (string, optional) -- path to project root\n\n### `search_docs`\n\nSearch the document partition only (PDFs, DOCX, CSVs, logs, and other non-code files). Uses BM25 and TF-IDF with an isolated vocabulary tuned for prose retrieval.\n\n**Parameters:**\n- `query` (string, required) -- natural language query\n- `budget` (integer, default 8000) -- maximum token budget\n- `project_root` (string, optional) -- path to project root\n\n### `index`\n\nIndex or re-index a codebase. Incremental by default (only processes changed files). Indexes both code and document partitions.\n\n**Parameters:**\n- `project_root` (string, optional) -- path to project root\n- `full` (boolean, default false) -- force full re-index\n\n### `stats`\n\nShow index statistics: file count, chunk count, tokens, language breakdown, chunk types.\n\n**Parameters:**\n- `project_root` (string, optional) -- path to project root\n\n### `schema_ingest`\n…","publisher":null,"homepage":"https://castnettechnology.com/blog/mnemosyne-context-engine-benchmark","repository":"https://github.com/castnettech/mnemosyne","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["claude-code","code-search","context-engine","llm","mcp","mnemosyne"],"pricing":null,"endpoints":[{"url":"pypi:mnemosyne-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":0.825,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.791,"provenance":"derived"}],"categories":["data","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mnemosyne-mcp","registry":"pypi","observedAt":"2026-09-10T06:25:18.931Z","publishedAt":"2026-04-07T16:16:54.545449Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mnemosyne-mcp","url":"https://pypi.org/project/mnemosyne-mcp/","firstSeenAt":"2026-09-10T06:23:28.784Z","fetchedAt":"2026-09-10T06:23:28.784Z","normalizedAt":"2026-09-10T06:23:28.784Z"}]},"firstSeenAt":"2026-09-10T06:23:28.784Z","updatedAt":"2026-09-10T06:25:18.931Z"}