{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_gkzrcmb37ehg","handle":"memex-md-mcp","url":"https://wellknown.network/agents/memex-md-mcp","links":{"self":"https://wellknown.network/agents/memex-md-mcp/record.json","html":"https://wellknown.network/agents/memex-md-mcp","markdown":"https://wellknown.network/agents/memex-md-mcp/record.md","api":"https://wellknown.network/api/v1/agents/memex-md-mcp","status":"https://wellknown.network/api/v1/agents/memex-md-mcp/status","claim":"https://wellknown.network/agents/memex-md-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/memex-md-mcp/claim.json","badge":"https://wellknown.network/agents/memex-md-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/memex-md-mcp/history","tools":"https://wellknown.network/api/v1/agents/memex-md-mcp/tools"},"ard":{"identifier":"urn:air::server:memex-md-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"memex-md-mcp","summary":"MCP server for semantic search over markdown vaults","description":"# memex-md-mcp\n\n*You like Obsidian? Your LLM will love it too.*\n\n*[Memex](https://en.wikipedia.org/wiki/Memex): Vannevar Bush's 1945 concept of a \"memory extender\" - a device for storing and retrieving personal knowledge. The conceptual ancestor of personal wikis and second brains.*\n\nMCP server for searching and navigating markdown vaults. Point it at your Obsidian vault (or any markdown folder) and get semantic search, wikilink/backlink traversal, and note renaming with automatic link updates.\n\n**What memex is:** A search and navigation layer over your markdown files. SQLite with FTS5 for keyword search, [embeddinggemma](https://huggingface.co/google/embeddinggemma-300m) for semantic similarity, wikilink graph for backlinks.\n\n**What memex isn't:** An automatic memory system. It won't capture context or write notes for you. For that, check out [claude-mem](https://github.com/thedotmack/claude-mem) (automatic memory compression with hooks and summaries). Memex pairs well with workflow layers on top—see [my agent workflows](https://github.com/MaxWolf-01/agents) for an example using memex as the knowledge backend.\n\n## Quick Start\n\n```bash\nclaude mcp add memex -- uvx --from 'memex-md-mcp==1.*' memex-md-mcp\n```\n\nThen ask Claude to help configure your vaults - it has `mcp_info()` which explains everything. Or manually edit your settings (see Configuration below).\n\n**Version note:** The above pins to the latest 1.x release for stability. For bleeding edge, use `memex-md-mcp@latest`—but watch the repo for releases, since major bumps may require deleting your index (`~/.local/share/memex-md-mcp/memex.db`).\n\n## What This Does\n\nMemex gives Claude read access to your markdown vaults. It creates a local index at `~/.local/share/memex-md-mcp/memex.db` and logs to `~/.local/share/memex-md-mcp/memex.log`. The index contains:\n\n- Full-text search index (FTS5) for keyword matching\n- Embeddings (google/embeddinggemma-300m) for semantic similarity\n- Wikilink graph for backlink queries\n…","publisher":{"name":"Maximilian Wolf","url":null},"homepage":null,"repository":"https://github.com/MaxWolf-01/memex/issues","version":"1.3.0","license":null,"protocols":["mcp"],"tags":["mcp","obsidian","markdown","semantic-search","embeddings","claude","agent","agentic","llm","rag"],"pricing":null,"endpoints":[{"url":"pypi:memex-md-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","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"productivity.notes","name":"Notes & Docs","confidence":1,"provenance":"declared"},{"slug":"ai.model-access","name":"Model Access","confidence":0.905,"provenance":"derived"}],"categories":["ai","data","productivity"],"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":"memex-md-mcp","registry":"pypi","observedAt":"2026-11-03T17:26:06.962Z","publishedAt":"2026-01-14T01:21:54.526069Z","latestVersion":"1.3.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"memex-md-mcp","url":"https://pypi.org/project/memex-md-mcp/","firstSeenAt":"2026-09-10T05:22:46.267Z","fetchedAt":"2026-11-03T17:25:07.833Z","normalizedAt":"2026-11-03T17:25:07.833Z"}]},"firstSeenAt":"2026-09-10T05:22:46.267Z","updatedAt":"2026-11-03T17:26:06.962Z"}