oomkapwn/enquire-mcp
by Various
The most advanced Obsidian MCP — long-term memory for AI agents. Hybrid retrieval (BM25 + ML + BGE rerank, RRF-fused), HNSW live-update, agentic RAG (HyDE + sub-question), Obsidian
MCP
oomkapwn/enquire-mcp
Added 13 July 2026
Overview
Enquire MCP is an Obsidian Model Context Protocol server that gives AI agents long-term memory through hybrid retrieval combining BM25, ML, and BGE reranking with RRF fusion. It supports HNSW live-update indexes, agentic RAG with HyDE and sub-question generation, and can ingest PDFs with OCR. The tool is designed for use with Claude Code, Cursor, ChatGPT, Codex, and OpenClaw.
Best for
Best for
Developers building AI agents that need persistent, searchable memory from an Obsidian knowledge base
Use cases
- Give AI agents persistent memory across Obsidian vault sessions
- Retrieve relevant notes using hybrid search and reranking
- Ingest and query PDF documents with OCR support
How to use
Install
npm install -g @oomkapwn/enquire-mcpTested with
Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw
Notes
Enquire MCP is an Obsidian Model Context Protocol server that gives AI agents long-term memory through hybrid retrieval combining BM25, ML, and BGE reranking with RRF fusion. It supports HNSW live-update indexes, agentic RAG with HyDE and sub-question generation, and can ingest PDFs with OCR. The tool is designed for use with Claude Code, Cursor, ChatGPT, Codex, and OpenClaw.
18 stars on GitHub. Last updated 2026-07-13. Licensed MIT.
Use cases
- Give AI agents persistent memory across Obsidian vault sessions
- Retrieve relevant notes using hybrid search and reranking
- Ingest and query PDF documents with OCR support
Pros
- Combines multiple retrieval methods for high relevance
- Supports live-updating HNSW indexes without rebuilds
- Agentic RAG with HyDE and sub-question decomposition
Cons
- Limited to Obsidian vaults as the data source
- Small community with only 18 GitHub stars
- Requires MCP-compatible clients to function
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Combines multiple retrieval methods for high relevance
- Supports live-updating HNSW indexes without rebuilds
- Agentic RAG with HyDE and sub-question decomposition
Cons
- Limited to Obsidian vaults as the data source
- Small community with only 18 GitHub stars
- Requires MCP-compatible clients to function
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.