vault-search MCP Server
mzazon/vault-search
Hybrid search for Obsidian vaults — BM25 + fuzzy + semantic vector search with RRF fusion. Full CLI, MCP server (stdio + HTTP/SSE), Docker-ready. Local ONNX embeddings or any OpenAI-compatible API.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
mzazon/vault-search is a TypeScript MCP server licensed under MIT. Hybrid search for Obsidian vaults — BM25 + fuzzy + semantic vector search with RRF fusion. Full CLI, MCP server (stdio + HTTP/SSE), Docker-ready. Local ONNX embeddings or any OpenAI-compatible API. Topics: cli, embeddings, mcp, mcp-server, obsidian, search, sqlite, typescript, bm25, hybrid-search, knowledge-base, markdown, obsidian-plugin, onnx, rag, self-hosted, selfhosted, vector-search.
Ranked #1 out of 109 indexed tools.
In the top 1% of all indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
1 stars → early stage
Last commit today → actively maintained
23/23 issues closed → responsive maintainer
1 contributor → solo project
No dependents → no downstream usage
Weights: Freshness 25% · Issue Health 25% · Dependents 25% · Stars 15% · Contributors 10% · How we score →
How to Improve
Matched Queries
From the README
# vault-search Hybrid search MCP server for Obsidian vaults. Combines BM25 keyword matching, fuzzy title search, and vector semantic search with Reciprocal Rank Fusion (RRF) into a single ranked result set. Embeddings run locally in-process via ONNX (no API key needed) or via any OpenAI-compatible API. Features layered config (`~/.vault-search/config.json`, `VS_` env vars, CLI flags), rate-limited embeddings, full CLI, dual MCP transport (stdio for Claude Desktop/Cursor, HTTP/SSE for Docker), and smart chunking strategies. --- ## Features - **Hybrid search with RRF fusion** — BM25 + fuzzy title + vector semantic search merged via Reciprocal Rank Fusion - **ONNX embeddings by default** — runs `nomic-ai/modernbert-embed-base` in-process via ONNX Runtime; no API key needed - **API embedding support** — works with any OpenAI-compatible API: Ollama, LiteLLM, OpenAI, OpenRouter - **Layered config system** — `~/.vault-search/config.json`, `VS_*` env vars, and CLI flags with full precedencRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.