Obsidian Index MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Obsidian Index MCP Serversearch for notes about meeting action items from last week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Obsidian Index MCP server
An MCP server that provides a semantic search over an Obsidian vault and exposes recent notes as resources.
Components
Resources
The server exposes recently modified notes in your vaults as resources to MCP clients.
Notes are addressed by an
obsidian://<VAULT_NAME>/<NOTE_PATH>URL schemeNotes have the
text/markdownmedia type
Tools
The server implements one tool:
search-notes: Performs semantic search over indexed notes
Related MCP server: Obsidian Research MCP
Run the server
uv run obsidian-index mcp --vault <VAULT_PATH> --database <DATABASE_PATH> --reindex --watch--vault: Path to the Obsidian vault (can be specified multiple times)--database: Path to the local database file (will be created if it doesn't exist)--reindex: Reindex all notes in the vault (you probably want this every time right now)--watch: Watch for changes in the vault and update the index accordingly
Quickstart
Install
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development
Building and Publishing
To prepare the package for distribution:
Sync dependencies and update lockfile:
uv syncBuild package distributions:
uv buildThis will create source and wheel distributions in the dist/ directory.
Publish to PyPI:
uv publishNote: You'll need to set PyPI credentials via environment variables or command flags:
Token:
--tokenorUV_PUBLISH_TOKENOr username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory <PATH_TO_PROJECT> run obsidian-indexUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
This server cannot be deployed
Maintenance
Related MCP Connectors
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Search, read, and write your Apple Notes from ChatGPT/Claude via a local Mac agent + MCP relay.
Zotero MCP server for Claude and ChatGPT: search, citations, safe writes, PDF passages and pages.
- TaprootOAuthcom.taproothq
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables semantic search over local knowledge bases like Obsidian notes, SQLite, and plaintext files, exposing results to Claude via MCP server.-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server enabling Claude to read, write, search, and analyse your Obsidian vault with advanced research capabilities.1MIT
- AlicenseNot gradedqualityBmaintenanceProvides semantic search, note retrieval, source explanation, daily digests, and health checks for a local Obsidian vault, enabling MCP clients like Claude Desktop and Claude Code to query the second brain via natural language.MIT
- FlicenseNot gradedqualityCmaintenanceEnables semantic search and related-note discovery across an Obsidian vault via MCP, providing RAG context blocks for natural language queries.-
Appeared in Searches
- Using an AI Agent for Structured Search and Traversal in a Neo4j Database
- Allowing Claude Desktop to manage and access an Obsidian library
- How to document a codebase using Markdown
- Information on GraphRAG, AutoGen, AG2, Daydream, and HybridRAG
- Understanding how memory is stored or memory storage methods