MCP Obsidian Index

An MCP server that provides semantic search and resource access for the Obsidian knowledge base

Knowledge management and memory Note-taking tools #Knowledge Management #Semantic Search #Note Indexing .Python

rating : 2.5 points

downloads : 23

update time : 2025-04-29

What is the Obsidian Index MCP Server?

The Obsidian Index MCP Server is a tool that can perform semantic searches on your Obsidian notes. It can also display your recently modified notes as resources.

How to use the Obsidian Index MCP Server?

Simply start the server and configure the path to your Obsidian notes to start using the semantic search function.

Applicable Scenarios

Suitable for users who need to quickly find and manage a large number of Obsidian notes, such as researchers, writers, or knowledge managers.

Main Features

Support for Semantic SearchImplement intelligent search for note content through advanced algorithms.

Resource ManagementDisplay recently modified notes as resources for easy management and access.

Advantages and Limitations

Advantages

Efficient semantic search function to improve work efficiency.

Easy to integrate into existing workflows.

Limitations

The initial indexing may take a long time.

Depends on the availability and quality of Obsidian notes.

How to Use

Install the Server

Run the following command to start the server: uv run obsidian - index --vault /path/to/vault --database /path/to/database --reindex --watch

Configure the Client

Add the server address in the Claude Desktop configuration.

Usage Examples

Search for NotesUse the'search - notes' command for semantic search.

Monitor Note UpdatesWhen a note changes, the server automatically updates the index.

Frequently Asked Questions

How to start the Obsidian Index MCP Server?

How does the server handle note changes?

Related Resources

Claude Desktop Configuration Example

How to configure the Obsidian Index MCP Server in Claude Desktop.

GitHub Project Homepage

The open - source code repository for the Obsidian Index MCP Server.

🚀 Obsidian Index MCP Server

An MCP server that provides semantic search functionality, based on an Obsidian vault, and makes recent note resources publicly available.

🚀 Quick Start

📦 Installation

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

Development/Unreleased Server Configuration

``` "mcpServers": { "obsidian-index": { "command": "uv", "args": [ "--directory", "", "run", "obsidian-index", "--database", "", "--vault", "", "--reindex", "--watch" ] } } ```

Released Server Configuration

``` "mcpServers": { "obsidian-index": { "command": "uvx", "args": [ "obsidian-index", "--database", "", "--vault", "", "--reindex", "--watch" ] } } ```

✨ Features

🔍 Resources

The server provides the most recently modified notes in your vault as resources to the MCP client.

Notes are identified by the custom URL scheme obsidian://<VAULT_NAME>/<NOTE_PATH>
Notes have the media type text/markdown

🛠️ Tools

The server implements one tool:

search-notes: Perform semantic search on the indexed notes

📦 Installation Guide

Running the Server

uv run obsidian-index mcp --vault <VAULT_PATH> --database <DATABASE_PATH> --reindex --watch

--vault: Path to the 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 vaults (may need to run this command every time for now)
--watch: Monitor changes in the vaults and update the index accordingly

💻 Usage Examples

Basic Usage

uv run obsidian-index mcp --vault <VAULT_PATH> --database <DATABASE_PATH> --reindex --watch

📚 Documentation

Building and Publishing

To prepare the distribution package:

Synchronize dependencies and update the lock file:

uv sync

Build the release:

uv build

This will create source code and wheel distributions in the dist/ directory.

Publish to PyPI:

uv publish

Note: You need to set your PyPI credentials via environment variables or command-line arguments:

Token: --token or UV_PUBLISH_TOKEN
Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since the MCP server runs via standard input and output, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP Inspector with the following command:

npx @modelcontextprotocol/inspector uv --directory <PATH_TO_PROJECT> run obsidian-index

After starting, the Inspector will display a URL that you can access in your browser to start debugging.

Featured MCP Services

Markdownify MCP

Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.

TypeScript

1.7K

5 points

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.

A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.

UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.

554

5 points

Figma Context MCP

Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.

Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.

The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.

Python

745

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご