Obsidian MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to your Obsidian vault through the Obsidian Local REST API plugin.
README
Obsidian MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to your Obsidian vault through the Obsidian Local REST API plugin.
Features
Tools
- obsidian-get-note: Retrieve note content by filename
- obsidian-create-note: Create new notes with optional frontmatter
- obsidian-update-note: Update existing note content and metadata
- obsidian-delete-note: Delete notes from the vault
- obsidian-search-notes: Search for notes containing specific text
- obsidian-list-files: List all files and folders in the vault
- obsidian-get-vault-info: Get vault information and statistics
- obsidian-create-folder: Create new folders in the vault
- obsidian-get-tags: Get all tags used in the vault
- obsidian-ping: Check server connectivity
Resources
- obsidian://note/{filename}: Access individual note content
- obsidian://vault/files: Complete file and folder listing
- obsidian://vault/info: Vault information and statistics
- obsidian://vault/tags: All tags in the vault
- obsidian://search/{query}: Dynamic search results
Prerequisites
- Obsidian with the Local REST API plugin installed and enabled
- Node.js (version 18 or higher)
Setting up Obsidian Local REST API
- Install the Obsidian Local REST API plugin
- Enable the plugin in Obsidian settings
- Configure the plugin settings:
- Port: Default is
27123(or choose your preferred port) - API Key: Set a secure API key (optional but recommended)
- CORS: Enable if needed for web-based MCP clients
- Port: Default is
Installation
From NPM (when published)
npm install -g obsidian-mcp-server
From Source
git clone <repository-url>
cd obsidian-mcp-server
npm install
npm run build
Configuration
The server uses environment variables for configuration:
Using .env File (Recommended)
- Copy the example environment file:
cp .env.example .env
- Edit
.envfile with your settings:
# Required: Obsidian Local REST API base URL
OBSIDIAN_API_BASE_URL=http://localhost:27123
# Optional: API key if configured in Obsidian plugin
OBSIDIAN_API_KEY=your-api-key-here
The server automatically loads the .env file when started.
Using Environment Variables
Alternatively, you can set environment variables directly:
# Required: Obsidian Local REST API base URL
export OBSIDIAN_API_BASE_URL="http://localhost:27123"
# Optional: API key if configured in Obsidian plugin
export OBSIDIAN_API_KEY="your-api-key-here"
With Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\\Claude\\claude_desktop_config.json
{
"mcpServers": {
"obsidian": {
"command": "obsidian-mcp-server",
"env": {
"OBSIDIAN_API_BASE_URL": "http://localhost:27123",
"OBSIDIAN_API_KEY": "your-api-key-here"
}
}
}
}
With Other MCP Clients
For stdio transport:
OBSIDIAN_API_BASE_URL="http://localhost:27123" OBSIDIAN_API_KEY="your-key" obsidian-mcp-server
Usage Examples
Once connected, you can ask your AI assistant to:
Basic Operations
- "Show me the content of my 'Meeting Notes.md' file"
- "Create a new note called 'Ideas.md' with the content 'My brilliant ideas'"
- "Search for notes containing 'project'"
- "List all files in my vault"
Advanced Operations
- "Create a note with frontmatter including tags and creation date"
- "Update my daily note with today's tasks"
- "Show me all tags in my vault"
- "Create a folder called 'Projects' for organizing my work"
Working with Resources
- Access note content directly:
obsidian://note/filename.md - View vault statistics:
obsidian://vault/info - Get search results:
obsidian://search/your%20query
Development
Setup
git clone <repository-url>
cd obsidian-mcp-server
npm install
Development Mode
npm run dev
Build
npm run build
Testing
# Test with MCP Inspector
npx @modelcontextprotocol/inspector npm run dev
# Or test with a specific configuration
OBSIDIAN_API_BASE_URL="http://localhost:27123" npx @modelcontextprotocol/inspector npm run dev
API Reference
Environment Variables
| Variable | Description | Default | Required |
|---|---|---|---|
OBSIDIAN_API_BASE_URL |
Base URL for Obsidian Local REST API | http://localhost:27123 |
No |
OBSIDIAN_API_KEY |
API key for authentication | - | No |
Tool Schemas
obsidian-get-note
{
filename: string // The filename of the note to retrieve
}
obsidian-create-note
{
filename: string // The filename for the new note
content: string // The content of the note
frontmatter?: Record<string, any> // Optional frontmatter metadata
}
obsidian-search-notes
{
query: string // The search query text
}
Resource URIs
obsidian://note/{filename}- Individual note contentobsidian://vault/files- Complete file listingobsidian://vault/info- Vault informationobsidian://vault/tags- All tagsobsidian://search/{query}- Search results
Troubleshooting
Connection Issues
- Server not accessible: Ensure Obsidian is running and the Local REST API plugin is enabled
- Port conflicts: Check if port 27123 (or your configured port) is available
- API key issues: Verify the API key matches your Obsidian plugin configuration
Common Problems
- "Cannot find module" errors: Run
npm installto install dependencies - Permission errors: Ensure proper file permissions for the build directory
- CORS errors: Enable CORS in the Obsidian Local REST API plugin settings
Debug Mode
Run with debug logging:
DEBUG=* OBSIDIAN_API_BASE_URL="http://localhost:27123" obsidian-mcp-server
📚 Documentation
📖 Complete Documentation
See the docs/ folder for comprehensive guides, or check the Documentation Index for organized access to all guides.
Setup & Configuration
- LM Studio Setup Guide - Complete LM Studio configuration and deployment
- LM Studio Quick Start - Quick reference for LM Studio integration
- Environment File Usage - Using .env files with LM Studio and other clients
Docker & Deployment
- Docker Deployment Guide - Complete Docker containerization guide
- Docker Summary - Docker toolkit integration overview
Publishing & Distribution
- Registry Publishing Guide - Complete guide to publish to Docker MCP Registry
- Publishing Summary - Quick publishing checklist and steps
Quick Links
| Topic | Guide | Description |
|---|---|---|
| 🚀 Getting Started | LM Studio Quick Start | Fastest way to get running |
| 🐳 Docker | Docker Summary | Containerization overview |
| ⚙️ Configuration | Environment Files | Managing environment variables |
| 🏪 Publishing | Registry Publishing | Share with the community |
Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature-name - Make your changes and add tests
- Run the build:
npm run build - Submit a pull request
License
MIT License - see LICENSE file for details.
Related Projects
- Obsidian - A powerful knowledge base
- Obsidian Local REST API - REST API plugin for Obsidian
- Model Context Protocol - Protocol for AI-context integration
- Claude Desktop - AI assistant supporting MCP
Built with ❤️ for the Obsidian and AI community
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.