Obsidian MCP Server
Integrates with the Obsidian Local REST API to enable reading, creating, editing, and searching notes within an Obsidian vault. It supports advanced operations like Dataview queries and partial file updates through both stdio and HTTP transport modes.
README
Obsidian MCP Server
A modern Model Context Protocol (MCP) server that integrates with the Obsidian Local REST API to read, create, and edit notes effectively within Obsidian.
Features
This MCP server provides the following tools:
Vault File Operations
| Tool | Description |
|---|---|
vault_get_file |
Get file content (raw markdown, JSON with metadata, or document map) |
vault_create_file |
Create or completely replace a file |
vault_append_to_file |
Append content to an existing or new file |
vault_patch_file |
Partially update a file (heading/block/frontmatter operations) |
vault_delete_file |
Delete a file from the vault |
Directory Operations
| Tool | Description |
|---|---|
vault_list |
List files and directories in the vault |
Search Operations
| Tool | Description |
|---|---|
search_simple |
Simple text search with context |
search_advanced |
Advanced search using Dataview DQL or JsonLogic |
Prerequisites
- Obsidian with the Local REST API plugin installed and enabled
- Node.js v18 or higher
- API Key from Obsidian's Local REST API settings
Quick Start
npm install
npm run build
npm run setup
The interactive setup wizard will guide you through:
- Entering your Obsidian API Key
- Selecting transport mode (stdio for Claude Desktop, HTTP for Open WebUI)
- Configuring optional settings
After setup, start the server:
# For Open WebUI (HTTP mode)
npm run start:http
# For Claude Desktop (stdio mode)
npm start
Installation
npm install
npm run build
Configuration
Setup Wizard (Recommended)
Run the interactive setup wizard:
npm run setup
This creates a .env file with your configuration.
Manual Configuration
Alternatively, copy .env.example to .env and edit manually:
cp .env.example .env
Environment Variables
| Variable | Description | Default |
|---|---|---|
OBSIDIAN_API_URL |
Obsidian REST API URL | http://127.0.0.1:27123 |
OBSIDIAN_API_KEY |
API Key | (required) |
MCP_TRANSPORT |
stdio or http |
stdio |
MCP_PORT |
Port for HTTP mode | 3000 |
DEBUG |
Enable debug logging | false |
Usage with MCP Clients
Claude Desktop (stdio mode)
Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"obsidian": {
"command": "node",
"args": ["/path/to/Obsidian_MCP/dist/index.js"],
"env": {
"OBSIDIAN_API_URL": "http://127.0.0.1:27123",
"OBSIDIAN_API_KEY": "your-api-key-here"
}
}
}
}
Open WebUI (HTTP mode)
-
Start the server in HTTP mode:
npm run start:http -
In Open WebUI, go to Admin Settings → Tools → MCP Servers
-
Add a new MCP server:
- Type: MCP Streamable HTTP
- URL:
http://localhost:3000/mcp - Auth: None (the server handles Obsidian auth internally)
-
Click Save
Startup Health Check
When the server starts, it automatically verifies the connection to Obsidian:
========================================
Obsidian MCP Server - Startup Check
========================================
API URL: http://127.0.0.1:27123
Debug Mode: disabled
Checking connection to Obsidian REST API...
✓ Connected to Obsidian REST API
✓ Authenticated successfully
Plugin Version: 3.4.2
Obsidian Version: 1.11.7
If there are connection issues, troubleshooting steps are displayed.
Debug Mode
Enable debug logging for verbose output:
DEBUG=true npm start
Shows detailed logs for API requests, tool calls, and HTTP connections.
Troubleshooting
Open WebUI Connection Failed
-
Verify server is running:
curl http://localhost:3000/health -
Check configuration:
- URL:
http://localhost:3000/mcp - Auth: None (not Bearer)
- Type: MCP Streamable HTTP
- URL:
-
Test the endpoint: The
/mcpendpoint accepts POST requests with MCP protocol messages.
General Issues
- Ensure Obsidian is running with Local REST API plugin enabled
- Verify API key is correct
- Try
DEBUG=true npm startfor detailed logs - Re-run setup:
npm run setup
Tool Details
vault_get_file
Get file content with optional format:
markdown(default): Raw markdown contentjson: Parsed note with metadatadocument-map: Shows headings, blocks, frontmatter fields
vault_patch_file
Partial updates without rewriting entire file:
- Operations:
append,prepend,replace - Targets: headings, block references, frontmatter fields
search_advanced
- Dataview DQL:
TABLE FROM #tag WHERE field = value - JsonLogic:
{"in": ["myTag", {"var": "tags"}]}
Development
# Build
npm run build
# Development with auto-rebuild
npm run dev # stdio mode
npm run dev:http # HTTP mode
# Setup wizard
npm run setup
# Clean build artifacts
npm run clean
License
MIT
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.