obsidian-mcp
MCP server that gives AI assistants access to an Obsidian vault, enabling folder navigation and note creation, reading, editing, moving, renaming, and deletion.
README
Obsidian MCP
An MCP (Model Context Protocol) server that gives AI assistants (Claude, Cursor, etc.) access to your Obsidian vault. Navigate folders, read notes, create, edit, move, rename and delete them — all from your AI chat.
Requirements
- Python 3.10+
- uv (recommended) or pip
- An Obsidian vault on your local machine
Installation
# Clone the repo
git clone https://github.com/your-username/obsidian-mcp
cd obsidian-mcp
# Copy the env template and set your vault path
cp .env.example .env
Edit .env and set your vault path:
OBSIDIAN_VAULT_PATH="/Users/you/Documents/MyVault"
To find your vault path in Obsidian: Settings → About → Vault path.
Running the server
Development (with MCP Inspector UI)
uv run mcp dev server.py
This opens the MCP Inspector in your browser where you can test all tools interactively.
Production
uv run server.py
Connecting to Cursor
Add this to your .cursor/mcp.json (or Cursor global MCP settings):
{
"mcpServers": {
"obsidian": {
"command": "python",
"args": ["/absolute/path/to/obsidian-mcp/server.py"],
"env": {
"OBSIDIAN_VAULT_PATH": "/path/to/your/vault"
}
}
}
}
Replace /absolute/path/to/obsidian-mcp/server.py with the actual path to server.py on your machine, and /path/to/your/vault with your vault path (find it in Obsidian: Settings → About → Vault path).
Connecting to Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"obsidian": {
"command": "uv",
"args": ["run", "/absolute/path/to/obsidian-mcp/server.py"],
"env": {
"OBSIDIAN_VAULT_PATH": "/path/to/your/vault"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
list_folder(folder_path) |
List subfolders and notes inside a vault folder. Leave empty for vault root. |
read_note(note_path) |
Read the full content of a note (path relative to vault root). |
create_note(note_path, content) |
Create a new note. Creates intermediate folders if needed. |
update_note(note_path, content) |
Replace the full content of an existing note. |
delete_note(note_path) |
Delete a note from the vault. |
rename_note(note_path, new_name) |
Rename a note keeping it in the same folder. |
move_note(note_path, destination_path) |
Move a note to a different folder. Can also rename as part of the move. Creates destination folders if needed. |
delete_folder(folder_path, recursive) |
Delete a folder. Use recursive=True to delete folders that contain files. |
All paths are relative to the vault root, e.g. "Projects/App/roadmap.md".
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.