joplin-mcp-server
Categories
Language:
Python
Stars:
2
Forks:
1
๐ Joplin MCP Server
A Model Context Protocol (MCP) Server for Joplin that enables note access through the Model Context Protocol. Perfect for integration with AI assistants like Claude.
โจ Features
- ๐ Search Notes: Full-text search across all notes
- ๐ Read Notes: Retrieve individual notes
- โ๏ธ Edit Notes: Create new notes and update existing ones
- ๐๏ธ Delete Notes: Move notes to trash or delete permanently
- ๐ฅ Markdown Import: Import markdown files as notes
- ๐ค AI Integration: Seamless integration with Claude and other MCP-capable AI assistants
๐ Installation
Prerequisites
- Python 3.10 or higher
- Joplin Desktop with Web Clipper Service enabled
- uv (Python package manager)
# Clone repository
git clone https://github.com/dweigend/joplin-mcp.git
cd joplin-mcp
# Create and activate virtual environment
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
```bash
uv pip install -e .
โ๏ธ Configuration
Joplin API Token
- Open Joplin Desktop
- Go to Tools -> Options -> Web Clipper
- Enable the Web Clipper Service
- Copy the API Token
Create a .env file in the project directory:
JOPLIN_TOKEN=your_api_token_here
Claude Desktop Setup
-
Install Claude Desktop
- Download Claude Desktop
- Ensure you have the latest version (Menu: Claude -> Check for Updates...)
-
Configure MCP Server
{ "mcpServers": { "joplin": { "command": "/PATH/TO/UV/uv", "args": [ "--directory", "/PATH/TO/YOUR/PROJECT/joplin_mcp", "run", "src/mcp/joplin_mcp.py" ] } } }- Replace
/PATH/TO/UV/uvwith the absolute path to your uv installation-
Find the path with:
which uv- Example macOS: `/Users/username/.local/bin/uv` -
Example Windows:
C:\Users\username\AppData\Local\Microsoft\WindowsApps\uv.exe
-
- Replace
/PATH/TO/YOUR/PROJECT/joplin_mcpwith the absolute path to your project
Important: Claude Desktop needs the full path to
uvas it cannot access shell environment variables. - Replace
๐ ๏ธ Available Tools
search_notes
Search for notes in Joplin.
Parameters:
query(string): Search querylimit(int, optional): Maximum number of results (default: 100)
get_note
Retrieve a specific note by its ID.
Parameters:
note_id(string): ID of the note
create_note
Create a new note.
Parameters:
title(string): Note titlebody(string, optional): Note content in Markdownparent_id(string, optional): ID of parent folderis_todo(boolean, optional): Whether this is a todo item
update_note
Update an existing note.
Parameters:
note_id(string): ID of note to updatetitle(string, optional): New titlebody(string, optional): New contentparent_id(string, optional): New parent folder IDis_todo(boolean, optional): New todo status
delete_note
Delete a note.
Parameters:
note_id(string): ID of note to deletepermanent(boolean, optional): If true, permanently delete the note
import_markdown
Import a markdown file as a new note.
Parameters:
file_path(string): Path to the markdown file
๐งช Development
Debug Mode
To start the server in debug mode:
MCP_LOG_LEVEL=debug mcp dev src/mcp/joplin_mcp.py
This starts the MCP Inspector at http://localhost:5173 where you can test the tools.
๐ License
MIT License - Copyright (c) 2025 David Weigend
๐ค Author
David Weigend
- Website: weigend.studio
- GitHub: @dweigend
๐ค Contributing
Contributions, issues and feature requests are welcome!
Visit the [issues page](https://github.com/dweigend/joplin-mcp/issues).
Publisher info
More MCP servers built with Python
A Model Context Protocol (MCP) server that enables natural language queries to databases