Joplin
Enables AI assistants to interact with Joplin notes through full-text search, reading, creating, updating, and deleting notes, as well as importing markdown files directly into Joplin notebooks.
What is Joplin?
Joplin is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to interact with joplin notes through full-text search, reading, creating, updating, and deleting notes, as well as importing markdown files directly into joplin notebooks.
Enables AI assistants to interact with Joplin notes through full-text search, reading, creating, updating, and deleting notes, as well as importing markdown files directly into Joplin notebooks.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables AI assistants to interact with Joplin notes through
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx joplin-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Joplin
The Joplin MCP Server connects AI assistants like Claude to your Joplin note-taking application via the Joplin Web Clipper API, enabling full note management through natural language. It exposes tools for full-text search across all notes, retrieving notes by ID, creating new notes with markdown content in specific notebooks, updating existing notes, deleting notes, and importing external markdown files. Writers, researchers, and knowledge workers who use Joplin as their primary note store can query and manage their entire knowledge base directly from their AI assistant.
Prerequisites
- Python 3.10+ and the uv package manager installed
- Joplin Desktop app installed and running (the Web Clipper plugin must be enabled)
- A Joplin API token (obtained from Joplin Desktop: Tools > Options > Web Clipper > Enable Web Clipper Service)
- The joplin-mcp repository cloned locally
- An MCP-compatible client such as Claude Desktop
Clone the repository and set up the Python environment
Clone the joplin-mcp-server repository and create an isolated Python virtual environment using uv.
git clone https://github.com/dweigend/joplin-mcp.git
cd joplin-mcp
uv venv
source .venv/bin/activate # Windows: .venv\Scripts\activateInstall the package
Install the joplin-mcp package and its dependencies in editable mode.
uv pip install -e .Get your Joplin API token
Open Joplin Desktop and navigate to Tools > Options > Web Clipper. Enable the Web Clipper service if it is not already running. Copy the API token shown on that page — you will need it for the MCP configuration.
Configure your MCP client with the JOPLIN_TOKEN
Add the joplin-mcp-server to your claude_desktop_config.json. The JOPLIN_TOKEN environment variable is required. The server uses the Joplin Web Clipper API running on localhost:41184 by default.
{
"mcpServers": {
"joplin": {
"command": "/absolute/path/to/joplin-mcp/.venv/bin/python",
"args": ["/absolute/path/to/joplin-mcp/src/mcp/joplin_mcp.py"],
"env": {
"JOPLIN_TOKEN": "your-joplin-api-token-here"
}
}
}
}Ensure Joplin Desktop is running and test
Joplin Desktop must be open and the Web Clipper service must be running whenever you use the MCP server. Restart Claude Desktop and try a search query to verify the connection.
# Optional: test in debug mode
MCP_LOG_LEVEL=debug mcp dev src/mcp/joplin_mcp.pyJoplin Examples
Client configuration
Claude Desktop config for the Joplin MCP server with the API token.
{
"mcpServers": {
"joplin": {
"command": "/Users/you/joplin-mcp/.venv/bin/python",
"args": ["/Users/you/joplin-mcp/src/mcp/joplin_mcp.py"],
"env": {
"JOPLIN_TOKEN": "abc123yourtokenhere"
}
}
}
}Prompts to try
Example prompts for managing and searching Joplin notes.
- "Search my Joplin notes for anything about project planning"
- "Create a new note titled 'Meeting Notes 2026-06-14' in my Work notebook with today's agenda"
- "Find my note about the API design decision and update it with the conclusion we reached"
- "Delete the draft note titled 'scratch pad'"
- "Import the file ~/Documents/research.md into my Research notebook in Joplin"Troubleshooting Joplin
Connection refused: server cannot reach the Joplin API
Joplin Desktop must be open and the Web Clipper service must be running. Go to Tools > Options > Web Clipper and confirm the service is enabled. It listens on port 41184 by default.
401 Unauthorized errors when calling Joplin API tools
Your JOPLIN_TOKEN is incorrect or missing. Re-copy the token from Joplin Desktop (Tools > Options > Web Clipper) and update the env block in your MCP client config. Note that the token changes each time you disable and re-enable the Web Clipper service.
'uv: command not found' or virtual environment not activated errors
Install uv with `curl -LsSf https://astral.sh/uv/install.sh | sh` and restart your terminal. Use absolute paths to the .venv/bin/python executable in your MCP config so the correct environment is used regardless of the shell's PATH.
Frequently Asked Questions about Joplin
What is Joplin?
Joplin is a Model Context Protocol (MCP) server that enables ai assistants to interact with joplin notes through full-text search, reading, creating, updating, and deleting notes, as well as importing markdown files directly into joplin notebooks. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Joplin?
Follow the installation instructions on the Joplin GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Joplin?
Joplin works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Joplin free to use?
Yes, Joplin is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Joplin Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Joplin? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Joplin in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Joplin?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.