Joplin MCP server

The joplin-mcp-server is a server implementation of the Model Context Protocol (MCP) specifically designed for Joplin notes. It allows you to integrate your local language models with your Joplin notes, enabling advanced AI functionality while keeping your data private and secure.

Installation

Prerequisites

• Node.js 18 or higher
• npm or yarn
• A running Joplin instance with Web Clipper API enabled

Setup Instructions

1. Clone the repository:

   git clone https://github.com/personalizedrefrigerator/joplin-mcp-server.git
   cd joplin-mcp-server
   

2. Install dependencies:

   npm install
   

3. Configure your server by creating a config.json file:

   {
     "joplinToken": "YOUR_JOPLIN_TOKEN",
     "joplinPort": 41184,
     "serverPort": 3000,
     "paths": {
       "ollama": "http://localhost:11434/api/generate"
     }
   }
   

   Replace YOUR_JOPLIN_TOKEN with your actual Joplin Web Clipper API token.

Getting Your Joplin Token

1. Open Joplin
2. Go to Tools > Options > Web Clipper
3. Enable the Web Clipper service
4. Copy the authorization token

Usage

Starting the Server

Start the server with:

npm start

The server will be available at http://localhost:3000 (or the port you specified in the config).

Configuration Options

The config.json file supports the following options:

• joplinToken: Your Joplin Web Clipper API token
• joplinPort: The port Joplin's Web Clipper API is running on (default: 41184)
• serverPort: The port your MCP server will run on (default: 3000)
• paths: Configuration for model services
  • ollama: URL to your Ollama API
  • openai: URL to an OpenAI-compatible API

Using with Language Models

Ollama

To use with Ollama:

1. Install Ollama
2. Pull a model:

   ollama pull llama2
   

3. Make sure Ollama is running on port 11434
4. Configure the server to use Ollama in your config.json

OpenAI Compatible APIs

To use with OpenAI-compatible APIs:

1. Add the API endpoint to your config.json:

   "paths": {
     "openai": "https://your-openai-compatible-api-endpoint"
   }
   

2. Add your API key (if required):

   "openaiApiKey": "your-api-key"
   

Integration with Applications

To connect applications to your MCP server, use the following endpoint:

http://localhost:3000/mcp/v1/generate

Your applications can send POST requests to this endpoint with the MCP protocol format to generate responses based on your Joplin notes.

Testing the Server

You can test if the server is running correctly by accessing:

http://localhost:3000/health

This should return a status indicating that the server is operational.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.