Readwise MCP server

The Kiseki-Labs-Readwise-MCP server implements the Model Context Protocol (MCP) to allow language models to interact with your Readwise library. It enables programmatic access to your documents and highlights stored in Readwise, making it possible to search, retrieve, and analyze your reading data through API calls.

Installation

Clone and Setup

git clone <your-repository-url>
cd readwise_mcp

If you have uv installed, initialize dependencies:

uv sync

Configuration

The server requires authentication with your Readwise account:

1. Obtain your API key from Readwise
2. Create a .env file in the project's root directory
3. Add your API key to the file:

READWISE_API_KEY=your_readwise_api_key_here

Running the Server

Development Mode

Start the server in development mode with:

uv run mcp dev server.py

By default, the server runs at http://127.0.0.1:6274/

Setting Up with Claude

To integrate with Claude on macOS:

1. Open the Claude configuration file:

vim ~/Library/Application\ Support/Claude/claude_desktop_config.json

2. Add a server entry in the mcpServers object:

"mcpServers": {
    "Kiseki-Labs-Readwise-MCP": {
      "command": "/Users/eddie/.pyenv/shims/uv",
      "args": [
        "run",
        "--with",
        "fastmcp",
        "fastmcp",
        "run",
        "/Users/eddie/Development/AI/mcp_servers/readwise_mcp/server.py"
      ]
    }
}

3. Save the file and restart Claude

Available Tools

The server provides several functions to interact with your Readwise data:

Document Functions

• Find document by name:

  find_readwise_document_by_name(document_name: str)
  

• List documents by filters:

  list_readwise_documents_by_filters(
      document_category: str = "", 
      from_date: Optional[date] = None, 
      to_date: Optional[date] = None
  )
  

  Requires at least one filter argument. Categories include 'books', 'articles', etc.

Highlight Functions

• Get highlights by document IDs:

  get_readwise_highlights_by_document_ids(document_ids: List[int])
  

• Get highlights by filters:

  get_readwise_highlights_by_filters(
      from_date: Optional[date] = None, 
      to_date: Optional[date] = None, 
      tag_names: List[str] = []
  )
  

  Requires at least one filter argument.

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.