Skip to main content

MCP Server for Readwise

Project description

Kiseki-Labs-Readwise-MCP

Overview

Kiseki-Labs-Readwise-MCP is a Model Context Protocol (MCP) Server designed to interact with the Readwise API.

It allows language models to access and manipulate your Readwise documents and highlights programmatically. This server is developed by Kiseki Labs.

Installation

  1. Clone the repository:

    git clone <your-repository-url>
    cd readwise_mcp
    
  2. Initialise dependencies with uv (Assuming you have uv installed)

    uv sync
    

Configuration

This server requires a Readwise API key to function.

  1. Obtain your API key from Readwise.
  2. Create a .env file in the root directory of the project.
  3. Add your API key to the .env file:
    READWISE_API_KEY=your_readwise_api_key_here
    
    The server uses python-dotenv to automatically load this variable when run.

Available Tools

The server exposes the following tools for interaction:

  • find_readwise_document_by_name(document_name: str) -> Book | None: Finds a specific document in Readwise by its exact name.
  • list_readwise_documents_by_filters(document_category: str = "", from_date: Optional[date] = None, to_date: Optional[date] = None) -> List[Book]: Lists documents based on category (e.g., 'books', 'articles') and/or a date range. Requires at least one filter.
  • get_readwise_highlights_by_document_ids(document_ids: List[int]) -> List[Highlight]: Retrieves all highlights associated with a list of specific document IDs.
  • get_readwise_highlights_by_filters(from_date: Optional[date] = None, to_date: Optional[date] = None, tag_names: List[str] = []) -> List[Highlight]: Fetches highlights based on a date range and/or a list of tags. Requires at least one filter.

(Note: Book and Highlight refer to the data structures defined in the readwise_mcp.types module.)

Running the Server

Development Mode

To run the MCP server in dev mode, execute the following command from the project's root directory:

uv run mcp dev server.py

The dev server will start and become accessible online by default on http://127.0.0.1:6274/ if you haven't modified the host and port.

Installing the MCP Server with Claude

On MacBook open the file below in your favourite text editor:

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

For instance using vim open this file you can run the command:

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

Then add the appropriate entry under the mcpServers object, like in the example below:

"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"
      ]
    }
    ...

Save the file with those changes. Finally, restart Claude. After restart, the Kiseki-Labs-Readwise-MCP MCP Server should be available.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iflow_mcp_kiseki_labs_readwise_mcp-0.1.0.tar.gz (7.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file iflow_mcp_kiseki_labs_readwise_mcp-0.1.0.tar.gz.

File metadata

File hashes

Hashes for iflow_mcp_kiseki_labs_readwise_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 353b81e621d87c4aeb8befab8b25d8196e492189355314fda0f5b8a950afe819
MD5 81617b8e39f07e4b0c61a2808d5ac950
BLAKE2b-256 0fe0dbeb102a36fe68590115d2850ab3e20f14edfa068897eb84ef4f8f074ccf

See more details on using hashes here.

File details

Details for the file iflow_mcp_kiseki_labs_readwise_mcp-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for iflow_mcp_kiseki_labs_readwise_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3401a309f883f20cdba9a04715118f79e4f0ab2a77c91b760bf9cddca7598a40
MD5 ed8b55eecf6e6705e076ea16916a80b6
BLAKE2b-256 e0ed160e94b289a29a6871f490fa7a39a8068c28324c4a32454d93ab9c1fa4b4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page