MCPInstall
readwise-chat logo

readwise-chat

by Scarvy 1 stars Scarvy/readwise-chat

Chat with your Reader documents and highlights using Claude - made possible with Anthropic's Model Context Protocol

READMEmain

Readwise Chat 📚💬 MCP server

Chat with your Reader library using Claude Desktop. Made possible with Anthropic's Model Context Protocol.

[!NOTE] 🚨 🚧 🏗️ Readwise Chat is under active development, as is the MCP specification itself. Core features are working but some advanced capabilities are still in progress.

Components

Resources

[!NOTE] 🚨 🚧 🏗️ Under development

Prompts

[!NOTE] 🚨 🚧 🏗️ Under development

Tools

The server implements two tools:

  • add-document: Adds a new document to your Reader library
    • Takes "url" as required string arguments
    • Updates server state and notifies clients of resource changes
  • list-documents: List documents in your Reader library
    • Takes "location" as a required string argument
    • Optional "category" or "updated after" string arguments

Configuration

[TODO: Add configuration details specific to your implementation]

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unpublished Servers Configuration ``` "mcpServers": { "readwise-chat": { "command": "uv", "args": [ "--directory", "/Users/scott_carvalho/projects/readwise-projects/readwise-chat", "run", "readwise-chat" ] } } ```
Published Servers Configuration ``` "mcpServers": { "readwise-chat": { "command": "uvx", "args": [ "readwise-chat" ] } } ```

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:
uv sync
  1. Build package distributions:
uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:
uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN
  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /Users/scott_carvalho/projects/readwise-projects/readwise-chat run readwise-chat

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

More AI Chatbot MCP servers

Similar servers from the same category.

Jentic

jentic

Enables AI assistants to discover and execute external APIs and workflows through a Python SDK that leverages the Open Agentic Knowledge repository for standardized API access and execution.

AI Chatbot

Provides a bridge to the Flyworks AI lipsync service, enabling creation of digital avatar videos synchronized with audio inputs through a simple API.

git

Official JavaScript implementation that integrates with MiniMax's multimodal capabilities for image generation, video creation, text-to-speech, and voice cloning across multiple transport modes.

APIVideo+7

Provides a bridge to Mureka.ai's music generation capabilities, enabling on-demand creation of lyrics, complete songs, and instrumental tracks without requiring specialized music production knowledge.

AI Chatbot