Letterboxd MCP Server
Enables AI models to interact with Letterboxd data and perform account actions like rating films, writing reviews, and managing watchlists.
README
Letterboxd MCP Server
Origin Note: This project was originally based on Racimy/Letterboxd-MCP. It has since been extensively rewritten and expanded (V3+) to include comprehensive Playwright actions, multi-mode transport (Stdio/SSE), and expanded toolsets.
A Model Context Protocol (MCP) server for Letterboxd. It enables AI models to interact with Letterboxd data and perform account actions like rating films, writing reviews, and managing watchlists.
This server uses Playwright for authenticated account actions and fast HTML scraping for read endpoints.
Features
- Rich Film Metadata: Fetch posters, cast, runtime, genres, and synopses.
- Search: Comprehensive search for films, members, lists, and reviews.
- Member Insights: Get profile summaries, stats, watchlists, diary entries, and ratings.
- Account Management:
- Rate films (0.5 to 5 stars).
- Toggle "Watched", "Watchlist", and "Like" status.
- Write and update reviews (supports ratings, spoilers, and rewatch flags).
- Create and manage lists.
meShortcut: Use "me" as a username to target your authenticated account.- Automatic Pagination: Fetches all pages by default or supports manual cursor-based navigation.
Installation
Prerequisites
Setup
-
Clone the repository:
git clone https://github.com/yourusername/Letterboxd-MCP.git cd Letterboxd-MCP -
Install dependencies:
npm installNote: This will also download Chromium for Playwright.
-
Create a
.envfile (see Configuration):cp .env.example .env
Configuration
The server is configured via environment variables. Create a .env file in the root directory:
# Required for account actions & private data
LETTERBOXD_USERNAME=your_username
LETTERBOXD_PASSWORD=your_password
# Optional
PORT=3000
MCP_API_KEY=your_optional_secret_key
LETTERBOXD_LOGIN_FOR_READS=true # Set to false to avoid logging in for public data
Usage
Stdio Mode (Recommended for local MCP clients)
To run the server in Stdio mode for local clients like Claude Desktop:
node index.js --mode=stdio
SSE Mode (For remote integrations)
To run the server in SSE (Server-Sent Events) mode:
npm start
Integration with AI Agents
For detailed instructions on how to configure an AI agent (like Claude or Gemini) to use this server effectively, including specialized workflows like natural language review posting, see the Agent Instructions & Example Guide.
Integration with Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"letterboxd": {
"command": "node",
"args": ["/absolute/path/to/Letterboxd-MCP/index.js", "--mode=stdio"],
"env": {
"LETTERBOXD_USERNAME": "your_username",
"LETTERBOXD_PASSWORD": "your_password"
}
}
}
}
Available Tools
Read Tools
search: Search Letterboxd (films, lists, members, reviews).get_film: Get detailed metadata for a film.get_member: Get profile and stats for a member.get_member_watchlist: List films in a member's watchlist.get_member_diary: List a member's diary entries.get_member_films: List films a member has watched.get_member_ratings: List films rated by a member.get_member_reviews: List reviews written by a member.get_member_pinned: Get a member's favorite/pinned films.get_member_lists: List lists created by a member.get_list: Get entries and metadata for a specific list.get_review: Get full review details.get_current_user: Check authentication status.
Write Tools (Requires Authentication)
rate_film: Set a star rating.add_to_watched: Mark a film as watched/unwatched.add_to_watchlist: Add/remove a film from your watchlist.toggle_like: Like/unlike a film.write_review: Write or update a review.write_review_by_title: Search by title and write a review.add_to_list: Add a film to an existing list.create_list: Create a new list.
Development & Testing
Running Tests
- Read-only tests:
npm run test:read - Mutating tests (Requires live credentials):
RUN_MUTATING_TESTS=true npm run test:mutating - All tests:
npm run test:all
Credits
This project was originally based on Racimy/Letterboxd-MCP. It has since been extensively rewritten and expanded (V3+) to include comprehensive Playwright actions, multi-mode transport (Stdio/SSE), and expanded toolsets.
Security Warning
This server uses Playwright to automate your Letterboxd account. Never share your .env file or commit it to version control. Always use a strong MCP_API_KEY if running in SSE mode over the internet.
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.