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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。