OpenSubtitles MCP Server

OpenSubtitles MCP Server

Enables searching and downloading subtitles from OpenSubtitles.com through their API. Supports comprehensive search by movie title, IMDB/TMDB ID, file hash, and TV show episodes with multiple subtitle formats (SRT, ASS, VTT).

Category
访问服务器

README

OpenSubtitles MCP Server

A TypeScript/Node.js-based MCP (Model Context Protocol) server for OpenSubtitles API integration. This server provides subtitle search and download functionality with a freemium model, using the Kong gateway at api.opensubtitles.com for all API management.

Features

  • Comprehensive Search: Search subtitles using all OpenSubtitles API parameters (title, IMDB ID, TMDB ID, file hash, etc.)
  • Multiple Download Formats: Support for SRT, ASS, and VTT subtitle formats
  • File Hash Calculation: Calculate OpenSubtitles hash for exact movie file matching
  • Rate Limiting: Integrated with Kong gateway for proper rate limiting
  • Freemium Model: Unlimited search, downloads limited by API key status

Installation & Usage

The OpenSubtitles MCP Server supports two modes:

1. HTTP Mode (Recommended for Server Deployment)

Run as a web server on port 1620:

# Install dependencies
npm install
npm run build

# Start HTTP server
npm start
# or
PORT=1620 MCP_MODE=http node dist/index.js

Access points:

  • Health Check: http://localhost:1620/health
  • API Info: http://localhost:1620/
  • MCP Endpoint: http://localhost:1620/sse (Server-Sent Events)

2. Stdio Mode (For Claude Desktop)

Quick Start with npx

npx @opensubtitles/mcp-server

Install via mcp-get

npx @michaellatman/mcp-get@latest install @opensubtitles/mcp-server

Claude Desktop Integration

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "opensubtitles": {
      "command": "npx",
      "args": ["-y", "@opensubtitles/mcp-server"],
      "env": {
        "MCP_MODE": "stdio",
        "OPENSUBTITLES_USER_KEY": "your_api_key_here"
      }
    }
  }
}

MCP Tools

1. search_subtitles

Search for subtitles with comprehensive parameter support:

Parameters:

  • query (string): Text search query
  • imdb_id (number): IMDB ID for exact matching
  • tmdb_id (number): TMDB ID for exact matching
  • parent_imdb_id (number): Parent IMDB ID for TV series
  • parent_tmdb_id (number): Parent TMDB ID for TV series
  • season_number (number): Season number for TV episodes
  • episode_number (number): Episode number for TV episodes
  • year (number): Release year
  • moviehash (string): OpenSubtitles file hash for exact matching
  • moviebytesize (number): File size in bytes for hash matching
  • languages (string): Comma-separated language codes (e.g., 'en,es,fr')
  • machine_translated (string): Include machine translated subtitles
  • ai_translated (string): Include AI translated subtitles
  • hearing_impaired (string): Include hearing impaired subtitles
  • foreign_parts_only (string): Include foreign parts only
  • trusted_sources (string): Only trusted sources
  • order_by (string): Sort order
  • order_direction (string): Sort direction (asc/desc)

Example:

await mcpClient.callTool("search_subtitles", {
  query: "The Matrix",
  year: 1999,
  languages: "en"
});

2. download_subtitle

Download subtitle content by ID:

Parameters:

  • subtitle_id (string, required): Subtitle ID from search results
  • format (string): Subtitle format (srt, ass, vtt) - defaults to 'srt'
  • user_api_key (string): Optional user API key for authenticated downloads

Example:

await mcpClient.callTool("download_subtitle", {
  subtitle_id: "123456",
  format: "srt",
  user_api_key: "your_api_key"
});

3. calculate_file_hash

Calculate OpenSubtitles hash for local movie files:

Parameters:

  • file_path (string, required): Path to the movie file

Example:

await mcpClient.callTool("calculate_file_hash", {
  file_path: "/path/to/movie.mkv"
});

Usage Examples

Search by Movie Title

await mcpClient.callTool("search_subtitles", {
  query: "Inception",
  year: 2010,
  languages: "en"
});

Search by File Hash

// First calculate the hash
const hashResult = await mcpClient.callTool("calculate_file_hash", {
  file_path: "/path/to/inception.mkv"
});

// Then search using the hash
await mcpClient.callTool("search_subtitles", {
  moviehash: "8e245d9679d31e12",
  moviebytesize: 12909756
});

Search TV Show Episodes

await mcpClient.callTool("search_subtitles", {
  parent_imdb_id: 944947, // Game of Thrones
  season_number: 1,
  episode_number: 5,
  languages: "en"
});

Rate Limiting & API Keys

Anonymous Usage

  • Search: Unlimited
  • Downloads: 0 per day (Kong enforced)

With OpenSubtitles API Key

  • Search: Unlimited
  • Downloads: Based on your OpenSubtitles account quota

Getting an API Key

  1. Register at OpenSubtitles.com
  2. Get your free API key
  3. Set the OPENSUBTITLES_USER_KEY environment variable or pass it in tool calls

Development

Prerequisites

  • Node.js 18.0.0 or higher
  • TypeScript

Setup

git clone <repository>
cd mcp-opensubtitles
npm install

Building

npm run build

Development Commands

# HTTP Mode (Web Server)
npm run dev                # Build and run HTTP server on port 1620
npm start                  # Run built HTTP server

# Stdio Mode (Claude Desktop)
npm run dev:stdio          # Build and run stdio mode
npm start:stdio            # Run built stdio mode

# Development with Auto-rebuild
npm run watch

Testing

# For HTTP mode testing
curl http://localhost:1620/health        # Health check
curl http://localhost:1620/             # API info

# For Stdio mode testing
npm test                   # Run evaluation tests
npm run inspector          # Debug with MCP Inspector (stdio mode)

# MCP evaluation tests
npx mcp-eval evals/evals.ts dist/index.js

Environment Variables

OPENSUBTITLES_API_BASE=https://api.opensubtitles.com  # Default Kong gateway
NODE_ENV=production
PORT=1620
OPENSUBTITLES_USER_KEY=your_api_key_here  # Optional

Architecture

The server uses a clean architecture with the following components:

  • MCP Server Core (src/server.ts): Main MCP protocol implementation
  • Kong API Client (src/api-client.ts): HTTP client for Kong gateway communication
  • Tools (src/tools/): Individual tool implementations
  • Utilities (src/utils/): Helper functions for hash calculation

All API requests go through the Kong gateway at api.opensubtitles.com, which handles:

  • Rate limiting enforcement
  • API key validation
  • Request routing to OpenSubtitles API
  • Error handling and responses

Error Handling

The server provides helpful error messages for common scenarios:

  • Rate Limit Exceeded: "Download limit reached. Get your free API key at opensubtitles.com/api"
  • Invalid API Key: "Invalid API key. Please check your OpenSubtitles API key"
  • File Not Found: Clear file path validation messages
  • Network Errors: Descriptive network connectivity messages

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests for new functionality
  5. Submit a pull request

License

MIT License - see LICENSE file for details

Support

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选