Tarkov MCP Server
Provides comprehensive access to Escape from Tarkov game data, including item statistics, market prices, quest information, and map details via the tarkov.dev API. It enables users to analyze market trends, compare items, and track game progression through natural language interactions.
README
Tarkov MCP Server
A Model Context Protocol (MCP) server that provides access to Escape from Tarkov game data through the community-maintained Tarkov API.
[!IMPORTANT]
I am not affiliated with the tarkov.dev project or API. I simply built this MCP server to interact with what they have built. If you appreciate their work, please consider donating to them here!
Features
Item Tools
- search_items - Search for items by name or type (supports localization)
- get_item_details - Get detailed item information including prices, stats, and usage
- get_item_prices - Get current pricing information for items
- compare_items - Compare multiple items side by side
- get_quest_items - Get quest-specific items with their associated tasks
Market Tools
- get_flea_market_data - Current flea market price data
- get_barter_trades - Available barter exchanges from traders
- calculate_barter_profit - Profit/loss analysis for barter trades
- get_ammo_data - Ammunition statistics and pricing
- get_hideout_modules - Hideout module information and requirements
Map Tools
- get_maps - List all available maps
- get_map_details - Detailed map information including spawns and extracts
- get_map_spawns - Spawn locations and information for specific maps
Trader Tools
- get_traders - List all traders
- get_trader_details - Detailed trader information
- get_trader_items - Items available from specific traders
Quest Tools
- get_quests - List quests, optionally filtered by trader
- get_quest_details - Detailed quest information including objectives and rewards
- search_quests - Search quests by name or description
Community Tools
- get_goon_reports - Get recent community-driven goon squad sighting reports
Installation
Prerequisites
- Python 3.8 or higher
- pip package manager
Install Dependencies
You can install the dependencies in several ways:
First, clone the repository and navigate into the repository root directory.
Option 1: Install as a package (recommended)
pip install -e .
Option 2: Install with development dependencies
pip install -e ".[dev]"
Option 3: Using requirements.txt (legacy)
pip install -r requirements.txt
Claude Desktop Setup
To use this MCP server with Claude Desktop, make sure you've followed the install instructions above.
Add the following configuration to your Claude Desktop config file:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"tarkov": {
"command": "python",
"args": ["-m", "tarkov_mcp"],
"cwd": "/path/to/tarkov-mcp"
}
}
}
Replace /path/to/tarkov-mcp with the actual path to this project directory.
After updating the config file, restart Claude Desktop for the changes to take effect.
Development
Running Tests
pytest tests/ -v
Running the Server
python -m tarkov_mcp
Configuration
The server can be configured using environment variables:
TARKOV_API_URL- Tarkov API endpoint (default: https://api.tarkov.dev/graphql)MAX_REQUESTS_PER_MINUTE- Rate limit (default: 60)REQUEST_TIMEOUT- Request timeout in seconds (default: 30)
Features
- Multi-language Support: Full localization support for 16 languages (English, Russian, German, French, Spanish, etc.)
- Enhanced Item Data: Comprehensive item properties including new weapon ballistics, armor materials, and medical effects
- Community Integration: Goon squad tracking and quest-specific item information
- Modern API Compatibility: Updated GraphQL queries using latest Tarkov API schema structure
- Rate Limiting: Built-in rate limiting to respect API limits (60 requests per minute by default)
- Error Handling: Comprehensive error handling with detailed error messages
- Async Support: Fully asynchronous implementation for better performance
- Comprehensive Testing: Extensive test suite with pytest
- Type Safety: Full type hints throughout the codebase
API Data Source
This server uses the community-maintained Tarkov API at https://api.tarkov.dev/graphql, which provides real-time data for Escape from Tarkov including:
- Item information and statistics
- Current market prices
- Trader information and barter trades
- Quest and task data
- Map and location information
- Ammunition data
- Hideout module requirements
Troubleshooting
Common Issues
- Rate Limiting: If you encounter rate limit errors, the server will automatically retry with exponential backoff
- Network Issues: Check your internet connection and ensure the Tarkov API is accessible
- Claude Desktop Integration: Make sure the path in your config file is correct and Python is in your PATH
Logging
The server includes comprehensive logging. To enable debug logging, set the environment variable:
export LOG_LEVEL=DEBUG
Contributing
We welcome contributions! Please see CONTRIBUTING.md for detailed guidelines.
Quick start:
- Fork the repository
- Set up development environment:
pip install -e ".[dev]" - Install pre-commit hooks:
pre-commit install - Create a feature branch
- Make your changes with tests
- Run quality checks:
pre-commit run --all-files - Submit a pull request
License
GPL-3.0 License - see LICENSE file for details.
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。