Valorant MCP Server
Provides Valorant game data through the Model Context Protocol, including player details, match history, MMR, leaderboards, and game content using the HenrikDev API.
README
Valorant MCP Server
A Model Context Protocol (MCP) server that provides access to Valorant game data using the unofficial Valorant API.
Features
- Player Information: Get account details, MMR, and match history
- Match Data: Detailed match information and statistics
- Game Content: Agents, maps, weapons, and other game assets
- Service Status: Check Valorant service status and maintenance
- Leaderboards: Competitive rankings and leaderboards
Prerequisites
- Python 3.11 or higher
- A Valorant API key from HenrikDev API
- Internet connection for API requests
Installation
Option 1: Run via uvx (Recommended)
No local environment setup required. uvx runs the packaged console script directly.
# Install UV if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh
# Run from GitHub (replace with your repo URL)
uvx --from git+https://github.com/<your-username>/valorant-mcp-server.git valorant-mcp-server
# Windows (PowerShell)
uvx --from git+https://github.com/<your-username>/valorant-mcp-server.git valorant-mcp-server
Optionally set an API key in the environment first (or use the set_api_key tool at runtime):
export VALORANT_API_KEY="your_api_key_here"
uvx --from git+https://github.com/<your-username>/valorant-mcp-server.git valorant-mcp-server
Option 2: Local UV/Pip environment
# Clone and setup
git clone https://github.com/<your-username>/valorant-mcp-server.git
cd valorant-mcp-server
# With UV
uv venv && . .venv/bin/activate # Windows: .venv\Scripts\activate
uv pip install -r requirements.txt
# Or with pip
python -m venv .venv && . .venv/bin/activate
pip install -r requirements.txt
# Environment
cp env.example .env # Windows: copy env.example .env
# Edit .env and add your VALORANT_API_KEY
Usage
Running the Server
# Recommended: uvx from git
uvx --from git+https://github.com/<your-username>/valorant-mcp-server.git valorant-mcp-server
# Locally (if you've installed deps)
python server.py
Note: The server will start and wait for MCP client connections. It will show a warning if no API key is set, but you can still use the set_api_key tool to configure it at runtime.
Using with MCP Clients
Claude Desktop
Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"valorant": {
"command": "uvx",
"args": ["--from", "git+https://github.com/<your-username>/valorant-mcp-server.git", "valorant-mcp-server"],
"env": {
"VALORANT_API_KEY": "your_api_key_here"
}
}
}
}
Cline (VS Code Extension)
Add to your Cline configuration:
{
"mcpServers": {
"valorant": {
"command": "uvx",
"args": ["--from", "git+https://github.com/<your-username>/valorant-mcp-server.git", "valorant-mcp-server"],
"env": {
"VALORANT_API_KEY": "your_api_key_here"
}
}
}
}
Generic MCP Client
Use the packaged command with uvx:
uvx --from git+https://github.com/<your-username>/valorant-mcp-server.git valorant-mcp-server
Available Tools
- get_account_details(name, tag, region="na"): Basic account info (PUUID, level, card, region).
- get_match_history_by_name(name, tag, region="na", size=10): Recent matches with per-game stats.
- get_match_details(match_id, region="na"): Full details for a specific match.
- get_mmr_details_by_name(name, tag, region="na"): Current competitive tier, ELO, RR.
- get_mmr_history_by_name(name, tag, region="na", size=10): Competitive MMR history with match IDs.
- get_lifetime_matches_by_name(name, tag, region="na", mode=None, map_filter=None, page=1, size=20): Aggregate lifetime stats and list of matches.
- get_leaderboard(region="na", season="e8a1"): Top players for a region/season.
- get_content(region="na"): Agents, maps, and other content.
- get_status(region="na"): Service status and incidents.
- set_api_key(api_key_input): Set HenrikDev API key at runtime.
- get_detailed_competitive_analysis(name, tag, region="na", match_count=10): Correlate MMR history with match stats.
- find_leaderboard_position(name, tag, region="na", season="e8a1"): Locate a player on the leaderboard (Immortal 3+).
Testing
You can validate connectivity by launching the server via uvx and connecting from your MCP client (Claude Desktop/Cline/Cursor). Use the get_status and get_content tools to confirm responses.
Configuration
Environment Variables
VALORANT_API_KEY: Your Valorant API key (required)
API Key Setup
You can set your API key in two ways:
- Environment Variable: Set
VALORANT_API_KEYin your environment - Runtime: Use the
set_api_keytool to configure it at runtime
Project Structure
valorant-mcp-server/
├── server.py # MCP server implementation (FastMCP)
├── pyproject.toml # Package metadata + console script
├── requirements.txt # Python dependencies (for local installs)
├── env.example # Environment variables template
├── mcp-client-configs.md # Client configuration examples
├── TOOLS_DOCUMENTATION.md # Detailed tool docs
├── LICENSE # MIT License
├── .gitignore # Git ignore file
└── README.md # This file
API Integration
This server uses:
- HenrikDev API - The core API service for Valorant data
- Direct HTTP Requests - Python requests library for API calls
- FastMCP - MCP framework
Error Handling
The server includes comprehensive error handling for:
- Invalid API keys
- Rate limiting
- Network errors
- Invalid player names or regions
- Service unavailability
All errors are logged and returned in a structured format.
Development
Adding New Tools
To add new Valorant API endpoints:
- Create a new function decorated with
@mcp.tool() - Add proper error handling with try/catch blocks
- Use the global
valo_apiinstance - Return structured data using Pydantic models
- Update this README with the new tool documentation
Code Quality
# Install development tools
pip install black isort mypy flake8
# Format code
black server.py test_server.py
isort server.py test_server.py
# Type checking
mypy server.py
# Linting
flake8 server.py test_server.py
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
This project is licensed under the MIT License.
Acknowledgments
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。