opendota-mcp-server
Enables querying Dota 2 player statistics, match data, and hero information through the OpenDota API using natural language.
README
OpenDota MCP Server
A Model Context Protocol (MCP) server that provides seamless access to the OpenDota API for querying Dota 2 player statistics, match data, and hero information through AI assistants like Claude.
Features
- 20+ Tools across 5 categories for comprehensive Dota 2 data access
- Natural Language Support - Fuzzy matching for hero names, lane positions, and stat fields
- Dual Transport - Supports both stdio (local) and HTTP (remote) modes
- Rate Limiting - Built-in protection respecting OpenDota API limits
- Reference Data Caching - Fast lookups with local hero/item data
Available Tools
Player Tools (6 tools)
Query player statistics, win/loss records, hero preferences, and performance metrics:
get_player_info- Get player profile, win rate, and favorite heroesget_player_win_loss- Win/loss stats with advanced filteringget_heroes_played- Detailed statistics for all heroes playedget_player_peers- Find frequent teammatesget_player_totals- Aggregated player statisticsget_player_histograms- Distribution of matches across statistical fields
Hero Tools (4 tools)
Access hero information, matchups, and item builds:
get_heroes- List all heroes with attributesget_hero_matchups- Matchup data and win ratesget_hero_item_popularity- Popular item builds by game phaseget_hero_stats- Aggregated hero statistics and pick rates
Match Tools (3 tools)
Retrieve detailed match information and parsed data:
get_match_details- Comprehensive match informationget_parsed_match_details- Parsed match data with advanced analyticsget_player_recent_matches- Recent matches for a player
Lookup Tools (4 tools)
Convert names to IDs with fuzzy matching:
get_hero_id_by_name- Hero name → ID (handles typos)get_hero_by_id- Get hero details by IDconvert_lane_name_to_id- Lane/position → lane_role IDresolve_time_name- Time period names → OpenDota filter parameters
Misc Tools (3 tools)
Search and utility functions:
search_players- Search for players by nameget_constants- Get OpenDota constants and reference dataget_player_counts- Get player count by rank tier
Installation
Prerequisites
- Python 3.10 or higher
- pip package manager
Install from Source
# Clone the repository
git clone https://github.com/hkaanengin/opendota-mcp-server.git
cd opendota-mcp-server
# Create virtual environment
python3 -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install with dev dependencies
pip install -e ".[dev]"
# Or install runtime only
pip install -e .
Usage
Option 1: Local Server (stdio mode)
Best for Claude Desktop integration on your local machine.
Using Claude Desktop
Config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Recommended: Using the installed command
After running pip install -e ., add to your claude_desktop_config.json:
{
"mcpServers": {
"opendota": {
"command": "/path/to/your/opendota-mcp-server/.venv/bin/opendota-mcp"
}
}
}
Note: Replace
/path/to/your/opendota-mcp-serverwith the actual path where you cloned this repository. On macOS/Linux, runpwdin the project directory to find this path. On Windows, runcdto see the full path.
Alternative: Using Python module directly
{
"mcpServers": {
"opendota": {
"command": "/path/to/your/opendota-mcp-server/.venv/bin/python",
"args": ["-m", "opendota_mcp.server"]
}
}
}
Alternative: Using the shell script
{
"mcpServers": {
"opendota": {
"command": "/path/to/your/opendota-mcp-server/start_mcp.sh"
}
}
}
Using Docker:
{
"mcpServers": {
"opendota": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e", "MCP_TRANSPORT=stdio",
"hkaanengin/opendota-mcp-server:latest"
]
}
}
}
After updating the config:
- Save the file
- Restart Claude Desktop completely
- Start a new conversation
- Your OpenDota tools should now be available!
Manual Testing
# Run the server directly
opendota-mcp
# Or using Python module
python -m opendota_mcp.server
# Or using the shell script
./start_mcp.sh
Option 2: Remote Server (HTTP mode)
Access a deployed server from anywhere.
Public Server
Use the publicly deployed server at:
https://opendota-mcp-server-jylza6gata-ew.a.run.app/mcp
Claude Desktop (Remote Connection)
Add to your claude_desktop_config.json:
{
"mcpServers": {
"opendota": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-remote-http",
"https://opendota-mcp-server-jylza6gata-ew.a.run.app/mcp"
]
}
}
}
Claude.ai Web Interface
- Go to Claude.ai → Settings → MCP Servers
- Click "Add Server"
- Enter Server URL:
https://opendota-mcp-server-jylza6gata-ew.a.run.app/mcp - Save and start chatting!
Option 3: Deploy Your Own
Deploy to Google Cloud Run or any container platform:
# Build Docker image
docker build -t opendota-mcp-server .
# Run in HTTP mode
docker run -p 8080:8080 \
-e MCP_TRANSPORT=http \
-e PORT=8080 \
opendota-mcp-server
Configuration
Environment Variables
Create a .env file in the project root (or copy from .env.example):
# OpenDota API Key (optional)
# Get your API key from: https://www.opendota.com/api-keys
OPENDOTA_API_KEY=
# Logging level (DEBUG, INFO, WARNING, ERROR)
LOG_LEVEL=INFO
# Transport mode (stdio or http)
MCP_TRANSPORT=stdio
# HTTP server port (for HTTP mode)
PORT=8080
OpenDota API Key (Optional)
An API key is optional but recommended for higher rate limits and better performance.
Rate Limits:
- Without API key: 60 requests/minute (anonymous)
- With API key: Higher limits for registered users
How to get an API key:
- Visit https://www.opendota.com/api-keys
- Sign in with your Steam account
- Click "Create API Key"
- Copy the generated API key
- Add it to your
.envfile:OPENDOTA_API_KEY=your-api-key-here - Restart the server
The server will automatically detect and use the API key when configured. You'll see a confirmation message in the logs:
✅ OpenDota API key configured (higher rate limits enabled)
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Acknowledgments
- OpenDota for providing the excellent Dota 2 API
- FastMCP for the MCP framework
- The Model Context Protocol team at Anthropic
- The Dota 2 community
Support
For issues, questions, or contributions:
- Open an issue on GitHub
- Check existing issues for solutions
- Review the OpenDota API documentation
Made with ❤️ for the Dota 2 community
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.