概览
What is OpenDota MCP Server?
A Model Context Protocol (MCP) server implementation for accessing OpenDota API data. It enables LLMs and AI assistants to retrieve real-time Dota 2 statistics, match data, player information, and more through a standard interface.
How to use OpenDota MCP Server?
Install via Smithery (npx -y @smithery/cli install @asusevski/opendota-mcp-server --client claude) or manually by cloning the repository and running python -m src.opendota_server.server. Optionally set the OPENDOTA_API_KEY environment variable using an API key from opendota.com. The server can also be configured as an MCP server in Claude Desktop by editing claude_desktop_config.json.
Key features of OpenDota MCP Server
- Access player profiles, statistics, and match history
- Retrieve detailed match information
- Look up professional players and teams
- Get hero statistics and rankings
- Search for players by name
- 16 specific tools for Dota 2 data queries
Use cases of OpenDota MCP Server
- Ask an AI assistant about a player’s recent matches
- Compare win/loss statistics for different players
- Get hero performance data during a live stream or discussion
- Find professional match results or team information
- Explore player word clouds or hero rankings
FAQ from OpenDota MCP Server
Do I need an API key to use OpenDota MCP Server?
An API key is optional but recommended. You can create one at https://www.opendota.com/api-keys and set it as the OPENDOTA_API_KEY environment variable.
How can I install OpenDota MCP Server?
You can install automatically via Smithery (npx -y @smithery/cli install @asusevski/opendota-mcp-server --client claude) or manually by cloning the repository and running the provided setup script or using uv with pyproject.toml.
What tools does OpenDota MCP Server include?
The server includes 16 tools such as get_player_by_id, get_match_data, search_player, get_hero_stats, get_pro_matches, get_team_info, and more. See the README for the full list.
How do I run OpenDota MCP Server with Claude Desktop?
Configure the MCP server in claude_desktop_config.json with the appropriate command. For WSL users, an example config is provided using wsl.exe and sourcing the Python virtual environment.
