OpenDota

What is OpenDota MCP Server?

OpenDota MCP Server is a Model Context Protocol (MCP) server designed to provide large language models (LLMs) and AI assistants with access to real-time Dota 2 game data via the OpenDota API. It acts as an intermediary, translating requests from AI models into OpenDota API calls and returning structured game information.

How to use OpenDota MCP Server?

1. Installation:

   • Clone the repository: git clone https://github.com/asusevski/opendota-mcp-server.git
   • Navigate to the directory: cd opendota-mcp-server
   • Automated setup: ./scripts/setup_env.sh or manual installation with uv add pyproject.toml.
   • For development dependencies: uv pip install -e ".[dev]".

2. API Key Setup:

   • (Optional but recommended) Obtain an OpenDota API key from https://www.opendota.com/api-keys.
   • Set the API key as an environment variable: export OPENDOTA_API_KEY=your_api_key_here.

3. Running the Server:

   • Directly: python -m src.opendota_server.server.
   • With Claude Desktop: Configure claude_desktop_config.json with the appropriate command for your environment (e.g., WSL).

4. Using the Client:

   • An example client is provided: python -m src.client.

Key Features of OpenDota MCP Server

OpenDota MCP Server offers a wide range of functionalities for accessing Dota 2 data, including:

• Player Information: Retrieve player profiles, statistics, match history, win/loss records, most played heroes, and word clouds from chat.
• Match Data: Get detailed information for specific matches, recent public matches, and professional matches.
• Hero Statistics: Access statistics and rankings for various Dota 2 heroes.
• Team Information: Obtain details about professional teams.
• Search Functionality: Search for players by name.
• Social Connections: Discover players who have played with a specified player.

Use Cases of OpenDota MCP Server

• AI-powered Dota 2 Assistants: Develop intelligent assistants that can answer questions about Dota 2, provide real-time game insights, or analyze player performance.
• Game Data Analysis: Conduct in-depth analysis of Dota 2 matches, player trends, and hero meta.
• Educational Tools: Create applications that help new players understand game mechanics and strategies.
• Content Creation: Generate data-driven content for Dota 2 blogs, videos, or streams.

FAQ about OpenDota MCP Server

Q: Do I need an OpenDota API key to use this server? A: While optional, it is highly recommended to obtain an OpenDota API key for optimal usage and to avoid rate limits.

Q: Can I use this with other LLMs besides Claude Desktop? A: Yes, as an MCP server, it is designed to work with any LLM or AI assistant that supports the Model Context Protocol.

Q: What kind of Dota 2 data can I access? A: You can access a comprehensive range of data including player stats, match details, hero information, team data, and more, as outlined in the "Specific tools included" section of the README.

OpenDota MCP Server

A Model Context Protocol (MCP) server implementation for accessing OpenDota API data. This server enables LLMs and AI assistants to retrieve real-time Dota 2 statistics, match data, player information, and more through a standard interface.

Features

• 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
• And more!

Installation

# Clone the repository
git clone https://github.com/asusevski/opendota-mcp-server.git
cd opendota-mcp-server

# Option 1: Automated setup (works with bash, zsh, and other shells)
./scripts/setup_env.sh

# Option 2: Manual installation with uv
uv add pyproject.toml

# For development dependencies
uv pip install -e ".[dev]"

Usage

Setting up your environment

1. (Optional but recommended) Create an OpenDota API key at https://www.opendota.com/api-keys
2. Set your API key as an environment variable:

export OPENDOTA_API_KEY=your_api_key_here

Running the server directly

python -m src.opendota_server.server

Running the server with Claude Desktop

Follow this: https://modelcontextprotocol.io/quickstart/user

If you use WSL, assuming you have cloned the repo and set up the python environment, this is how I wrote the claude_desktop_config.json:

{
  "mcpServers": {
    "opendota": {
      "command": "wsl.exe",
      "args": [
        "--",
        "bash",
        "-c",
        "cd ~/opendota-mcp-server && source .venv/bin/activate && python src/opendota_server/server.py"
      ]
    }
  }
}

Using the example client

python -m src.client

Specific tools included:

• get_player_by_id - Retrieve player information by account ID
• get_player_recent_matches - Get recent matches for a player
• get_match_data - Get detailed data for a specific match
• get_player_win_loss - Get win/loss statistics for a player
• get_player_heroes - Get a player's most played heroes
• get_hero_stats - Get statistics for heroes
• search_player - Search for players by name
• get_pro_players - Get list of professional players
• get_pro_matches - Get recent professional matches
• get_player_peers - Get players who have played with a specified player
• get_heroes - Get list of all Dota 2 heroes
• get_player_totals - Get player's overall stats totals
• get_player_rankings - Get player hero rankings
• get_player_wordcloud - Get most common words used by player in chat
• get_team_info - Get information about a team
• get_public_matches - Get recent public matches
• get_match_heroes - Get heroes played in a specific match

License

MIT