Steam Web API MCP server

Integrates with the Steam Web API. Allows for querying various stats, such as games in your library and their respective playtime.
Back to servers
Provider
David Soria Parra
Release date
Feb 17, 2025
Language
Java
Stats
1 star

This MCP Steam Server provides gaming context to AI assistants by integrating with the Steam API to fetch user gaming information. It allows AI systems to access and understand users' gaming activities and preferences through the Model Context Protocol.

Installation and Setup

Docker Installation

The easiest way to run the MCP Steam server is using Docker:

docker run --rm -i ghcr.io/dsp/mcp-server-steam:latest

Configuration

The server requires configuration using environment variables:

# Required configuration
STEAM_API_KEY=your_steam_api_key

You'll need to obtain a Steam API key from the Steam Developer site and provide it as an environment variable when running the server.

Usage

Running with Docker and Configuration

To run the server with your Steam API key:

docker run --rm -i -e STEAM_API_KEY=your_steam_api_key ghcr.io/dsp/mcp-server-steam:latest

API Usage

The server implements the Model Context Protocol (MCP) specification, allowing AI assistants to:

  • Retrieve users' game libraries
  • Access play history and statistics
  • Get information about games in a user's collection

For detailed API documentation on available endpoints and request formats, refer to the MCP Documentation.

Example API Requests

When integrating with an MCP-compatible AI system, the Steam context will be automatically provided to the assistant based on the user's Steam profile, enabling gaming-relevant conversations without requiring manual input of gaming preferences or history.

Troubleshooting

If you encounter issues:

  • Verify your Steam API key is valid and properly configured
  • Check that your Docker environment is running correctly
  • Ensure network connectivity to the Steam API services

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later