Steam Reviews MCP
About Search Steam games, fetch user reviews, and analyze sentiment with topic drill-down to make informed purchasing decisions.
README
Steam Reviews MCP Server
A Model Context Protocol (MCP) server for Steam game reviews and analysis. Search games, fetch reviews, and analyze sentiment through the Model Context Protocol.
🎯 Key Features
- 🔍 Game Search - Search Steam games by name with batch support (up to 5 queries)
- 📊 Detailed Game Info - Get comprehensive game data with criteria filtering
- 💬 Review Fetching - Advanced filtering (time-bounded, Steam Deck, review bombs)
- 🧠 Sentiment Analysis - NLP-powered analysis with topic drill-down
- ⚡ Smart Caching - 70-85% API call reduction with variable TTL
- 🔗 Example Quotes - Clickable Steam community links for review quotes
🔒 Security
- 🐳 Hardened Docker Images
- Non-root user (mcpuser)
- Multi-stage builds
- Minimal Alpine base
- dumb-init process management
- ✅ Input Validation
- Zod schema validation for all inputs
- Type-safe TypeScript throughout
🛠️ Available Tools
| Tool | Purpose | Key Features |
|---|---|---|
| search_steam_games | Search for games | Single/batch search, AppID lookup, price info |
| get_game_info | Get game details | Batch lookup, criteria filtering, system requirements, DLC |
| fetch_reviews | Fetch user reviews | Advanced filters, pagination, time-bounded queries |
| analyze_reviews | Analyze sentiment | NLP analysis, topic drill-down, example quotes with links |
📋 Prerequisites
- Node.js 18.0 or higher
- npm or compatible package manager
- No API key required! Uses public Steam Store API
🚀 Quick Start
Option 1: NPM (Recommended)
npm install -g @jhomen368/steam-reviews-mcp
Configure with Claude Desktop:
Add to your configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"steam-reviews": {
"command": "npx",
"args": ["-y", "@jhomen368/steam-reviews-mcp"]
}
}
}
Option 2: Docker (HTTP Mode)
docker run -d \
--name steam-reviews-mcp \
-p 8086:8086 \
ghcr.io/jhomen368/steam-reviews-mcp:latest
Docker Compose:
services:
steam-reviews-mcp:
image: ghcr.io/jhomen368/steam-reviews-mcp:latest
container_name: steam-reviews-mcp
ports:
- "8086:8086"
restart: unless-stopped
Test the server:
curl http://localhost:8086/health
Connect MCP clients:
- Transport: SSE (Server-Sent Events)
- URL:
http://localhost:8086/mcp
Option 3: From Source
git clone https://github.com/jhomen368/steam-reviews-mcp.git
cd steam-reviews-mcp
npm install
npm run build
node build/index.js
💡 Usage Examples
Search for Games
// Single search
search_steam_games({
query: "Baldur's Gate 3",
limit: 10
})
// Batch search (up to 5 queries)
search_steam_games({
queries: ["Elden Ring", "Cyberpunk 2077", "Hades"],
limit: 5
})
Get Game Info with Criteria
get_game_info({
appIds: [1086940, 1245620],
criteria: {
minReviewScore: 80,
minReviews: 1000,
requireMetacritic: true
},
includeRequirements: true,
includeDlc: true
})
Fetch Reviews with Filters
// Recent positive reviews
fetch_reviews({
appId: 1086940,
filter: "recent",
reviewType: "positive",
dayRange: 30
})
// Filter out review bombs
fetch_reviews({
appId: 1086940,
filterOfftopicActivity: true
})
Analyze Sentiment
// General analysis
analyze_reviews({
appId: 1086940,
sampleSize: 100
})
// Topic-focused analysis
analyze_reviews({
appId: 1086940,
topic: "performance"
})
Natural Language Examples
Simply ask your AI assistant:
- "Search for Elden Ring on Steam"
- "Get info about Baldur's Gate 3 including system requirements"
- "What are people saying about Cyberpunk 2077 recently?"
- "Analyze negative reviews for No Man's Sky - what are the main complaints?"
- "Find free games with at least 90% positive reviews"
⚙️ Configuration
Environment Variables
All configuration is optional with sensible defaults:
# Cache settings
CACHE_ENABLED=true # Enable caching (default: true)
CACHE_MAX_SIZE=1000 # Max cache entries
# Rate limiting
RATE_LIMIT_ENABLED=true # Enable rate limiting (default: true)
MAX_REQUESTS_PER_MINUTE=30 # Max API calls per minute
# HTTP mode (for Docker)
HTTP_MODE=false # Enable HTTP transport
PORT=8086 # HTTP server port
📚 Documentation
- CHANGELOG.md - Version history and release notes
- CONTRIBUTING.md - Contribution guidelines
- Steam Store API - Steam API reference
🔧 Troubleshooting
Connection Issues
- Verify Steam Store API is accessible (no firewall blocks)
- Check rate limiting if receiving 429 errors
- Review logs for timeout errors
Docker Issues
# Check logs
docker logs steam-reviews-mcp
# Verify health
curl http://localhost:8086/health
Build Issues
# Ensure Node.js 18+
node --version
# Clean rebuild
rm -rf node_modules build
npm install
npm run build
🤝 Contributing
Contributions welcome! Please see CONTRIBUTING.md for guidelines.
📄 License
MIT License - see LICENSE for details
🙏 Acknowledgments
- Steam - Gaming platform and API
- Model Context Protocol - Open protocol for AI integrations
- Anthropic - Creators of the MCP standard
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.