opencritic-mcp
Enables AI assistants to search for games and retrieve aggregated critic scores, review tiers, and individual reviews from OpenCritic. Provides tools for game search, score retrieval, and review lookup via the OpenCritic API.
README
opencritic-mcp
An MCP (Model Context Protocol) server that gives AI assistants access to OpenCritic game review scores via the official OpenCritic API on RapidAPI.
Search for games and retrieve aggregated critic scores, review tiers, and individual reviews — all without scraping. For full API endpoints and response specs, see the OpenCritic API Documentation.
Tools
| Tool | Parameters | Description |
|---|---|---|
search_game |
query (string) |
Search by game title — returns up to 10 matches with IDs |
get_game |
id (number), platform? (string) |
Get critic score, % recommended, tier, developer, publisher, platforms, genres, loot boxes, and box art. Filter by platform (e.g. 'PC', 'PS5', 'Xbox'). |
get_game_reviews |
id (number), platform? (string), limit? (number) |
Get individual critic reviews (outlet, score, author, language, platform tags, excerpt, link). Filter by platform. |
Prerequisites
- Node.js v18 or later
- A free RapidAPI key for the OpenCritic API
Getting a RapidAPI key
- Go to rapidapi.com/opencritic/api/opencritic-api
- Sign up or log in (free)
- Subscribe to the Basic plan (free tier: 200 requests/day, 25 searches/day)
- Copy your
X-RapidAPI-Keyfrom the dashboard
Your key is only ever used locally. It is read from an environment variable at runtime and never stored in the package.
Installation
Option A — npx (no install required)
{
"mcpServers": {
"opencritic": {
"command": "npx",
"args": ["-y", "opencritic-mcp"],
"env": {
"RAPIDAPI_KEY": "your_rapidapi_key_here"
}
}
}
}
Option B — Clone and build locally
git clone https://github.com/brandikun/opencritic-mcp.git
cd opencritic-mcp
npm install
npm run build
Then add to your MCP config:
{
"mcpServers": {
"opencritic": {
"command": "node",
"args": ["/absolute/path/to/opencritic-mcp/dist/index.js"],
"env": {
"RAPIDAPI_KEY": "your_rapidapi_key_here"
}
}
}
}
MCP Client Config Locations
| Client | Config file |
|---|---|
| Antigravity / AGY | ~/.gemini/antigravity-cli/settings.json |
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
Example usage
Once connected, you can ask your AI assistant things like:
- "Search for Hollow Knight on OpenCritic"
- "What's the critic score for Disco Elysium?"
- "Show me the top critic reviews for Elden Ring"
- "Cross-reference my Steam library with OpenCritic scores" (when paired with a Steam MCP)
Security notes
- Your
RAPIDAPI_KEYis passed via environment variable — it never appears in source code or gets committed to git - The server uses only Node's built-in
fetchand the official MCP SDK — no third-party HTTP clients - If
RAPIDAPI_KEYis missing, the server exits immediately with a clear error message
Free tier limits & Caching
| Limit | Value |
|---|---|
| Requests per day | 200 |
| Searches per day | 25 |
| Requests per second | 4 |
Built-in Caching: To protect your daily RapidAPI quota, responses are cached in memory for 1 hour. Repeated detail or review queries cost 0 API requests.
License
MIT
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.