test-mcp-server
Verified Safeby jhpark-psynet
Overview
Enables LLM agents to interact with sports data (schedules, detailed statistics) and other external APIs, presenting results via interactive React widgets or formatted text. Supports multi-sport, multi-league data fetching with caching and robust error handling.
Installation
npm run devEnvironment Variables
- ENV
- HTTP_HOST
- HTTP_PORT
- LOG_LEVEL
- LOG_FILE
- EXTERNAL_API_BASE_URL
- EXTERNAL_API_KEY
- EXTERNAL_API_TIMEOUT_S
- EXTERNAL_API_AUTH_HEADER
- EXTERNAL_API_AUTH_SCHEME
- SPORTS_API_BASE_URL
- SPORTS_API_KEY
- SPORTS_API_TIMEOUT_S
- USE_MOCK_SPORTS_DATA
- CACHE_TTL_SECONDS
- CACHE_MAX_SIZE
- BASE_URL
- RATE_LIMIT_PER_MINUTE
- RATE_LIMIT_ENABLED
Security Notes
The server employs robust input validation using Pydantic, replaces dangerous `eval()` with a safe AST-based evaluator, and implements rate limiting. However, it explicitly disables DNS rebinding protection in `TransportSecuritySettings` to accommodate diverse origins in ChatGPT App Store integration, which can be a security concern in other deployment contexts. API keys are managed via environment variables/`.env` files.
Similar Servers
SageMCP
A scalable platform for hosting MCP servers with multi-tenant support, OAuth integration, and connector plugins for various services, deployed on Kubernetes.
leanmcp-sdk
Building production-ready Model Context Protocol (MCP) servers with TypeScript, supporting features like authentication, elicitation, and UI integration for AI agents.
mcp
Provides a Model Context Protocol (MCP) server for accessing comprehensive sports data and analytics from the BALLDONTLIE API across 18 major sports and leagues.
tokenbowl-mcp
A Model Context Protocol (MCP) server for a fantasy football league, providing tools to interact with the Sleeper API, Fantasy Nerds API, and Token Bowl Chat for LLM-powered fantasy management.