test-mcp-server
Verified Safeby beanspapa
Overview
An MCP server designed to provide rich, interactive sports data through React widgets and text-based tools to conversational AI platforms like ChatGPT. It fetches game schedules, detailed statistics (team/player stats, standings, head-to-head), and is built for modularity and extensibility to integrate various external APIs.
Installation
npm run devEnvironment Variables
- ENVIRONMENT
- HTTP_PORT
- LOG_LEVEL
- BASE_URL
- SPORTS_API_KEY
- SPORTS_API_BASE_URL
- USE_MOCK_SPORTS_DATA
- RATE_LIMIT_PER_MINUTE
- RATE_LIMIT_ENABLED
- CONTACT_EMAIL
- PRIVACY_POLICY_URL
Security Notes
The server demonstrates robust security practices: - **SafeFastMCPWrapper**: Protects against internal FastMCP API changes, providing clear error messages and preventing crashes. - **AST-based `safe_eval()`**: Replaced direct `eval()` usage (often a security vulnerability) with a secure AST parsing mechanism for expression evaluation (though the calculator tool has been removed in latest production configuration). - **Pydantic BaseSettings**: Ensures type-safe and validated configuration loaded from environment variables or .env files, guarding against invalid or malicious settings. - **RateLimitMiddleware**: Implements in-memory rate limiting per client IP, mitigating potential DoS attacks. - **Input Validation**: Pydantic models are used for validating tool input schemas, ensuring only valid data is processed. - **API Key Protection**: API keys are managed via environment variables and are not logged or exposed in error messages. - **DNS Rebinding Protection**: Explicitly disabled (`enable_dns_rebinding_protection=False`) due to the specific requirements of OpenAI App Store integration, which typically involves requests from multiple dynamic origins. This is a deliberate trade-off for platform compatibility, though generally a security consideration.
Similar Servers
aderyn
A Rust-based Solidity static analyzer that identifies vulnerabilities in smart contracts and provides developer tooling such as LSP and an MCP server for integration with other development environments and AI agents.
enrichmcp
Exposes structured data models as a semantic, discoverable API for AI agents.
graphlit-mcp-server
The Model Context Protocol (MCP) Server integrates with the Graphlit platform to ingest diverse data sources, build a searchable knowledge base, and enable LLM-powered search, retrieval, RAG, and generative capabilities for MCP clients.
thought-chain-mcp
Transforms any AI model into an advanced reasoning engine by providing structured, step-by-step thinking with persistent memory across sessions.