{"id":"pymcp-sse","name":"pymcp-sse","af_score":55.8,"security_score":45.8,"reliability_score":30.0,"what_it_does":"pymcp-sse is an asynchronous Python library to build Model Context Protocol (MCP) servers and clients that communicate over HTTP/SSE. It provides base classes for server/client, tool registration and discovery, server push/notification support with keep-alives, and a multi-server client abstraction. It also includes an LLM client abstraction for integration with LLM providers (e.g., an Anthropic Claude example).","best_when":"You want a lightweight Python MCP server/client implementation where SSE transport and async concurrency are convenient, and you can rely on your surrounding infrastructure for security controls.","avoid_when":"You need comprehensive, explicitly documented auth, rate limiting semantics, retry/idempotency guidance, or production-grade operational guarantees that are clearly documented in the repository/docs.","last_evaluated":"2026-04-04T21:47:15.558058+00:00","has_mcp":true,"has_api":true,"auth_methods":["None explicitly documented for MCP server/client in provided README","Anthropic API key (example for LLM integration via ANTHROPIC_API_KEY)"],"has_free_tier":false,"known_gotchas":["Tool registration relies on type hints for describe_tools; missing/incorrect type hints may reduce tool schema quality.","SSE timeouts require alignment with keep-alive/ping intervals (README suggests read timeout > ping interval); misconfiguration can cause disconnects.","No explicit auth/rate-limit/idempotency/retry semantics were documented in the provided content, so agents may need to implement conservative retry/backoff and safety checks at the application layer."],"error_quality":0.0}