{"id":"joshuaalpuerto-mcp-agent","name":"mcp-agent","af_score":48.0,"security_score":42.5,"reliability_score":27.5,"what_it_does":"A TypeScript framework for building AI agents that can interact with Model Context Protocol (MCP) servers and local tool functions. It provides agent abstraction, an MCP connection manager for reusing server connections, per-agent MCP tool aggregation, LLM provider integration (example for Fireworks AI), simple in-memory message history, and example orchestration/workflows.","best_when":"You want a lightweight Node/TypeScript developer experience for MCP tool calling with connection reuse across agents and you control the runtime/tool configuration.","avoid_when":"You cannot control MCP server configuration/transport security or you require strong built-in operational guarantees (SLA, detailed retry/idempotency semantics) without additional engineering.","last_evaluated":"2026-03-30T15:34:32.356609+00:00","has_mcp":true,"has_api":false,"auth_methods":["Environment-variable based API keys for LLM/tool providers (e.g., EXA_API_KEY in example)","Indirect/transport-specific authentication for MCP servers (not specified in README)"],"has_free_tier":false,"known_gotchas":["Tool execution and transport details are configuration-dependent; ensure MCP server contracts and transports are correct (stdio/sse/streamable-http/websockets).","Authentication/authorization for MCP servers is not described here; misconfiguration could expose sensitive tools.","In-memory message history suggests limited durability; long-running or crash-sensitive workflows may require external persistence.","No documented retry/idempotency semantics in the provided README; agent behavior may be non-idempotent for tool calls like filesystem writes."],"error_quality":0.0}