{"id":"agoda-com-api-agent","name":"api-agent","af_score":59.5,"security_score":53.5,"reliability_score":26.2,"what_it_does":"Provides a universal MCP server that exposes GraphQL and REST APIs as MCP tools. It introspects a target GraphQL endpoint or OpenAPI/Swagger spec, answers questions in natural language, fetches data, stores results in DuckDB, and performs SQL post-processing. It also supports “recipe learning” to cache reusable query pipelines as additional dynamic MCP tools.","best_when":"You want an agent/MCP client to explore and analyze external GraphQL/REST APIs quickly using a consistent tool interface, and you accept that results may involve SQL post-processing over fetched data.","avoid_when":"You need deterministic, contract-first correctness (e.g., strict schema-to-query validation) or you must minimize data retention/storage, or you cannot safely supply auth headers to a server that will call third-party endpoints.","last_evaluated":"2026-03-30T13:35:00.943417+00:00","has_mcp":true,"has_api":false,"auth_methods":["Environment variable for LLM provider: OPENAI_API_KEY (and optional OPENAI_BASE_URL)","Target API auth via MCP client headers: X-Target-Headers (static JSON headers such as Authorization: Bearer …)"],"has_free_tier":false,"known_gotchas":["Rate limits and pagination behavior of the upstream API are not described in the provided content; agent may fetch partial data unless the upstream API/data volume is handled explicitly.","Auth is provided via static headers; if tokens expire, long-running agents may fail without a refresh mechanism.","Results are stored in DuckDB; large responses may increase memory/disk usage and affect reliability.","Recipes depend on schema hash; schema changes can invalidate cached tools."],"error_quality":0.0}