{"id":"ragflow-retrieval-mcp-server","name":"ragflow-retrieval-mcp-server","af_score":37.5,"security_score":35.5,"reliability_score":27.5,"what_it_does":"ragflow-retrieval-mcp-server is an MCP (Model Context Protocol) server intended to provide retrieval capabilities (e.g., querying a RAG/knowledge base) to AI agents via MCP tools.","best_when":"You have (or can access) a RAG/knowledge retrieval backend and want agents to call retrieval via MCP tool calls with minimal integration friction.","avoid_when":"You need a fully documented REST/SDK interface, strict multi-tenant authorization controls, or clearly specified rate limiting/error/retry semantics that are not visible from the provided materials.","last_evaluated":"2026-04-04T21:46:23.665386+00:00","has_mcp":true,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["Tool contracts (inputs/outputs) may be underspecified—agents can mis-handle required parameters.","Retrieval endpoints may not be idempotent if tool calls trigger side effects (e.g., logging/query history); verify behavior.","Pagination/limit semantics for retrieved documents may require explicit agent-side handling."],"error_quality":0.0}