{"id":"sharan-kumar-r-custom-mcp-server","name":"Custom-MCP-Server","af_score":42.8,"security_score":49.2,"reliability_score":22.5,"what_it_does":"Provides a Python-based Model Context Protocol (MCP) server exposing tools to scrape social media profile data (LinkedIn, Facebook, Instagram) and perform Google search via Serper/Google search. It is intended to be run locally (e.g., with Claude Desktop) and uses external APIs (RapidAPI and Serper) authenticated via environment variables.","best_when":"You need an MCP tool interface to quickly connect an agent to third-party scraping/search APIs for occasional, user-driven URL lookups and you can manage API keys securely.","avoid_when":"You require strong guarantees around compliance, provenance, or stability of scraped fields; or you need a well-defined public API contract (OpenAPI/SDK) with predictable schemas beyond the described example.","last_evaluated":"2026-03-30T13:52:04.980258+00:00","has_mcp":true,"has_api":false,"auth_methods":["Environment variable API keys for RapidAPI (RAPIDAPI_KEY) and Serper (SERPER_API_KEY)"],"has_free_tier":false,"known_gotchas":["Tool output schema is only exemplified; exact fields and error formats are not documented in the README.","Scraping/search depends on third-party APIs (RapidAPI/Serper), which may rate limit or fail intermittently; agent retry/backoff guidance is not provided.","Requires environment variables (.env) to be set; without them tools likely fail at runtime.","LinkedIn/Facebook/Instagram scraping may have access and policy constraints—results may vary or fail depending on the upstream provider and URL type."],"error_quality":0.0}