{"id":"outscraper-mcp-server","name":"outscraper-mcp-server","homepage":"https://pypi.org/project/outscraper-mcp-server/","repo_url":"https://github.com/outscraper/outscraper-mcp.git","category":"ai-ml","subcategories":[],"tags":["mcp","outscraper","web-scraping","ai-agents","data-extraction","reviews","geocoding","python"],"what_it_does":"Provides an MCP (Model Context Protocol) server that exposes Outscraper-based extraction tools (e.g., Google Maps/Google/Yelp/Trustpilot/Amazon reviews and business/contact data) to MCP clients (e.g., Claude Desktop, Cursor).","use_cases":["AI-assisted business research and lead enrichment from multiple public web sources","Aggregating reviews and ratings for competitors or specific locations","Extracting contact info (emails/phones) and validating deliverability","Geocoding and reverse geocoding workflows via an agent","Bulk review scraping workflows with pagination/time filtering"],"not_for":["Directly scraping sites where automated extraction is disallowed by the target service’s terms","User-specific or sensitive data processing without appropriate legal/compliance review","Use in a security-critical production environment without reviewing error handling, logging, and data retention"],"best_when":"You need a standardized MCP tool interface for multi-source web/data extraction and you already have an Outscraper API key.","avoid_when":"You require a documented, self-hostable REST/SDK interface with complete machine-readable specs or you need strong guarantees on idempotency/retry/error semantics at the MCP tool level.","alternatives":["Use Outscraper’s API directly (REST) if preferred over MCP orchestration","Build a custom MCP server wrapper around Outscraper endpoints","Use domain-specific scrapers or vendor SDKs where available instead of a generalized extraction service"],"af_score":59.0,"security_score":57.5,"reliability_score":23.8,"package_type":"mcp_server","discovery_source":["pypi"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:49:35.217183+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Outscraper API key via OUTSCRAPER_API_KEY environment variable"],"oauth":false,"scopes":false,"notes":"Authentication is described as an environment variable containing an Outscraper API key. No mention of OAuth or scoped tokens in the provided content."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Readme points to Outscraper pricing and notes request-based tracking; specific limits/costs are not provided in the package content."},"requirements":{"requires_signup":true,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":59.0,"security_score":57.5,"reliability_score":23.8,"mcp_server_quality":70.0,"documentation_accuracy":60.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":90.0,"rate_limit_clarity":40.0,"tls_enforcement":70.0,"auth_strength":65.0,"scope_granularity":20.0,"dependency_hygiene":55.0,"secret_handling":75.0,"security_notes":"Transport security (TLS) is not explicitly stated in the provided content; assume HTTPS by typical API practice but score conservatively. Authentication is via API key in environment variables (better than embedding in code/logs), but no scope granularity or security controls are described. License in metadata is MIT; dependency list is limited in the manifest, but no CVE/vulnerability status is provided.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":30.0,"error_recovery":25.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"skip/limit parameters supported (as described), likely for large result sets","retry_guidance_documented":false,"known_agent_gotchas":["LLM/agent callers may trigger high-volume extraction; pricing/rate limits are only broadly referenced, so agents should self-throttle/cap requests.","Because the MCP tool set is broad (25+ tools) but tool-level error/retry/idempotency semantics are not shown in the provided README, agents may need defensive handling for partial failures.","Ensure API key is correctly injected into the MCP server environment; misconfiguration will likely cause tool failures (exact error behavior not documented)."]}}