{"id":"egoist-fetch-mcp","name":"fetch-mcp","homepage":null,"repo_url":"https://github.com/egoist/fetch-mcp","category":"api-gateway","subcategories":[],"tags":["mcp","fetch","web-scraping","youtube","transcripts","typescript","stdio","sse"],"what_it_does":"fetch-mcp is an MCP server that provides tools to fetch arbitrary URLs (returning HTML or Markdown) and to fetch YouTube video transcripts.","use_cases":["Augment an agent with web-page fetching and content extraction","Retrieve and summarize YouTube video transcripts","Convert fetched HTML into Markdown for downstream LLM processing","Provide MCP tool access to crawling/transcript retrieval inside agent workflows"],"not_for":["Authenticated/private content scraping where credentials are required","High-volume crawling without attention to rate limits or robots/terms","Use as a secure gateway for untrusted user-provided URLs without additional sandboxing"],"best_when":"You need lightweight MCP-accessible tools for fetching public web content and YouTube transcripts, integrated into an LLM agent.","avoid_when":"You need strong security controls for untrusted inputs, guaranteed compliance requirements, or industrial-grade uptime/reliability guarantees.","alternatives":["@modelcontextprotocol/sdk-based custom MCP servers you implement for your specific needs","Generic web fetching services/APIs (e.g., readability/document extraction APIs) plus a custom MCP wrapper","YouTube transcript libraries/APIs plus a custom MCP wrapper"],"af_score":49.2,"security_score":35.8,"reliability_score":33.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:40:51.815090+00:00","interface":{"has_rest_api":true,"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":[],"oauth":false,"scopes":false,"notes":"README does not mention authentication or API keys; likely operates without auth for local/agent-to-server use."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided (appears to be an open-source npm package intended to run self-hosted)."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":49.2,"security_score":35.8,"reliability_score":33.8,"mcp_server_quality":55.0,"documentation_accuracy":45.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":10.0,"tls_enforcement":50.0,"auth_strength":20.0,"scope_granularity":0.0,"dependency_hygiene":45.0,"secret_handling":70.0,"security_notes":"No auth mechanism is documented; running an HTTP/SSE server without authentication increases risk if exposed publicly. Fetching arbitrary URLs implies potential SSRF-like risks and data exfiltration risks unless agents strictly validate inputs and the server is sandboxed/network-restricted. TLS usage is not documented; assume transport depends on how the server is deployed.","uptime_documented":0.0,"version_stability":55.0,"breaking_changes_history":50.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":"Fetching URLs/transcripts is naturally repeatable, but no explicit idempotency semantics are documented for MCP tool calls.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Untrusted URL inputs can trigger unexpected network access behaviors; agents should validate/allowlist domains.","YouTube transcript availability varies by video/region; tool may fail or return empty transcripts.","If running as an HTTP/SSE server, ensure network exposure is controlled (bind address/firewall) since no auth is documented."]}}