{"id":"shareai-lab-share-best-mcp","name":"share-best-mcp","homepage":"https://sharemcp.cn","repo_url":"https://github.com/shareAI-lab/share-best-mcp","category":"devtools","subcategories":[],"tags":["mcp","registry","discovery","crawling","curation","ai-tools","automation"],"what_it_does":"share-best-mcp appears to be an aggregator/curation repo (\"Share Best MCP Servers\") that crawls and analyzes MCP server repositories and publishes a categorized list (and points to a web search site). It does not, by itself, define a single MCP server interface for clients; instead, it provides scripts and content to discover other MCP servers and filter them by a score threshold (>= 85).","use_cases":["Discovering and selecting third-party MCP servers for use with an LLM/MCP client","Building an internal catalog of MCP tools by category","Automating periodic scanning/crawling of GitHub MCP server projects and filtering by quality score"],"not_for":["Providing a ready-to-run, single MCP server API/toolset","Production use as a trusted security gateway or authorization layer","Reliable execution of MCP tools (since it delegates to third-party MCP servers)"],"best_when":"You want to find high-signal MCP server options quickly and are comfortable reviewing/hosting third-party MCP servers independently.","avoid_when":"You need a stable, documented MCP server contract from this repo itself or you require vetted security posture guarantees for the MCP tools it lists.","alternatives":["Any MCP marketplace/catalog site (if available)","Direct discovery by GitHub search and manual vetting","Using a maintained MCP registry (if your org already has one)"],"af_score":29.2,"security_score":12.0,"reliability_score":20.0,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:45:36.791706+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":false,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No authentication described for this aggregator/repo."},"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; content suggests self-hosted/local crawling scripts and an external website for searching."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":29.2,"security_score":12.0,"reliability_score":20.0,"mcp_server_quality":0.0,"documentation_accuracy":25.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":100.0,"rate_limit_clarity":10.0,"tls_enforcement":0.0,"auth_strength":0.0,"scope_granularity":0.0,"dependency_hygiene":40.0,"secret_handling":30.0,"security_notes":"Security posture cannot be confirmed from the provided content: the README mainly describes crawling/analyzing other repositories and a website link. It provides no details about TLS, authentication/authorization, dependency pinning, sandboxing, or how it handles secrets while crawling. Because it curates third-party MCP servers, the consumer must independently vet and sandbox any listed MCP servers before granting them access to sensitive systems.","uptime_documented":0.0,"version_stability":30.0,"breaking_changes_history":30.0,"error_recovery":20.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["This repo is an MCP-server aggregator, not a single MCP server; an agent should not expect a consistent MCP tool surface from this package.","Listed MCP servers are third-party; any runtime behavior/security guarantees depend on the upstream server implementations.","Crawling scripts may be long-running (README notes manual stopping may be needed), so agents should expect operational/time constraints rather than a synchronous API."]}}