MCP gateways & tool hubs MCP servers

A server here bundles, proxies or manages many MCP servers, APIs or tools behind one connection.

Not here: a server with one clear purpose.

6,619servers
5,447 remote1,172 localTagged by Odel's AI, which can make mistakes

Best fit

2,082 made for this, ranked by starsRemoteLocal
  1. EasyBits @easybits/easybitsPersistent Linux microVMs for agents: root, internet, sub-second resume and a public URL.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7 GitHub stars.
  2. PipesHub @pipeshub-ai/mcpPermissioned search and cited answers over Slack, Drive, Gmail, Jira, and 50+ workplace sources.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  3. EnConvert @enconvert/mcpUnified web ingestion for AI agents: perceive, discover, search, extract, ingest, watch, convert.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  4. Affiliate Networks MCP @agenticaffiliate/affiliate-networks-mcpAffiliate network reporting in your AI client. Bring your own keys. Most adapters experimental.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7 GitHub stars.
  5. Bastion @gowthaman90/mcp-bastionReliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  6. Gaff Check @iarfhlaith/gaff-checkIrish property due diligence: planning, prices, flood, radon, zoning, BER and crime context.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  7. Stock Scanner @yyordanov-tradu/stock-scanner-mcpStock and crypto market data — 49 tools for quotes, technicals, options, SEC filings, and more.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  8. Jitapi @nk3750/jitapiTurn any OpenAPI spec into an executable agent interface using graphs and semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
  9. Plant Genomics @musharna/plant-genomics-mcpPlant genomics MCP — 56 tools across 23 backends with cross-source synthesis.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
  10. Agent Discover @keshrath/agent-discoverFind, install and enable MCP servers mid-session on any host, with consent and tool pinning6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  11. Kie @elibarnett/kie-mcpMCP for kie.ai: 45+ image, 70+ video, 20+ audio models with model intelligence6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  12. Observability @thotischner/observability-mcpUnified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  13. Pipeworx @pipeworx-io/pipeworx-catalogLive data gateway for AI — 3,300+ tools across 750+ sources, with citations7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.7 GitHub stars.
  14. NYC Property Intel @ccedacero/nyc-property-intelMCP server giving Claude AI access to 22+ NYC public-record databases for real estate due diligence7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.7 GitHub stars.
  15. Studiomcphub @codex-curator/studiomcphub32 creative AI tools (18 free) for agents: generate, upscale, mockup, print, watermark.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.7 GitHub stars.
  16. Windsor.ai MCP @windsor/windsor-mcpQuery and analyze marketing, sales, and business data from 325+ platforms via Windsor.ai.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.7 GitHub stars.
  17. Scanbim @scanbimlabs/scanbimUnified AEC tools: ACC, Revit, Navisworks, Twinmotion, and APS from one endpoint.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.6 GitHub stars.
  18. AkTools Pro MCP Server @tchivs/aktools-pro🚀 AkTools Pro: 增强型金融 MCP 服务器。内置策略回测、模拟盘管理及实时异动监控。7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
  19. Gateway @rupinder2/mcp-gatewayAggregates tools from multiple MCP servers with unified BM25/regex search and deferred loading.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
  20. APIMesh @mbeato/apimesh74 paid web-analysis APIs (SEO, security, TLS, DNS, email) as MCP tools. USDC via x402.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
  21. Dd @cz-agents/ddCzech & EU due diligence in one call — facts, insolvency, sanctions, VAT, risk score, UBO chain.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
  22. Munim @vishalsg42/munimOne MCP server holding a live session with every client's account at once.78% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
  23. Squiggles @carldaws/squigglesLet your coding agent see the squiggles — LSP diagnostics, navigation, refactoring, and extras3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
  24. Ennodia @cherninlab/ennodiaConnects the AI agents you use: your agent hands a task to another and gets the answer back6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.