全部 MCP 服务器
40,062 个结果
- GenPark Vector Embedding Cache Deduplication SentinelalphaparkincHigh-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation
- genpark-financial-auditAlpha-ParkArithmetic consistency checks for supplied financial statement data.
- genpark-jitter-bufferAlpha-ParkPacket ordering simulation and inter-arrival jitter telemetry.
- genpark-voice-vadAlpha-ParkEnergy and transcript heuristics for voice turn endpoint detection.
- GinguguginguguLocal SQLite memory for coding assistants with typed memories, namespaces, a knowledge graph, hybrid search and a credential vault.
- Git Forensics MCPdavidorexInvestigates git repositories: branch overviews, time-period analysis, file changes and merge recommendations.
- Gitee MCP Servernormal-coder国内厂商Lets agents work with Gitee repositories, files, branches, issues and pull requests.
- GitHub PR Contextpaarths-collabAI-Powered Repository Memory
- Gmail Postmaster ToolsoptipubGmail Postmaster Tools (v2 API) as an MCP server — domains, traffic metrics & sender compliance in Claude, Cursor, and any MCP client. Bring your own Google OAuth. Zero dependencies.
- go-mcp-postgresguoling2008Go-based server for running CRUD queries against PostgreSQL over stdio or SSE, without needing Node.js or Python.
- Google AI Search MCPshariqriazzSearch, documentation retrieval, code analysis and architecture research using Vertex AI or the Gemini API.
- Google Play Console MCPAgiMaulanaGoogle Play release lifecycle: tracks, testers, rollout, and Android Vitals.
- Google Search Console MCPlionkiiiQueries Google Search Console: search analytics, URL inspection, sitemaps, keyword opportunities and SEO performance comparison.
- Google Webtools MCPstufentlyUnified MCP server for Google Analytics 4 + Google Search Console
- GroundLensgroundlens-devGuardrails for LLM answers. GroundLens checks an LLM answer against its sources without a model, decides PASS, REVIEW or FAIL under your policy, and keeps a signed record.
- Guru PK MCPchuenlye按问题动态生成专家角色，让三位专家围绕任意话题进行多轮辩论。
- gutKungieAnswers yes/no, pick-one and rating questions about text with small models such as TypeSafe's Jev, Ollama or a local NLI model, returning YES, NO or UNSURE.
- hardware-probeyamaru-euExpert hardware probe for AI, Gaming, and HPC. Analyzes GPU, VRAM, and Memory Bandwidth to optimize local LLM inference (Ollama) and provide actionable hardware upgrade recommendations.
- HasData DuckDuckGohasdataHosted DuckDuckGo MCP server from HasData. Ranked results, ads separated, 37 regions, structured JSON for Claude, Cursor and any MCP client.
- HasData ShopifyhasdataMCP server for Shopify storefronts: pull the public product catalogue and collections of any store by URL, with variants, SKUs and prices. No app, no merchant token. 1,000 free credits every month.
- HasData YouTube MCPHasDataHosted YouTube server from HasData for search, video and channel data and transcripts, without a Google Cloud project.
- HefestoAIartvepa80AI-powered code quality agent with ML semantic analysis. Prevents technical debt before production. Free tier: static analysis. Pro tier: ML duplicate detection, real-time metrics, CI/CD automation. Built for AI coding era. Open core model: Phase 0 free, Phase 1 paid.
- Helm Chart CLI MCPjeff-nasseriExposes the Helm CLI to agents so they can install charts, manage repositories and run other Helm commands for Kubernetes.
- Hermes Action BridgeTheBlueHouse75Lets external agents delegate actions such as research, browser workflows, messaging and scheduling to Hermes Agent, with approval for risky actions.