MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
—
Apache-2.0 -
vertex-ai-mcp-servergithub.com/shariqriazz/vertex-ai-mcp-serverupdated this year
MCP server for Vertex AI and Gemini tools, including grounded answers, documentation research, and filesystem workflows.
npm MIT ★ 88 -
MCP server for Google Vertex AI — 181 tools covering all v1 REST API endpoints
npm ★ 1 -
A lightweight Model Context Protocol (MCP) server that exposes Google Cloud's Vertex AI Search for Commerce as a tool for AI agents. This allows agents to easily search a product catalog using natural language queries. Built with Python and FastMCP.
-
End-to-End-MCP-Tooling-System-with-Vertex-AI-Geminigithub.com/AvinashBolleddula/End-to-End-MCP-Tooling-System-with-Vertex-AI-Geminiupdated this year
End-to-end MCP tooling system implementing a FastMCP server and STDIO-based client with JSON-RPC, multi-step tool chaining, and Vertex AI Gemini–powered orchestration.
-
openreflect-gcp-vertex-memorycoregithub.com/openreflect/openreflect-gcp-vertex-memorycoreupdated this year
Prototype MCP server for Google Cloud Vertex AI memory infrastructure
-
Go-based MCP server exposing Google Cloud Vertex AI Gemini models to AI assistants
★ 1 -
mcp-google-vertexgithub.com/ragna-ai/mcp-google-vertexupdated this year
A Model Context Protocol (MCP) server that provides AI-powered image and video generation capabilities using Google Vertex AI's Imagen and Veo models.
MIT ★ 1 -
A lightweight MCP server that integrates with Vertex AI Search to retrieve configurable snippets and extractive segments for document discovery.
go MIT -
mcp-google-agent-platform-docsgithub.com/OpenGerwin/mcp-google-agent-platform-docsupdated this year
MCP server for Google Agent platform docs — Google AI + Vertex AI. 3400+ pages searchable by AI agents.
pypi MIT ★ 1 -
gemini-cloud-mcpstale
MCP server for semantic code search via Vertex AI and Firestore
npm MIT -
@mcn1ne/gemini-mcp-nodeupdated this year
Gemini debate MCP server (stdio) for Claude Code. Vertex AI 기반.
npm MIT -
banking_datagithub.com/kirantraj/banking_dataupdated this year
Multi-agent AI system that translates natural language into BigQuery queries. Built with MCP, Vertex AI Gemini, and Python.
-
ai-vision-mcpgithub.com/tan-yong-sheng/ai-vision-mcpupdated this year
Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI
npm MIT -
Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI
npm MIT -
Secure student planner with encrypted offline clients and a Firebase and Cloud Run RAG copilot using Vertex AI, Gemini, and MCP.
-
@twick/mcp-agentupdated this year
MCP server for Claude Desktop that generates video captions using Google Vertex AI and integrates with Twick Studio
npm https://github.com/ncounterspecialist/twick/blob/main/LICENSE.md -
@kybrcore/gemini-search-mcpgithub.com/kybrcore/gemini-search-mcpupdated this year
MCP server for real-time Google Search via Gemini API with search grounding (AI Studio, Vertex AI Express Mode, ADC, Service Account)
npm MIT -
Compare text LLMs across OpenRouter, Amazon Bedrock, Google Vertex AI and Microsoft Foundry — bring your own credentials. Automated grading, reports, and an MCP server.
pypi MIT -
Estudio privado de producción con IA sobre Google Vertex AI: Nano Banana, Veo 3.1, Gemini Omni, Lyria 3, motion graphics por código y un director autónomo con MCP.
MIT -
markdown-fastrag-mcpgithub.com/lidge-jun/markdown-fastrag-mcpupdated this year
Fast markdown RAG with multi-provider embeddings (Vertex AI, Gemini, OpenAI, Voyage), incremental indexing with mtime/size fast-path, stale vector pruning, Milvus vector store.
Apache-2.0 ★ 5 -
@ajmalaksar/multimodal-mcpgithub.com/ajmalaksar25/multimodal-mcpupdated this year
MCP server and CLI exposing Google's multimodal models (Gemini AI Studio and Vertex AI) for image, video, and audio analysis plus image generation — for Claude Code and other agents.
npm MIT -
@dondonudonjp/vertexai-imagen-mcp-servergithub.com/ex-takashima/vertexai-imagen-mcp-serverupdated this year
[DEPRECATED] MCP Server for Vertex AI Imagen image generation. Imagen endpoints shut down 2026-06-30; migrate to the nanoBanana MCP Server (Gemini image models).
npm MIT -
multi-agent-it-ops-deskgithub.com/Rudra7777/multi-agent-it-ops-deskupdated this year
Governed multi-agent IT operations desk — LangGraph orchestration + 3 MCP servers (custom Directory & Access, Zapier, vectorless Policy KB RAG) with human-in-the-loop approval gates, on Gemini/Vertex AI
-
Gemini's eyes, ears and long context inside Claude Desktop — an MCP server for document/audio/video digest, Vertex AI Search, and image & video generation. Reports what each call keeps out of Claude's context.
MIT ★ 3 -
MCP server for Gemini image generation ("Nano Banana" / "Nano Banana Pro"). Supports a Gemini API key from AI Studio, a Vertex AI / Gemini Enterprise Agent Platform API key (Express Mode), and Application Default Credentials (ADC).
npm MIT -
PocketRAGgithub.com/mbettan/PocketRAGupdated this year
PocketRAG is a zero-infrastructure, portable agent plugin (Skill + FastMCP Server) that turns NotebookLM Enterprise (via Vertex AI Discovery Engine) into an instant, managed RAG backend for any LLM client (Claude Desktop, Cursor, Gemini, Cline). Bring your own documents to your AI assistant in under 60 seconds.
Apache-2.0 -
A MCP server for Vertex AI Search
Apache-2.0 ★ 38 -
An MCP server to use Gemini via Vertex AI API.
-
organon-create-imagegithub.com/aurynsinclair/organon-create-imageupdated this year
MCP server for image generation using Gemini on Vertex AI
-
claude-gemini-bridgegithub.com/archolet/claude-gemini-bridgeupdated this year
Claude Code icin Vertex AI uzerinden Gemini 3 modellerine erisim saglayan MCP sunucusu
MIT -
Unified Go MCP server for AI media generation via Google Gemini API and Vertex AI
oci Apache-2.0 ★ 14 -
Xiaozhi MCP Remix - Enhanced Model Context Protocol server with Vertex AI and Gemini API support
MIT -
imagen-tools-mcpgithub.com/hwalde/imagen-tools-mcpupdated this year
MCP-Server für Bildgenerierung und -bearbeitung mit Google Gemini (Vertex AI oder AI Studio) — Provider- und Modellwechsel zur Laufzeit
MIT -
✈️ QA Autopilot: Un MCP en Python que conecta Jira con Google Gemini (Vertex AI) para generar Casos de Prueba (TCs) automáticamente.
★ 4 -
gosce-llm-orchestration-agent-mcpupdated this year
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
pypi MIT -
gosce-llm-orchestration-mcp-agentupdated this year
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
pypi MIT -
gosce-traced-llm-mcp-proxyupdated this year
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.
pypi MIT -
gosce-mcp-native-llm-orchestration-agentupdated this year
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
pypi MIT -
gosce-authenticated-llm-mcp-agentupdated this year
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
pypi MIT -
gosce-structured-output-mcp-traced-agentupdated this year
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).
pypi MIT -
mcpstore-gemini-designgithub.com/tanguyors/mcp-storeupdated this year
Gemini Design MCP (patched fork accepting new Google AQ. API key format AND supporting Vertex AI mode to bill against Google Cloud credits)
npm MIT -
MCP server providing web search and Gemini Deep Research, for Claude Code on Vertex AI where native WebSearch is blocked by org policy
npm MIT -
gemini-omni-mcpgithub.com/tamiratias93-gif/gemini-omni-mcpupdated this year
Control Google Gemini Omni (AI video generation) from any MCP client — Claude, Cursor, agents. A browser bridge until the official Vertex AI Omni API ships.
-
@infopercept/invinsense-rag-mcphttps://gitlab-ssh.invinsense.dev/infopercept/docs/pg-rag.gitupdated this year
MCP (Model Context Protocol) server that provides Claude and other AI assistants with semantic search access to InvinSense documentation using Vertex AI RAG Engine. Enables AI-powered documentation queries with grounded, citation-backed responses.
npm MIT -
Finds OpenAI, Anthropic, Google, Mistral, xAI, Cohere, DeepSeek, Groq, Bedrock, Vertex AI and Azure model IDs in your code and warns before they are retired. CLI, GitHub Action and MCP server.
npm Elastic-2.0 -
Multi-agent coding assistant using LangGraph, Vertex AI Gemini, embedding-based RAG, and MCP client/server tooling to generate implementation code, tests, and code reviews from software requirements.
MIT -
Multi-agent demo with Google ADK on Vertex AI Agent Engine — every LLM, A2A, and MCP call routed through Apigee X for API-key auth, per-user quotas, and token analytics.
Apache-2.0 ★ 12 -
easy-memorygithub.com/flippysun/easy-memoryupdated this year
MCP persistent memory service — let AI assistants remember across sessions. Powered by Qdrant vector search + official embeddings (via OpenAI-compatible relay or Gemini Vertex AI) with Ollama fallback and hybrid retrieval (vector + BM25).
npm MIT -
SQLGenius is an AI-powered SQL assistant that converts natural language to SQL queries using Vertex AI's Gemini Pro. Built with MCP and Streamlit, it provides an intuitive interface for BigQuery data exploration with real-time visualization and schema management.
★ 13 -
MCP server + agent that answers infra/ops questions only from official upstream docs, with exact source citations. Built on Gemini and Vertex AI Search.
Apache-2.0 -
MCP server that generates music from text prompts using several different song tools - Lyria (Vertex AI), ACE-Step 1.5, Stable Audio 3 and Studio SG2 - first available wins. Webapp + MCP tools, local-first.
MIT ★ 4 -
Evidence-first Medicare Stars agent on GCP, Vertex AI, ADK, MCP, and BigQuery, privately deployed to Cloud Run with fail-closed guardrails, CVE-gated OCI CI/CD, evaluations, and per-request cost telemetry.
NOASSERTION -
MCP-native agent graphs with a real UI. Local-first / BYOK — TypeScript monorepo (Next.js + Electron + MCP server + LangGraph). Powered by Google Gemini + Vertex AI on Cloud Run. Submitted to the Google for Startups AI Agents Challenge.
MIT -
AI agents write tested code for your project, test-first; you approve the key steps. Dashboard, terminal app, Android app, MCP server, code review and a supervisor. Claude, Codex, Copilot, Vertex AI or local models (Ollama). One Docker image.
MIT ★ 13 -
Even your AI needs a second opinion. A self-hosted MCP server on Google Cloud Run that lets Claude, ChatGPT, Cursor, and Gemini CLI peer-review their work with a different frontier model — Claude Opus 5.5 or Gemini 3.8 Flash on Vertex AI — with PII scrubbed before anything leaves your server.
Apache-2.0 -
workspace-agentgithub.com/rashidalmarri-dev/workspace-agentupdated this year
Enterprise Google Chat assistant that reads Workspace context (Gmail, Drive, Docs) and writes deliverables to a Shared Drive, split across two MCP servers so read-only personal data and read/write actions never share credentials. Built on Google ADK + Vertex AI Gemini with slash-command workflows and runtime access control.
MIT -
vertex-mcp-geminigithub.com/michaelandrewgamble/vertex-mcp-geminiupdated this year
Minimal MCP gateway connecting Claude Desktop to enterprise AI providers using ADC authentication, with reproducible call recording and replay.
MIT -
AI-assisted video production workflow with teleprompter, recording progress, Gemini, ClickHouse, and MCP.
AGPL-3.0 -
team-synapsegithub.com/ajaysingh-codes/team-synapseupdated this year
Hackathon project for Huggingface's MCP 1-year Anniversary 2025 – Team Synapse