google/mcp

This repository contains a list of Google's official Model Context Protocol (MCP) servers, guidance on how to deploy MCP servers to Google Cloud, and examples to get started.

⚡ Google MCP Servers

Remote MCP servers

These remote MCP servers are managed by Google, and are available via endpoint. Below are a few key remote servrs. For a comprehensive list of all remote MCP servers managed by Google in General Availability (GA) and public preview vist the supported products pager

• AlloyDB for PostgreSQL
• BigQuery
• Bigtable
• Cloud Resource Manager
• Cloud SQL for MySQL
• Cloud SQL for PostgreSQL
• Cloud SQL for SQL Server
• Compute Engine (GCE)
• Developer Knowledge API (Google Developer Documentation)
• Firestore
• Google Maps (Grounding Lite)
• Google Security Operations (Chronicle)
• Kubernetes Engine (GKE)
• Spanner
• Cloud Run (GA)
• Cloud Storage

Open-source MCP servers

You can run these open-source MCP servers locally, or deploy them to Google Cloud (see below).

• Google Workspace, including Google Docs, Sheets, Slides, Calendar, and Gmail. (Gemini CLI extension)
• Firebase (Gemini CLI extension)
• Cloud Run (Gemini CLI Extension)
• Go
• Google Analytics
• MCP Toolbox for Databases, including BigQuery, Cloud SQL, AlloyDB, Spanner, Firestore, and more.
• Google Cloud Storage
• Genmedia, including Imagen and Veo models.
• Kubernetes Engine (GKE)
• Google Cloud Security, including Security Command Center, Chronicle, and more.
• gcloud CLI
• Google Cloud Observability
• Flutter/Dart
• Angular
• Google Maps Platform Code Assist toolkit
• Chrome DevTools

💻 Examples

• Launch My Bakery (/examples/launchmybakery): A sample agent built with Agent Development Kit (ADK) that uses remote MCP servers for Google Maps and BigQuery.
• Allstrides (/examples/allstrides): A sample app migrated from local to Cloud using remote MCP servers for Developer Knowledge, Cloud SQL and Cloud Run

📙 Resources

Run an MCP server in Google Cloud

• Documentation - Host MCP Servers on Cloud Run
• Blog Post - Build and Deploy a Remote MCP Server to Google Cloud Run in Under 10 Minutes
• MCP Toolbox for Databases - Deploy to Cloud Run, Deploy to Google Kubernetes Engine (GKE)
• Blog post - Announcing MCP support for Apigee (Turnkey MCP hosting for Apigee-hosted APIs)
• “Tools Make an Agent” - Blog and Codelab
• Codelab - How to deploy a secure MCP server on Cloud Run
• Codelab - "Agent Verse" - Architecting Multi-agent Systems

🤝 Contributing

We welcome contributions to this repository, including bug reports, feature requests, documentation improvements, and code contributions. Please see our Contributing Guidelines to get started.

📃 License

This project is licensed under the Apache 2.0 License - see the LICENSE file for details.

Disclaimers

This is not an officially supported Google product. This project is intended for demonstration purposes only.

This project is not eligible for the Google Open Source Software Vulnerability Rewards Program.

EHEPS Google MCP Integration

Overview

automatic-journey provides an EHEPS integration layer for Google's Model Context Protocol (MCP) ecosystem.

This file documents the Google MCP resources that may be used by the project, including remote MCP services, open-source MCP servers, deployment options, Gemini integration, and security requirements.

Disclaimer: automatic-journey is an independent EHEPS project. It is not an official Google, Google Cloud, Gemini, or Google MCP product and does not imply endorsement by Google.

---

EHEPS Project

Setting	Value
Organization	EHEPS International Organization
Project	automatic-journey
Google Cloud Project ID	ehepso-nonprofit-eb1db
Google Cloud Project Number	286452521627
Region	us-central1
Website	https://eheps.com
Organization	https://eheps.org

---

Google MCP

Google provides MCP integrations that allow compatible AI agents and clients to interact with supported Google services through standardized tools and interfaces.

Official MCP overview:

https://docs.cloud.google.com/mcp/overview

Supported products:

https://docs.cloud.google.com/mcp/supported-products

Enable or disable MCP servers:

https://docs.cloud.google.com/mcp/enable-disable-mcp-servers

---

Remote Google MCP Servers

The following are examples of Google-managed MCP services.

Service	Documentation
AlloyDB	https://docs.cloud.google.com/alloydb/docs/ai/use-alloydb-mcp
BigQuery	https://docs.cloud.google.com/bigquery/docs/use-bigquery-mcp
Bigtable	https://docs.cloud.google.com/bigtable/docs/use-bigtable-mcp
Cloud Resource Manager	https://docs.cloud.google.com/resource-manager/reference/mcp
Cloud SQL MySQL	https://docs.cloud.google.com/sql/docs/mysql/use-cloudsql-mcp
Cloud SQL PostgreSQL	https://docs.cloud.google.com/sql/docs/postgres/use-cloudsql-mcp
Cloud SQL SQL Server	https://docs.cloud.google.com/sql/docs/sqlserver/use-cloudsql-mcp
Compute Engine	https://docs.cloud.google.com/compute/docs/reference/mcp
Developer Knowledge	https://developers.google.com/knowledge/mcp
Firestore	https://docs.cloud.google.com/firestore/native/docs/use-firestore-mcp
Google Maps	https://developers.google.com/maps/ai/grounding-lite
Google Security Operations	https://docs.cloud.google.com/chronicle/docs/reference/mcp
Google Kubernetes Engine	https://docs.cloud.google.com/kubernetes-engine/docs/reference/mcp
Spanner	https://docs.cloud.google.com/spanner/docs/use-spanner-mcp
Cloud Run	https://docs.cloud.google.com/run/docs/reference/mcp
Cloud Storage	https://docs.cloud.google.com/storage/docs/reference/mcp

The supported-products page should be treated as the authoritative list because Google may add, remove, or change MCP availability.

---

Open-Source MCP Servers

Google and related Google organizations also publish open-source MCP servers and extensions.

Examples include:

MCP project	Repository / Documentation
Google Workspace	https://github.com/gemini-cli-extensions/workspace
Firebase	https://github.com/gemini-cli-extensions/firebase
Cloud Run	https://github.com/GoogleCloudPlatform/cloud-run-mcp
Google Analytics	https://github.com/googleanalytics/google-analytics-mcp
MCP Toolbox	https://github.com/googleapis/genai-toolbox
Google Cloud Storage	https://github.com/googleapis/gcloud-mcp/tree/main/packages/storage-mcp
Genmedia	https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/tree/main/experiments/mcp-genmedia
GKE	https://github.com/GoogleCloudPlatform/gke-mcp
Google Cloud Security	https://github.com/google/mcp-security
gcloud MCP	https://github.com/googleapis/gcloud-mcp/tree/main/packages/gcloud-mcp
Cloud Observability	https://github.com/googleapis/gcloud-mcp/tree/main/packages/observability-mcp
Flutter/Dart	https://github.com/dart-lang/ai/tree/main/pkgs/dart_mcp_server
Angular	https://github.com/angular/angular-cli/tree/main/packages/angular/cli/src/commands/mcp
Chrome DevTools	https://github.com/ChromeDevTools/chrome-devtools-mcp

Before using any external MCP server, review its current documentation, permissions, source code, dependencies, and security model.

---

EHEPS MCP Architecture

                         EHEPS
                           |
             +-------------+-------------+
             |                           |
        eheps.com                    eheps.org
             |                           |
             +-------------+-------------+
                           |
                    automatic-journey
                           |
                    Python Application
                           |
                    Gemini / AI Agent
                           |
                       MCP Layer
                           |
       +-------------------+-------------------+
       |                   |                   |
    BigQuery           Cloud Run         Cloud Storage
       |                   |                   |
    Cloud SQL              GKE             Firestore
       |                   |                   |
       +-------------------+-------------------+