# google/mcp

Google 💚 MCP

Repository: https://github.com/google/mcp
Canonical: https://ross.abutalabs.com/products/google-mcp
License: Apache-2.0
License Family: permissive
Last push: 2026-08-17T19:46:40+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 19
- inputs: {"age_days": 271, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4538, forks 529 (observed 2026-08-28T04:08:53.075791+00:00)

## What it is
A curated catalog of Google's official Model Context Protocol (MCP) servers, including remote managed endpoints on Google Cloud and open-source servers that can be run locally. It also provides deployment guidance for hosting MCP servers on Google Cloud and examples to get started.

## Use cases
- find official Google MCP servers for BigQuery or Cloud SQL
- connect AI agents to Google Workspace like Gmail and Calendar
- deploy an MCP server to Google Cloud Run
- give Gemini CLI access to Firebase and Google Analytics
- expose Google Cloud Storage to an LLM via MCP
- learn how to get started with MCP on Google Cloud

## When to choose
- you want Google-maintained MCP integrations for GCP products
- you need a starting point to connect AI agents to Google services
- you want guidance on deploying MCP servers to Google Cloud

## When to avoid
- you need MCP servers for non-Google services
- you want a single installable MCP client rather than a catalog
- you need third-party community MCP tooling

## Facets
- artifact type: learning-resource
- maturity: active
- function: mcp, developer-tools, documentation
- domain: developer-tools, artificial-intelligence, cloud-computing, apis
- platform: cloud, self-hosted, python, go
- tags: model-context-protocol, google-cloud, mcp-servers, gemini-cli, awesome-list, ai-agents, docker, nodejs

## Member repositories
- google/mcp (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.075791+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:10.375552+00:00, confidence not recorded.
  - readme: https://github.com/google/mcp (fetched 2026-08-28T04:08:53.075791+00:00, sha 2621f42229d0)
- Data as of 2026-08-30T08:39:29.467469+00:00.