GCP MCP Host on Cloud Run
Provides tools for managing Google Cloud Platform resources, including projects, services, and IAM permissions.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@GCP MCP Host on Cloud Runlist all my Compute Engine instances"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
GCP Stateless MCP Server
Tilaton Model Context Protocol (MCP) -palvelin Google Cloud Run -alustalle. Toimii dynaamisena välityspalvelimena GCP:n kaikkiin REST API -rajapintoihin Discovery Servicen kautta.
Arkkitehtuuri
Palvelin käyttää tilatonta Streamable HTTP -transporttia (StreamableHTTPServerTransport). Tilattomuus tarkoittaa, ettei pyyntöjen välillä säily tilaa — jokainen HTTP-pyyntö on itsenäinen. Tämä mahdollistaa Cloud Runin scale-to-zero -käytön ilman session affinity -vaatimusta.
JSON-RPC-viestit reititetään manuaalisesti ilman SDK:n McpServer-luokkaa, mikä antaa täyden kontrollin protokollan käsittelystä.
Related MCP server: gcloud MCP Cloud Run
Tarjotut työkalut
Työkalu | Kuvaus |
| Listaa saatavilla olevat GCP REST API:t Discovery Serviceltä. Tukee valinnaista filtteröintiä. |
| Palauttaa yksittäisen API-version kaikki metodit polkutemplaatteineen ja parametreineen. |
| Suorittaa minkä tahansa GCP REST -metodin dynaamisesti palvelun service accountin oikeuksilla. |
Tyypillinen käyttöketju
1. list_gcp_apis { filter: "run" }
→ [{ name: "run", version: "v2", ... }]
2. describe_gcp_api { api: "run", version: "v2" }
→ [{ id: "projects.locations.services.list", httpMethod: "GET", ... }]
3. call_gcp_api {
api: "run", version: "v2",
method_id: "projects.locations.services.list",
path_params: { projectsId: "my-project", locationsId: "europe-north1" }
}
→ { services: [...] }Tiedostorakenne
gcp-stateless-mcp/
├── mcp-gcp-server.ts — palvelimen pääkoodi (TypeScript)
├── Dockerfile — monivaiheinen konttikuva
├── service.yaml — Cloud Run -palvelun Knative-määritys
├── deploy-mcp.sh — automaattinen deploy-skripti
├── package.json — riippuvuudet
├── tsconfig.json — TypeScript-konfiguraatio
├── README.md — tämä tiedosto
└── INTEGRATION.md — asiakasintegraation ohjeetKäyttöönotto
Aja deploy suorittamalla:
./deploy-mcp.shSkripti suorittaa seuraavat vaiheet:
Varmistaa pääsyn GCP-projektiin
uutisseuranta-activitystreams.Kääntää TypeScript-lähdekoodin ja rakentaa Docker-konttikuvan.
Lataa konttikuvan Artifact Registryn
mcp-servers-repositorioon.Päivittää Cloud Run -palvelun
service.yaml-määrityksen mukaisesti.
IAM-oikeudet
Palvelu on yksityinen (--no-allow-unauthenticated). Kutsujilla täytyy olla roles/run.invoker -rooli.
Oikeuden lisääminen kehittäjälle:
gcloud run services add-iam-policy-binding mcp-gcp-server \
--region europe-north1 \
--member="user:jaakko.korhonen@gmail.com" \
--role="roles/run.invoker" \
--project=uutisseuranta-activitystreamsPalvelun service accountille tarvitaan oikeudet niihin GCP-resursseihin joita call_gcp_api kutsuu. Esimerkiksi Cloud Run -palveluiden listaukseen:
gcloud projects add-iam-policy-binding uutisseuranta-activitystreams \
--member="serviceAccount:<SERVICE_ACCOUNT_EMAIL>" \
--role="roles/run.viewer"Lokaalikehitys ja testaus
Ks. INTEGRATION.md asiakasintegraation ohjeista ja lokaalitestauksesta.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to interact with and manage Google Cloud Platform resources including Compute Engine, Cloud Run, Storage, BigQuery, and other GCP services through a standardized MCP interface.16MIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Google Cloud Platform services through gcloud CLI commands via a Cloud Run deployed MCP server. Supports executing gcloud commands and managing GCP resources through natural language.MIT
- AlicenseBqualityNot gradedmaintenanceEnables AI assistants to interact with and manage Google Cloud Platform resources including Artifact Registry, BigQuery, Cloud Build, Compute Engine, Cloud Run, Cloud Storage, and monitoring services through a standardized MCP interface.1-
- AlicenseNot gradedqualityDmaintenanceAn MCP server deployed on Cloud Run that enables reading Cloud Storage and leveraging Vertex AI models via natural language.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jaakkokorhonen/gcp-stateless-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server