GCP MCP
by eniayomi
GCP MCP is a Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your Google Cloud Platform environment. It allows for natural language querying and management of your GCP resources during conversations.
Last updated: N/A
What is GCP MCP?
GCP MCP is a server that acts as a bridge between AI assistants (like Claude, Cursor, and Windsurf) and your Google Cloud Platform (GCP) environment. It allows you to use natural language to query and manage your GCP resources directly within your AI assistant's interface.
How to use GCP MCP?
First, install the GCP MCP server and configure it to work with your chosen AI assistant (Claude Desktop, Cursor, or Windsurf). This involves adding an MCP configuration to the assistant's settings, specifying the command to run the GCP MCP server. Ensure you have GCP credentials configured locally. Then, you can start interacting with your GCP resources by asking questions or giving commands in natural language within your AI assistant.
Key features of GCP MCP
Query and modify GCP resources using natural language
Support for multiple GCP projects
Multi-region support
Secure credential handling
Local execution with your GCP credentials
Automatic retries for improved reliability
Use cases of GCP MCP
Querying GCP resources (e.g., listing projects, instances, buckets)
Managing GCP resources (e.g., starting/stopping instances, creating buckets)
Monitoring GCP resources (e.g., checking billing status, viewing logs)
Automating GCP tasks through natural language commands
FAQ from GCP MCP
How do I set up GCP credentials?
How do I set up GCP credentials?
Use the command gcloud auth application-default login to set up application default credentials.
What if I get authentication errors?
What if I get authentication errors?
Ensure you have run gcloud auth application-default login and that your account has the necessary IAM roles.
What services are supported?
What services are supported?
Currently supports Google Compute Engine, Cloud Storage, Cloud Functions, Cloud Run, BigQuery, Cloud SQL, Google Kubernetes Engine (GKE), Cloud Logging, Cloud Billing, and Resource Manager. More services are coming soon.
How can I see the server logs?
How can I see the server logs?
Use the command tail -n 50 -f ~/Library/Logs/Claude/mcp-server-gcp.log to view the logs.
What do I do if I get permission errors?
What do I do if I get permission errors?
Check the IAM roles for your account to ensure you have the necessary permissions to access the GCP resources you are trying to query or modify.