Overview
What is Google Custom Search MCP?
Google Custom Search MCP is an async Python MCP (Model Context Protocol) server that provides access to Google Custom Search API using service account authentication. It is designed for developers and AI assistants that need to perform Google Custom Search queries programmatically through the MCP protocol.
How to use Google Custom Search MCP?
Clone the repository, configure a Google Service Account and Custom Search Engine, then run uv run google-custom-search-mcp with the required environment variables GOOGLE_SERVICE_ACCOUNT_FILE or GOOGLE_SERVICE_ACCOUNT_BASE64 and GOOGLE_SEARCH_ENGINE_ID. The server supports STDIO mode (default) and HTTP mode (via --transport http). Docker and Helm deployments are available.
Key features of Google Custom Search MCP
- Perform Google Custom Search queries with configurable result count
- Service Account authentication (file path or base64)
- Live integration tests against actual Google API
- FastMCP Python SDK integration
- Docker support with Alpine Linux image
- UV compatibility for modern Python packaging
Use cases of Google Custom Search MCP
- Building AI assistants that need real-time web search results
- Enabling MCP clients to query Google Custom Search inside workflows
- Integrating custom search into CI/CD pipelines with base64 auth
- Deploying a custom search microservice on Kubernetes
FAQ from Google Custom Search MCP
What is required to use Google Custom Search MCP?
You need a Google Cloud project with the Custom Search API enabled, a service account with a JSON key, and a Custom Search Engine ID. Environment variables authenticate the service account.
How does authentication work?
Authentication uses a Google Service Account, either via a file path (local development) or a base64-encoded JSON string (CI/CD). API keys are deprecated.
What are the API limits?
The Google Custom Search API provides 100 free search queries per day. Additional queries require billing setup. Service accounts have the
