MCP Server (artifact)

Google publishes an official (labelled "Experimental") MCP server for Google Analytics. It is a LOCAL stdio server: you install it with pipx/uv and an MCP client launches it as a subprocess. There is no hosted endpoint an agent can POST to. It wraps the Google Analytics Admin API and Google Analytics Data API (GA4) and authenticates with Application Default Credentials, so the human running it must already hold Google Analytics access.

View descriptor → Google Analytics provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

⚠ Proposed MCP surface. No official hosted MCP server was found for Google Analytics. The tools below are a candidate set derived from this provider's API, and the link points at the source descriptor rather than a live server. If Google Analytics publishes an official server, this page will update to it on the next build.

Provider: Google Analytics Type: Candidate descriptor Transport: Host: raw.githubusercontent.com

Descriptor

https://raw.githubusercontent.com/api-evangelist/google-analytics/refs/heads/main/mcp/google-analytics-mcp.yml

Candidate descriptor · transport

Tools

get_account_summaries — Retrieves information about the user's Google Analytics accounts and properties.
get_property_details — Returns details about a property.
list_google_ads_links — Returns a list of links to Google Ads accounts for a property.
list_property_annotations — Returns reporting data annotations for a property — notes left on GA4 for specific dates or periods.
run_report — Runs a Google Analytics report using the Data API.
run_realtime_report — Runs a Google Analytics realtime report using the Data API.
run_funnel_report — Runs a Google Analytics funnel report using the Data API.
run_conversions_report — Runs a conversion-performance report using the Data API v1alpha conversion reporting surface (Advertising > Conversion performance).
get_custom_dimensions_and_metrics — Retrieves the custom dimensions and metrics for a specific property.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.