Skip to main content
Glama
Sign In

Google Analytics 4 MCP by InsightfulPipe

by com.insightfulpipe
OverviewDiscussionsAdmin

Server Details

Hosted Google Analytics 4 MCP server, with each action switched on or off per account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Insightful-Pipe/google-analytics-mcp-server
GitHub Stars
0
Server Listing
Google Analytics 4 MCP Server
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 4 tools

Disambiguation2/5

execute_action and query_data have virtually identical descriptions ('Execute Google Analytics actions (Step 3 FINAL)' vs 'Execute Google Analytics data queries (Step 3 FINAL)') and identical prerequisite/payload instructions, making it very hard for an agent to know which to call. query_contexts and prompts_menu are clearer, but the core execution pair has unclear boundaries.

Naming Consistency4/5

All four names use snake_case with a two-word verb/object pattern (execute_action, query_data, query_contexts, prompts_menu), which is predictable and readable. Minor inconsistency: 'prompts_menu' puts the noun first while the others lead with a verb.

Tool Count3/5

Four tools is thin for a GA4 server whose scope includes report execution, realtime data, metadata discovery, and a prompt catalog. The design collapses all data operations into one generic parameterized tool rather than scoping distinct capabilities.

Completeness3/5

The action-driven body parameter theoretically allows many report types, and query_contexts/prompts_menu cover discovery, so basic read workflows are reachable. However, there is no distinct handling for realtime vs standard reports, no admin/configuration operations, and no prompt creation despite browsing support.

Available Tools

4 tools
execute_actionGA4 Execute ActionA
Destructive
Inspect

Execute Google Analytics actions (Step 3 FINAL).

Prerequisites: Run query_contexts with request='accounts' (includes available_requests) + request='actions_details' to understand the required payload.

IMPORTANT: The 'body' parameter is a dictionary that must contain ALL fields including:

  • action: Table/action name (e.g. 'runReport', 'runRealtimeReport')

  • workspace_id: Integer workspace ID

  • brand_id: Integer brand ID

  • property_id: GA4 property identifier

  • Any other fields from the helper response (filters, date ranges, dimensions, metrics, etc.)

Do NOT pass these as separate parameters - they must ALL be inside the body dictionary.

Inputs: body (required). Returns: object

prompts_menuGA4 PromptsA
Read-only
Inspect

Browse the Google Analytics prompt catalog.

  1. request='menu' – List public/system prompts (optionally pass workspace_id + prompt_type).

  2. request='prompt_details' – Fetch prompt body by prompt_id. Set is_custom=True + workspace_id for workspace prompts.

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsGA4 Setup HelperA
Read-only
Inspect

Helper for planning InsightfulPipe Google Analytics data queries.

Step 1: request='accounts' – Retrieve workspace_id, brand_id, property_id, other source metadata, AND available_requests (all tables you can query).

Step 2: request='actions_details' with actions=['table_a', 'table_b'] – REQUIRED before querying. Returns the exact request body, required identifiers, fields, time ranges, and notes for each action.

Optional: request='available_actions' – Standalone call to list all available tables/actions (already included in accounts response).

Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.

Inputs: request (required), actions, brand_id, platform, +2 more. Returns: object

query_dataGA4 Data QueryA
Read-only
Inspect

Execute Google Analytics data queries (Step 3 FINAL).

Prerequisites: Run query_contexts with request='accounts' (includes available_requests) + request='actions_details' to understand the required payload.

IMPORTANT: The 'body' parameter is a dictionary that must contain ALL fields including:

  • action: Table/action name (e.g. 'runReport', 'runRealtimeReport')

  • workspace_id: Integer workspace ID

  • brand_id: Integer brand ID

  • property_id: GA4 property identifier

  • Any other fields from the helper response (filters, date ranges, dimensions, metrics, etc.)

Do NOT pass these as separate parameters - they must ALL be inside the body dictionary.

Inputs: body (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

    Related MCP Connectors

    Related MCP Servers

    • mcp-gtm-ga4

      mharnett
      A
      license
      A
      quality
      B
      maintenance
      MCP server for Google Tag Manager and GA4, enabling tag management, consent auditing, workspace versioning, and analytics reporting through natural language.
      11
      71 npm
      3
      MIT

    • Google Analytics MCP

      PlatAid
      A
      license
      Not graded
      quality
      D
      maintenance
      A GCP-hosted MCP server for Google Analytics GA4 where each user logs in with their own Google account and queries are scoped to that user's permissions.
      Apache 2.0

    • google-analytics-gtm-mcp

      burhan29ee
      A
      license
      B
      quality
      C
      maintenance
      MCP server for Google Analytics 4 and Google Tag Manager with read and write access, providing 40 tools to manage GA4 reports, audiences, and GTM tags, triggers, and variables via natural language.
      40
      MIT

    • google-analytics-mcp

      dhawalshah
      A
      license
      A
      quality
      C
      maintenance
      Google Analytics 4 MCP server with local STDIO and shared team Cloud Run modes, realtime visitor counts, metadata discovery, and funnel analysis.
      10
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources