← Back to Skills Marketplace
vittor1o

Google Analytics MCP

by vittor1o · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
68
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install google-analytics-mcp
Description
Query Google Analytics 4 data — reports, funnels, realtime, property details — via the GA MCP server. Uses per-workspace service account credentials; no Gemi...
README (SKILL.md)

Google Analytics

Query GA4 properties using the Google Analytics MCP server via MCPorter. Each workspace supplies its own service account credentials — no shared or global auth.

Prerequisites

  • uvx (from uv) — runs analytics-mcp ephemerally, no install needed
  • mcporternpm i -g mcporter
  • Service account JSON with GA read access in the workspace (see Setup)

Per-workspace credentials

Each workspace stores its own credentials:

{workspace}/
  credentials/
    ga-service-account.json   ← Google service account key file
    ga-config.json            ← optional: default project/property

ga-config.json shape (optional):

{
  "projectId": "my-gcp-project",
  "defaultProperty": "properties/123456789"
}

If ga-config.json is absent, pass property explicitly in every query.

Workflow

  1. Locate credentials — read {workspace}/credentials/ga-service-account.json (fail clearly if missing).
  2. Load config — read {workspace}/credentials/ga-config.json if present; extract projectId and defaultProperty.
  3. Run query via the helper script or direct mcporter call:
bash {skill_dir}/scripts/ga.sh \x3Cworkspace> \x3Ctool> [args...]

Or directly:

CREDS="{workspace}/credentials/ga-service-account.json"
PROJECT_ID="$(cat {workspace}/credentials/ga-config.json | python3 -c 'import json,sys; print(json.load(sys.stdin).get("projectId",""))')"

mcporter call \
  --stdio uvx \
  --stdio-arg analytics-mcp \
  --env "GOOGLE_APPLICATION_CREDENTIALS=$CREDS" \
  --env "GOOGLE_CLOUD_PROJECT=$PROJECT_ID" \
  "analytics-mcp.\x3Ctool>" \
  [key=value ...]

Available tools

Tool Purpose
get_account_summaries List all GA accounts + properties the SA has access to
get_property_details Details for a specific property
run_report Standard GA4 data report (dimensions, metrics, date ranges)
run_funnel_report Funnel analysis
run_realtime_report Realtime data
get_custom_dimensions_and_metrics Custom dimensions/metrics for a property
list_google_ads_links Google Ads links for a property

Common queries

List all accessible properties:

mcporter call --stdio uvx --stdio-arg analytics-mcp \
  --env "GOOGLE_APPLICATION_CREDENTIALS=$CREDS" \
  analytics-mcp.get_account_summaries

Run a report (sessions last 30 days):

mcporter call --stdio uvx --stdio-arg analytics-mcp \
  --env "GOOGLE_APPLICATION_CREDENTIALS=$CREDS" \
  --env "GOOGLE_CLOUD_PROJECT=$PROJECT_ID" \
  analytics-mcp.run_report \
  property=properties/123456789 \
  'dimensions=[{"name":"date"}]' \
  'metrics=[{"name":"sessions"}]' \
  'dateRanges=[{"startDate":"30daysAgo","endDate":"today"}]'

Setup (one-time per workspace)

See references/setup.md for full instructions. Short version:

  1. Create a GCP service account
  2. Enable Google Analytics Admin API and Google Analytics Data API
  3. Download the JSON key → save to {workspace}/credentials/ga-service-account.json
  4. In GA4: Admin → Property Access Management → add the service account email as Viewer
  5. Test: bash {skill_dir}/scripts/ga.sh {workspace} get_account_summaries

Error notes

  • PERMISSION_DENIED — SA email not added to GA property access
  • credentials not found — check ga-service-account.json path
  • API not enabled — enable Admin + Data APIs in GCP console
Usage Guidance
Install only in workspaces where you are comfortable granting read access to the relevant GA4 properties. Create a least-privilege service account with Viewer access only, keep the credentials directory out of source control and backups where possible, restrict file permissions, and rotate or revoke the JSON key if it may have been shared or committed.
Capability Assessment
Purpose & Capability
The stated purpose is to query GA4 reports, funnels, realtime data, and property details through the Google Analytics MCP server, and the required GA service account access is directly related to that purpose.
Instruction Scope
Runtime instructions are scoped to workspace-local GA credential/config files and named GA MCP tools; the helper passes the requested tool name through to the GA MCP server, so users should invoke only the documented read/reporting tools.
Install Mechanism
The skill requires uvx and mcporter and the helper runs mcporter/analytics-mcp through package tooling, which is expected for this MCP wrapper but depends on external packages at runtime.
Credentials
The skill stores a Google service account JSON key under the workspace credentials directory and uses it as GOOGLE_APPLICATION_CREDENTIALS; this is proportionate for GA API access, and the setup recommends Viewer access.
Persistence & Privilege
There is no hidden persistence or privilege escalation, but the service account key is a long-lived local credential and should be protected, excluded from git, and rotated if exposed.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install google-analytics-mcp
  3. After installation, invoke the skill by name or use /google-analytics-mcp
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: query GA4 reports, funnels, realtime data and property details via MCP server
Metadata
Slug google-analytics-mcp
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Google Analytics MCP?

Query Google Analytics 4 data — reports, funnels, realtime, property details — via the GA MCP server. Uses per-workspace service account credentials; no Gemi... It is an AI Agent Skill for Claude Code / OpenClaw, with 68 downloads so far.

How do I install Google Analytics MCP?

Run "/install google-analytics-mcp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Google Analytics MCP free?

Yes, Google Analytics MCP is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Google Analytics MCP support?

Google Analytics MCP is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Google Analytics MCP?

It is built and maintained by vittor1o (@vittor1o); the current version is v1.0.0.

💬 Comments