Google Analytics 4 MCP Server
Google Analytics 4 MCP server for Model Context Protocol hosts. Discover account/property structure, explore the live schema, run reports (with row-volume safety), create large asynchronous exports, and inspect admin configuration through a standardised MCP interface. Its 22 documented tools cover report, audience, property, task.
People connecting productivity tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.
One of 41 MCP servers published from mindstone/mcp-servers. Stars and repository activity are shared across all of them. See all 41 →
VERIFIED ACTIVE
LAST COMMIT 2026-08-19 · VERIFIED 2026-08-25
NOASSERTION · TypeScript servers · how we verify → /methodology
01 · Install Google Analytics 4
before you install - you'll need
GOOGLE_APPLICATION_CREDENTIALS, GA4_PROPERTY_ID are optional or environment-specific per the README.
Claude Code
claude mcp add mindstone-mcp-servers-connectors-google- -- npx -y @mindstone/mcp-server-google-analytics Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"mindstone-mcp-servers-connectors-google-": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-google-analytics"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license no standard license detected - usage rights unclear; check the repo before commercial use
npm package @mindstone/mcp-server-google-analytics - published under the repo owner's npm scope (@mindstone)
registry namespace io.github.mindstone is GitHub-verified and matches the repo owner
03 · What Google Analytics 4 can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
What you can build
With this server connected, an agent can discover available accounts and properties, verify dimension/metric combinations before reporting, start an asynchronous report task for large exports (no synchronous timeout, no row-volume gate), and find and reuse existing exports.
Capability map
Tools grouped from the project's README - what Google Analytics 4 lets an agent do.
Report
6 tools - e.g. core report with row-volume safety (estimate, opt-in to large datasets, automatic aggregation suggestions); cross-tabulated reports; last 30 minutes of activity
ga_run_report · ga_run_pivot_report · ga_run_realtime_report · ga_create_report_task · ga_get_report_task · ga_query_report_task
Audience
4 tools - e.g. snapshot the users in an audience (incl. predictive segments); charges audience-export quota tokens; poll export state until ACTIVE; find and reuse existing exports
ga_create_audience_export · ga_get_audience_export · ga_list_audience_exports · ga_query_audience_export
Property
3 tools - e.g. currency, time zone, industry category, service level; same data with summary counts; remaining tokens / requests
ga_get_property_details · ga_get_property_schema · ga_get_property_quotas_snapshot
Account
1 tool - e.g. discover available accounts and properties
ga_list_account_summaries
Properties
1 tool - e.g. flat list of GA4 properties with optional filtering
ga_list_properties
Metadata
1 tool - e.g. live property schema
ga_get_metadata
Schema
1 tool - e.g. keyword search across dimensions and metrics
ga_search_schema
Check
1 tool - e.g. verify dimension/metric combinations before reporting
ga_check_compatibility
Limitations (from the README)
- Read-only posture. All tools are read-only except ga_create_report_task and ga_create_audience_export, which materialise server-side snapshots and charge quota (annotated readOnlyHint: false, destructiveHint: true, idempotentHint: false) without modifying property configuration. Hosts can gate the two creation tools behind explicit user approval. - Alpha endpoints. Audiences, channel groups, BigQuery links, the glo
04 · Who maintains Google Analytics 4
Google Analytics 4 is maintained by mindstone. We track 41 MCP servers from mindstone - 41 actively maintained, 10 combined GitHub stars, oldest repo from Apr 2026. Full record: all servers from mindstone.
- OpenAI Image OpenAI image generation MCP server for Model Context Protocol hosts ★ 10
- Google Workspace Google Workspace MCP server for Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, and more ★ 10
- Slack Slack MCP server: channels, messages, threads, reactions, users, files, and scheduled messages ★ 10
- HubSpot HubSpot CRM: contacts, deals, tickets, line items, properties, marketing, files, workflows, threads ★ 10
- Gamma Gamma AI presentation generation MCP server for Model Context Protocol hosts ★ 10
- Browser Automation Browser automation MCP server: navigate, fill forms, click, screenshot, and manage tabs ★ 10
05 · Facts
- repository
- github.com/mindstone/mcp-servers
- category
- productivity - actively maintained as of 2026-08-25.
- registry
- io.github.mindstone/mcp-server-google-analytics (active, first published 2026-05-21 · 3 versions)
- packages
- npm:@mindstone/mcp-server-google-analytics
06 · Google Analytics 4 FAQ
Is Google Analytics 4 still maintained?
Yes - as of 2026-08-25, its last commit was 2026-08-19. We re-verify nightly.
What can Google Analytics 4 do?
With this server connected, an agent can discover available accounts and properties, verify dimension/metric combinations before reporting, start an asynchronous report task for large exports (no synchronous timeout, no row-volume gate), and find and reuse existing exports.
How do I install Google Analytics 4?
Run `npx -y @mindstone/mcp-server-google-analytics`. The README documents 2 environment variables (GOOGLE_APPLICATION_CREDENTIALS, GA4_PROPERTY_ID) to set first. GOOGLE_APPLICATION_CREDENTIALS, GA4_PROPERTY_ID are optional or environment-specific per the README. You can also paste the ready-made client config above.
Does Google Analytics 4 run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Google Analytics 4
Alternatives to Google Analytics 4
Maintained productivity servers if Google Analytics 4 isn't the fit.
- Reactive Resume Free open-source resume builder with remote MCP tools for resumes and job applications. ★ 41,676 · 2026-08-24
- Praison AI AI Agents Framework with Self Reflection and MCP support ★ 8,955 · 2026-08-24
- Kaneo Official MCP server for Kaneo: manage tasks, projects, and labels from Claude and other MCP clients ★ 8,508 · 2026-08-24
- Basic Memory Local-first knowledge management with bi-directional LLM sync via Markdown files. ★ 3,749 · 2026-08-24
- Mindwtr Task and project automation for local Mindwtr data, with read-only self-hosted Cloud access. ★ 1,742 · 2026-08-25
- Pm Claude Skills 1117 professional Agent Skills + workflow recipes - searchable & fetchable over MCP. ★ 1,308 · 2026-08-24
Pairs well with
Servers that cover what Google Analytics 4 doesn't - only shown when the pairing reason fits the companion.
More productivity MCP servers · Google Workspace (mindstone) · HubSpot · Humaans · Kling · Microsoft 365 Calendar