Skip to content
Back to search

google-analytics-mcp

Google Analytics MCP Server (Experimental)

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/googleanalytics/google-analytics-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/googleanalytics/google-analytics-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/googleanalytics--google-analytics-mcp/badge.svg)](/listings/googleanalytics--google-analytics-mcp)

HTML

<a href="/listings/googleanalytics--google-analytics-mcp"><img src="/api/listings/googleanalytics--google-analytics-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

✨ Watch the [Google Analytics MCP Setup Tutorial](https://youtu.be/nS8HLdwmVlY) on YouTube for a step-by-step walkthrough of these instructions.

Setup involves the following steps:

1. Configure Python. 1. Configure credentials for Google Analytics. 1. Configure Gemini.

Configure Python 🐍

[Install pipx](https://pipx.pypa.io/stable/#install-pipx).

Enable APIs in your project ✅

[Follow the instructions](https://support.google.com/googleapi/answer/6158841) to enable the following APIs in your Google Cloud project:

- [Google Analytics Admin API](https://console.cloud.google.com/apis/library/analyticsadmin.googleapis.com) - [Google Analytics Data API](https://console.cloud.google.com/apis/library/analyticsdata.googleapis.com)

Configure credentials 🔑

Configure your [Application Default Credentials (ADC)](https://cloud.google.com/docs/authentication/provide-credentials-adc). Make sure the credentials are for a user with access to your Google Analytics accounts or properties.

Credentials must include the Google Analytics read-only scope:

https://www.googleapis.com/auth/analytics.readonly

Check out [Manage OAuth Clients](https://support.google.com/cloud/answer/15549257) for how to create an OAuth client.

Here are some sample `gcloud` commands you might find useful:

- Set up ADC using user credentials and an OAuth desktop or web client after downloading the client JSON to `YOUR_CLIENT_JSON_FILE`.

  gcloud auth application-default login \
    --scopes https://www.googleapis.com/auth/analytics.readonly,https://www.googleapis.com/auth/cloud-platform \
    --client-id-file=YOUR_CLIENT_JSON_FILE

- Set up ADC using service account impersonation.

  gcloud auth application-default login \
    --impersonate-service-account=SERVICE_ACCOUNT_EMAIL \
    --scopes=https://www.googleapis.com/auth/analytics.readonly,https://www.googleapis.com/auth/cloud-platform

When the `gcloud auth application-default` command completes, copy the `PATH_TO_CREDENTIALS_JSON` file location printed to the console in the following message. You'll need this for the next step!

Credentials saved to file: [PATH_TO_CREDENTIALS_JSON]

Configure Gemini

1. Install [Gemini CLI](https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/installation.md) or [Gemini Code Assist](https://marketplace.visualstudio.com/items?itemName=Google.geminicodeassist).

1. Create or edit the file at `~/.gemini/settings.json`, adding your server to the `mcpServers` list.

Replace `PATH_TO_CREDENTIALS_JSON` with the path you copied in the previous step.

We also recommend that you add a `GOOGLE_CLOUD_PROJECT` attribute to the `env` object. Replace `YOUR_PROJECT_ID` in the following example with the [project ID](https://support.google.com/googleapi/answer/7014113) of your Google Cloud project.

```json { "mcpServers": { "analytics-mcp": { "command": "pipx", "args": ["run", "analytics-mcp"], "env": { "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON", "GOOGLE_PROJECT_ID": "YOUR_PROJECT_ID" } } } } ```

Configure Claude Code

1. Add the MCP server with the following command:

Replace `PATH_TO_CREDENTIALS_JSON` with the path you copied in the previous step, and replace `YOUR_PROJECT_ID` with the [project ID](https://support.google.com/googleapi/answer/7014113) of your Google Cloud project.

```shell claude mcp add analytics-mcp \ --scope user \ -e "GOOGLE_APPLICATION_CREDENTIALS=PATH_TO_CREDENTIALS_JSON" \ -e "GOOGLE_PROJECT_ID=YOUR_PROJECT_ID" \ -- pipx run analytics-mcp ```

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 351 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Google Analytics MCP Server
  2. [![PyPI version](https://img.shields.io/pypi/v/analytics-mcp.svg)](https://pypi.org/project/analytics-mcp/)
  3. [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
  4. [![GitHub branch check runs](https://img.shields.io/github/check-runs/googleanalytics/google-analytics-mcp/main)](https://github.com/googleanalytics/google-analytics-mcp/actions?query=branch%3Amain++)
  5. [![PyPI - Downloads](https://img.shields.io/pypi/dm/analytics-mcp)](https://pypi.org/project/analytics-mcp/)
  6. [![GitHub stars](https://img.shields.io/github/stars/googleanalytics/google-analytics-mcp?style=social)](https://github.com/googleanalytics/google-analytics-mcp/stargazers)
  7. [![GitHub forks](https://img.shields.io/github/forks/googleanalytics/google-analytics-mcp?style=social)](https://github.com/googleanalytics/google-analytics-mcp/network/members)
  8. [![YouTube Video Views](https://img.shields.io/youtube/views/PT4wGPxWiRQ)](https://www.youtube.com/watch?v=PT4wGPxWiRQ)
  9. This repo contains the source code for running a local or remote multi-tenant
  10. [MCP](https://modelcontextprotocol.io) server that interacts with APIs for
  11. [Google Analytics](https://support.google.com/analytics).
  12. Join the discussion and ask questions in the
  13. [🤖-analytics-mcp channel](https://discord.com/channels/971845904002871346/1398002598665257060)
  14. on Discord.
  15. ## Tools 🛠️
  16. The server uses the
  17. [Google Analytics Admin API](https://developers.google.com/analytics/devguides/config/admin/v1)
  18. and
  19. [Google Analytics Data API](https://developers.google.com/analytics/devguides/reporting/data/v1)
  20. to provide several
  21. [Tools](https://modelcontextprotocol.io/docs/concepts/tools) for use with LLMs.
  22. ### Retrieve account and property information 🟠
  23. - `get_account_summaries`: Retrieves information about the user's Google
  24. Analytics accounts and properties.
  25. - `get_property_details`: Returns details about a property.
  26. - `list_google_ads_links`: Returns a list of links to Google Ads accounts for
  27. a property.
  28. - `list_property_annotations`: Returns annotations for a property.
  29. - `create_property_annotation`: Creates an annotation for a property (requires
  30. passing the `--allow-write` flag and the `analytics.edit` scope).
  31. - `list_key_events`: Returns the key events (formerly conversions) defined on a
  32. property.
  33. - `create_custom_dimension`: Creates a custom dimension on a property (requires
  34. passing the `--allow-write` flag and the `analytics.edit` scope, and the
  35. Editor role on the property).
  36. - `create_key_event`: Marks an event as a key event on a property (requires
  37. passing the `--allow-write` flag and the `analytics.edit` scope, and the
  38. Marketer or Editor role on the property).
  39. ### Run core reports 📙
  40. - `run_report`: Runs a Google Analytics report using the Data API.
  41. - `run_funnel_report`: Runs a Google Analytics funnel report using the Data API.
  42. - `run_conversions_report`: Runs a Google Analytics conversions report
  43. (ad costs, conversions, ROAS and attribution models) using the Data API.
  44. - `get_custom_dimensions_and_metrics`: Retrieves the custom dimensions and
  45. metrics for a specific property.
  46. ### Run realtime reports ⏳
  47. - `run_realtime_report`: Runs a Google Analytics realtime report using the
  48. Data API.
  49. ## Setup instructions 🔧
  50. ✨ Watch the [Google Analytics MCP Setup
  51. Tutorial](https://youtu.be/nS8HLdwmVlY) on YouTube for a step-by-step
  52. walkthrough of these instructions.
  53. [![Watch the video](https://img.youtube.com/vi/nS8HLdwmVlY/mqdefault.jpg)](https://www.youtube.com/watch?v=nS8HLdwmVlY)
  54. Setup involves the following steps:
  55. 1. Configure Python.
  56. 1. Configure credentials for Google Analytics.
  57. 1. Configure Gemini.
  58. ### Configure Python 🐍
  59. [Install pipx](https://pipx.pypa.io/stable/#install-pipx).
  60. ### Enable APIs in your project ✅
  61. [Follow the instructions](https://support.google.com/googleapi/answer/6158841)
  62. to enable the following APIs in your Google Cloud project:
  63. - [Google Analytics Admin API](https://console.cloud.google.com/apis/library/analyticsadmin.googleapis.com)
  64. - [Google Analytics Data API](https://console.cloud.google.com/apis/library/analyticsdata.googleapis.com)
  65. ### Configure credentials 🔑
  66. Configure your [Application Default Credentials
  67. (ADC)](https://cloud.google.com/docs/authentication/provide-credentials-adc).
  68. Make sure the credentials are for a user with access to your Google Analytics
  69. accounts or properties.
  70. Credentials must include the Google Analytics read-only scope:
  71. ```
  72. https://www.googleapis.com/auth/analytics.readonly
  73. ```
  74. If you plan to enable write tools (such as `create_property_annotation`,
  75. `create_custom_dimension` or `create_key_event`) using the `--allow-write` flag,
  76. your credentials must also include the edit scope:
  77. ```
  78. https://www.googleapis.com/auth/analytics.edit
  79. ```
  80. When using Application Default Credentials, add this scope to the `--scopes`
  81. value of the `gcloud` commands below and re-run the login.
  82. Check out
  83. [Manage OAuth Clients](https://support.google.com/cloud/answer/15549257)
  84. for how to create an OAuth client.
  85. Here are some sample `gcloud` commands you might find useful:
  86. - Set up ADC using user credentials and an OAuth desktop or web client after
  87. downloading the client JSON to `YOUR_CLIENT_JSON_FILE`.
  88. ```shell
  89. gcloud auth application-default login \
  90. --scopes https://www.googleapis.com/auth/analytics.readonly,https://www.googleapis.com/auth/cloud-platform \
  91. --client-id-file=YOUR_CLIENT_JSON_FILE
  92. ```
  93. - Set up ADC using service account impersonation.
  94. ```shell
  95. gcloud auth application-default login \
  96. --impersonate-service-account=SERVICE_ACCOUNT_EMAIL \
  97. --scopes=https://www.googleapis.com/auth/analytics.readonly,https://www.googleapis.com/auth/cloud-platform
  98. ```
  99. When the `gcloud auth application-default` command completes, copy the
  100. `PATH_TO_CREDENTIALS_JSON` file location printed to the console in the
  101. following message. You'll need this for the next step!
  102. ```
  103. Credentials saved to file: [PATH_TO_CREDENTIALS_JSON]
  104. ```
  105. ### Configure Gemini
  106. 1. Install [Gemini
  107. CLI](https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/installation.md)
  108. or [Gemini Code
  109. Assist](https://marketplace.visualstudio.com/items?itemName=Google.geminicodeassist).
  110. 1. Create or edit the file at `~/.gemini/settings.json`, adding your server
  111. to the `mcpServers` list.
  112. Replace `PATH_TO_CREDENTIALS_JSON` with the path you copied in the previous
  113. step.
  114. We also recommend that you add a `GOOGLE_CLOUD_PROJECT` attribute to the
  115. `env` object. Replace `YOUR_PROJECT_ID` in the following example with the
  116. [project ID](https://support.google.com/googleapi/answer/7014113) of your
  117. Google Cloud project.
  118. ```json
  119. {
  120. "mcpServers": {
  121. "analytics-mcp": {
  122. "command": "pipx",
  123. "args": ["run", "analytics-mcp"],
  124. "env": {
  125. "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
  126. "GOOGLE_CLOUD_PROJECT": "YOUR_PROJECT_ID"
  127. }
  128. }
  129. }
  130. }
  131. ```
  132. To enable write tools (e.g. `create_property_annotation`), append
  133. `"--allow-write"` to `"args"`: `["run", "analytics-mcp", "--allow-write"]`.
  134. ### Configure Claude Code
  135. 1. Add the MCP server with the following command:
  136. Replace `PATH_TO_CREDENTIALS_JSON` with the path you copied in the previous
  137. step, and replace `YOUR_PROJECT_ID` with the
  138. [project ID](https://support.google.com/googleapi/answer/7014113) of your
  139. Google Cloud project.
  140. ```shell
  141. claude mcp add analytics-mcp \
  142. --scope user \
  143. -e "GOOGLE_APPLICATION_CREDENTIALS=PATH_TO_CREDENTIALS_JSON" \
  144. -e "GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID" \
  145. -- pipx run analytics-mcp
  146. ```
  147. ## Multi-tenant HTTP & End-User OAuth 🌐
  148. To host `analytics-mcp` as a shared multi-tenant HTTP service (where each end
  149. user signs in with their own Google account via OAuth 2.0 rather than using
  150. server-side Application Default Credentials), start the server with
  151. `--transport http`:
  152. ```shell
  153. pipx run analytics-mcp \
  154. --transport http --stateless-http --host 0.0.0.0 --port 8080
  155. ```
  156. - **Agent Framework OAuth (e.g. Google ADK)**: Configure per-user Google OAuth
  157. on `McpToolset` so end users are automatically prompted with a **Sign in**
  158. button in the chat UI, and can even combine Google Analytics MCP alongside
  159. other MCP servers in the same agent. Paired with `--stateless-http`, this
  160. mode is completely stateless and horizontally scalable across multiple
  161. replicas.
  162. - **Native MCP OAuth 2.1 Server (`--oauth`)**: Pass `--oauth` or set
  163. `ANALYTICS_MCP_OAUTH=true` (with `GOOGLE_OAUTH_CLIENT_ID`,
  164. `GOOGLE_OAUTH_CLIENT_SECRET`, and optional `ANALYTICS_MCP_ISSUER_URL`) to
  165. enable the built-in MCP OAuth 2.1 Authorization Server:
  166. ```shell
  167. export GOOGLE_OAUTH_CLIENT_ID="your-client-id.apps.googleusercontent.com"
  168. export GOOGLE_OAUTH_CLIENT_SECRET="your-client-secret"
  169. export ANALYTICS_MCP_ISSUER_URL="https://analytics-mcp.yourdomain.com"
  170. pipx run analytics-mcp \
  171. --transport http --stateless-http --oauth --host 0.0.0.0 --port 8080
  172. ```
  173. Note: The built-in `--oauth` provider stores dynamic client registrations,
  174. pending authorization state, and refresh tokens in process memory (run as a
  175. single instance or with sticky sessions; restarts require re-authentication).
  176. ### Deploy with Docker & Google Cloud Run 🐳
  177. The repository includes a root [`Dockerfile`](Dockerfile) that runs
  178. `analytics-mcp` in stateless HTTP mode on `$PORT` (default `8080`) as a
  179. non-root user. Server flags can be configured entirely through environment
  180. variables:
  181. | Environment Variable | CLI Option | Default | Description |
  182. | --- | --- | --- | --- |
  183. | `PORT` | `--port` | `8000` (`8080` in `Dockerfile`) | Port to bind when `--transport http`. |
  184. | `ANALYTICS_MCP_STATELESS_HTTP` | `--stateless-http` | `false` (`true` in `Dockerfile`) | Handle each HTTP request independently without in-memory session state. |
  185. | `ANALYTICS_MCP_ALLOW_WRITE` | `--allow-write` | `false` | Enable tools that create or modify Google Analytics resources. |
  186. | `ANALYTICS_MCP_OAUTH` | `--oauth` | `false` | Enable the built-in MCP OAuth 2.1 Authorization Server. |
  187. | `ANALYTICS_MCP_ISSUER_URL` | `--issuer-url` | `http://<host>:<port>` | Public HTTPS base URL of the service when OAuth is enabled. |
  188. | `GOOGLE_OAUTH_CLIENT_ID` | — | — | Google OAuth 2.0 Web Client ID (required when OAuth is enabled). |
  189. | `GOOGLE_OAUTH_CLIENT_SECRET` | — | — | Google OAuth 2.0 Web Client Secret (inject via Secret Manager in production). |
  190. - **Stateless HTTP mode on Cloud Run** (for upstream agents like Google ADK that
  191. forward per-user Bearer tokens):
  192. ```shell
  193. gcloud run deploy analytics-mcp \
  194. --source . \
  195. --region us-central1 \
  196. --allow-unauthenticated
  197. ```
  198. Note that `--allow-unauthenticated` exposes the public HTTPS endpoint at the
  199. Cloud Run layer, while `analytics-mcp` itself strictly requires a Google OAuth
  200. Bearer token on every tool request.
  201. - **Native MCP OAuth 2.1 mode on Cloud Run** (storing the client secret in
  202. Google Cloud Secret Manager so it is injected as an environment variable at
  203. runtime rather than stored in files or source control):
  204. ```shell
  205. # 1. Store your Google OAuth Client Secret in Secret Manager once
  206. printf "%s" "YOUR_CLIENT_SECRET" | \
  207. gcloud secrets create analytics-mcp-oauth-secret --data-file=-
  208. # 2. Deploy to Cloud Run (--max-instances=1 keeps in-memory OAuth state consistent)
  209. gcloud run deploy analytics-mcp \
  210. --source . \
  211. --region us-central1 \
  212. --allow-unauthenticated \
  213. --max-instances 1 \
  214. --set-env-vars "ANALYTICS_MCP_OAUTH=true,GOOGLE_OAUTH_CLIENT_ID=YOUR_CLIENT_ID.apps.googleusercontent.com" \
  215. --set-secrets "GOOGLE_OAUTH_CLIENT_SECRET=analytics-mcp-oauth-secret:latest"
  216. # 3. Set ANALYTICS_MCP_ISSUER_URL to the deployed Cloud Run URL and add
  217. # <SERVICE_URL>/oauth/callback to Authorized redirect URIs in Cloud Console
  218. SERVICE_URL=$(gcloud run services describe analytics-mcp --region us-central1 --format="value(status.url)")
  219. gcloud run services update analytics-mcp \
  220. --region us-central1 \
  221. --update-env-vars "ANALYTICS_MCP_ISSUER_URL=${SERVICE_URL}"
  222. ```
  223. - **Local Docker**:
  224. ```shell
  225. docker build -t analytics-mcp .
  226. docker run --rm -p 8080:8080 \
  227. -e ANALYTICS_MCP_OAUTH=true \
  228. -e GOOGLE_OAUTH_CLIENT_ID="your-client-id.apps.googleusercontent.com" \
  229. -e GOOGLE_OAUTH_CLIENT_SECRET="your-client-secret" \
  230. analytics-mcp
  231. ```
  232. See the complete multi-tenant walkthrough and runnable ADK agent code in
  233. [`examples/multi_tenant_adk_agent/README.md`](examples/multi_tenant_adk_agent/README.md).
  234. ## Try it out 🥼
  235. Launch Gemini Code Assist or Gemini CLI and type `/mcp`. You should see
  236. `analytics-mcp` listed in the results.
  237. Here are some sample prompts to get you started:
  238. - Ask what the server can do:
  239. ```
  240. what can the analytics-mcp server do?
  241. ```
  242. - Ask about a Google Analytics property
  243. ```
  244. Give me details about my Google Analytics property with 'xyz' in the name
  245. ```
  246. - Prompt for analysis:
  247. ```
  248. what are the most popular events in my Google Analytics property in the last 180 days?
  249. ```
  250. - Ask about signed-in users:
  251. ```
  252. were most of my users in the last 6 months logged in?
  253. ```
  254. - Ask about property configuration:
  255. ```
  256. what are the custom dimensions and custom metrics in my property?
  257. ```
  258. - Create a custom dimension (requires the `--allow-write` flag):
  259. ```
  260. Create an event-scoped custom dimension for the plan_tier parameter in property 12345
  261. ```
  262. ## Contributing ✨
  263. Contributions welcome! See the [Contributing Guide](CONTRIBUTING.md).
  264. ## Troubleshooting
  265. See the [Troubleshooting Guide](TROUBLESHOOTING.md) for common issues and workarounds.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.