setup-google-access
Skill1 starsChanged 34 days agoMITView on GitHub
Guide the user through connecting Claude to Google Search Console and Google Analytics 4 with a reusable service account. Use when the user wants to set up, connect, or configure Search Console / GA4 access, mentions "setup google access", credentials, service accounts, or when other skills in this plugin fail with authentication or empty-property errors.
- Pipes a download into a shell
In this repository3 other files it gives its agents.
- indexnowSkill
- onboard-siteSkill
- seo-auditSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before anything, verify what already works:
- Very specific: line 15
Check uvx is installed (uvx --version).
- Distinctive: line 21
Create a project at console.cloud.google.com.
- Distinctive: line 23
Create a service account (Credentials → Create credentials → Service account).
- Distinctive: line 24
Create a JSON key (service account → Keys → Add key → JSON) and save it in a permanent local path outside cloud-synced folders.
- Distinctive: line 31
Search Console → property → Settings → Users and permissions → Add user → service account email → Full (or Restricted for read-only).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Setup Google access
Walk the user through a one-time setup that works for unlimited websites afterwards. The end state: a Google Cloud service account whose JSON key feeds two local MCP servers (gsc and analytics, declared in this plugin's .mcp.json). If this skill was installed standalone (via npx skills add, without the plugin), the user must declare those servers manually in their client — give them the JSON block from section 4 of https://github.com/PapiScholz/search-visibility-kit/blob/main/SETUP.md.
Prerequisites check
Before anything, verify what already works:
- Try
list_properties(gsc) andget_account_summaries(analytics). If both return data, setup is done — skip to verification. - Check
uvxis installed (uvx --version). If missing, have the user install uv: Windowspowershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex", macOS/Linuxcurl -LsSf https://astral.sh/uv/install.sh | sh. If the installer errors with "file in use", uv is already installed — do not reinstall.
One-time Google Cloud setup
Guide the user through (they do this in the browser; offer to walk through each screen):
- Create a project at console.cloud.google.com. Note the Project ID.
- Enable three APIs (APIs & Services → Library): Google Search Console API, Google Analytics Data API, Google Analytics Admin API.
- Create a service account (Credentials → Create credentials → Service account). No project roles needed.
- Create a JSON key (service account → Keys → Add key → JSON) and save it in a permanent local path outside cloud-synced folders.
- Note the service account email (
name@project.iam.gserviceaccount.com) — it is the only thing needed to add future sites.
Per-site access grant
For each website:
- Search Console → property → Settings → Users and permissions → Add user → service account email → Full (or Restricted for read-only).
- GA4 → Admin → Property access management → Add user → service account email → Viewer role. Recommend Viewer (least privilege); only suggest Editor if the user has a concrete write use case.
Environment variables
This plugin's .mcp.json expects two environment variables set in the user's shell/OS:
GOOGLE_SA_KEY_PATH— absolute path to the service account JSON keyGOOGLE_CLOUD_PROJECT_ID— the Google Cloud project ID
On Windows: setx GOOGLE_SA_KEY_PATH "C:\path\to\key.json" and setx GOOGLE_CLOUD_PROJECT_ID "project-id", then fully restart the Claude app. On macOS/Linux, export them in the shell profile.
Verification
list_propertiesmust return the user's GSC properties.get_account_summariesmust return the GA4 account and property. Note the numeric property ID for reports.
Troubleshooting
- Empty property list / permission denied → the service account email was not added to that specific property, or was added at account level instead of property level in GA4.
spawn uvx ENOENT→ the client needs the full path to the uvx binary in.mcp.jsonoverrides (GUI apps do not read shell PATH). Find it withwhich uvx/Get-Command uvx.- MCP servers not appearing after config changes → the Claude app was not fully quit (system tray on Windows, Cmd+Q on macOS).
- Data mismatch vs GSC dashboard → the gsc server defaults to
dataState: all(matches dashboard).GSC_DATA_STATE=finalreturns only confirmed data (2-3 day lag).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

