Google Search ConsoleSAFE
A Model Context Protocol (MCP) server providing access to Google Search Console
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server providing comprehensive access to Google Search Console data with enhanced analytics capabilities.
Features
- Enhanced Search Analytics: Retrieve up to 25,000 rows of performance data
- Advanced Filtering: Support for regex patterns and multiple filter operators
- Quick Wins Detection: Automatically identify optimization opportunities
- Rich Dimensions: Query, page, country, device, and search appearance analysis
- Flexible Date Ranges: Customizable reporting periods with historical data access
Sponsored by
macuse.app is a native macOS application that gives your AI superpowers by integrating AI assistants with macOS apps like Calendar, Mail, and Notes, plus universal UI control for any application. Supports Claude Desktop, Cursor, and Raycast with one-click setup. Privacy-first, runs locally.
Prerequisites
- Node.js 18 or later
- Google Cloud Project with Search Console API enabled
- Service Account credentials with Search Console access
Installation
npm install mcp-server-gsc
Authentication Setup
To obtain Google Search Console API credentials:
- Visit the Google Cloud Console
- Create a new project or select an existing one
- Enable the API:
- Go to "APIs & Services" > "Library"
- Search for and enable "Search Console API"
- Create credentials:
- Navigate to "APIs & Services" > "Credentials"
- Click "Create Credentials" > "Service Account"
- Fill in the service account details
- Create a new key in JSON format
- The credentials file (.json) will download automatically
- Grant access:
- Open S
1ca60a48cb53OBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add buffer-equal-constant-time --env GOOGLE_APPLICATION_CREDENTIALS=${GOOGLE_APPLICATION_CREDENTIALS} -- npx -y [email protected]{
"mcpServers": {
"buffer-equal-constant-time": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}"
}
}
}
}Exposed tools (8)
7 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
detect_quick_wins | read | Automatically detect SEO quick wins and optimization opportunities |
enhanced_search_analytics | read | Enhanced search analytics with up to 25,000 rows, regex filters, and quick wins detection |
get_sitemap | read | Get a sitemap for a site in Google Search Console |
index_inspect | read | Inspect a URL to see if it is indexed or can be indexed |
list_sitemaps | read | List sitemaps for a site in Google Search Console |
list_sites | read | List all sites in Google Search Console |
search_analytics | read | Get search performance data from Google Search Console |
submit_sitemap | write | Submit a sitemap for a site in Google Search Console |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@google-cloud/local-auth, @hono/mcp, @modelcontextprotocol/sdk, google-auth-library, googleapis, hono, zod, zod-to-json-schema
Gates applied: no_behavioural_pass, no_license.
1ca60a48cb53full audit observations/trust-audit/mcp-server/ahonn__google-search-console.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 1ca60a48cb53 | SAFE | B | 89 | first audit |
Questions
What is the Google Search Console MCP server?
A Model Context Protocol (MCP) server providing access to Google Search Console
What tools does Google Search Console expose?
8 in total: 7 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Google Search Console safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Google Search Console need?
It reads GOOGLE_APPLICATION_CREDENTIALS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Google Search Console run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as buffer-equal-constant-time at 1.0.2.
How current is this page?
The grade is for one exact copy of the source (1ca60a48cb53), read on 2026-10-06. The repository is watched and re-audited when it changes.