Log inSubmit server
MCP Gsc logo

MCP Gsc

Connects AI assistants to Google Search Console for SEO analytics, URL inspection, property management, and sitemap operations.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install MCP Gsc

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mcp-gsc-2": {
      "command": "uvx",
      "args": [
        "method"
      ],
      "env": {
        "GSC_OAUTH_CLIENT_SECRETS_FILE": "YOUR_VALUE_HERE",
        "GSC_CREDENTIALS_PATH": "YOUR_VALUE_HERE",
        "GSC_SKIP_OAUTH": "YOUR_VALUE_HERE",
        "GSC_ALLOW_DESTRUCTIVE": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

mcp-gsc connects Google Search Console to AI assistants over MCP, exposing tools for analytics, URL inspection, property administration, and sitemap management. It supports OAuth with a Google account or a service account, and stores OAuth tokens for later use. Reach for it when you want to investigate search performance, indexing, or sitemap status through natural-language requests in a compatible client.

Use cases

  • Analyze clicks, impressions, CTR, and positions for a Search Console property
  • Compare organic search performance across two date ranges
  • Inspect multiple URLs for crawl and indexing problems
  • Review sitemap errors and submit updated sitemaps
  • Find the queries driving traffic to a specific page

Key features

  • Google Search Console OAuth and service-account authentication
  • Search analytics with date comparisons and filters
  • Individual and batch URL inspection
  • Property listing and site details
  • Sitemap status, submission, and deletion
  • Read-only access by default with opt-in destructive operations

Tools15

What MCP Gsc lets your agent do. Expand a tool for its parameters.

Self-reported~227 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

8/8 checks healthy over the last 5d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · method (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars2.2kStargazers on the source repository.
Last commit5d agoMost recent push to the default branch.
Tools exposed15Callable tools this server registers over MCP.

How MCP Gsc works

What mcp-gsc does

mcp-gsc exposes Google Search Console data and account operations as MCP tools for AI assistants. It covers four main areas:

  • Property administration, including listing properties, viewing site details, and adding or removing properties.
  • Search analytics, including queries, pages, clicks, impressions, click-through rate, position, trends, date comparisons, and filtered analysis.
  • URL inspection, including crawl and index status for individual URLs or groups of URLs.
  • Sitemap operations, including listing sitemaps, reviewing warnings and errors, and submitting or deleting sitemaps.

The analytics tools can identify queries bringing traffic to a site, summarize performance for a date range, compare two periods, or focus on a particular page. The advanced analytics tool supports filters such as country, device, query, and page.

How it works

The server communicates with an MCP client such as Claude Desktop, Cursor, Codex CLI, or Gemini CLI. You ask the assistant for a Search Console operation, and it selects the corresponding tool and parameters, such as a site URL, page URL, date range, action, or list of URLs.

Authentication uses either a Google OAuth desktop application or a Google service account. OAuth opens a browser for the initial sign-in, then saves a token for later sessions. Service-account use requires granting the service account’s email access to the relevant Search Console property.

Search Console API calls run in a worker thread, so a slow request does not block other tool calls. OAuth requests read-only access by default; destructive operations require enabling the related setting.

Setup and configuration

Before configuring the MCP client, create or select a Google Cloud project and enable the Search Console API. For OAuth, create a desktop OAuth client, configure the consent screen, and save the downloaded client-secrets JSON file. For service-account authentication, create a service account, download its JSON key, and add its email to the property in Search Console with full access.

The recommended launcher is uvx, which downloads and runs the mcp-search-console package. Client configuration supplies the full path to uvx, passes mcp-search-console as its argument, and sets the relevant environment variables.

Use GSC_OAUTH_CLIENT_SECRETS_FILE with OAuth. Use GSC_CREDENTIALS_PATH together with GSC_SKIP_OAUTH=true for a service account. After changing credentials or switching Google accounts, the reauthenticate tool starts the browser login flow again.

Tools and capabilities

Available operations include:

  • get_capabilities to list tools and show authentication status.
  • list_properties and get_site_details for property discovery and details.
  • get_search_analytics, get_performance_overview, and compare_search_periods for reporting.
  • get_search_by_page_query and get_advanced_search_analytics for page-specific and filtered analysis.
  • inspect_url_enhanced, batch_url_inspection, and check_indexing_issues for indexing investigations.
  • get_sitemaps, list_sitemaps_enhanced, and manage_sitemaps for sitemap review and management.
  • reauthenticate to repeat OAuth browser authentication.

batch_url_inspection accepts up to 10 URLs at once. Advanced analytics supports pagination and caps requests at 25,000 rows per page.

Limitations and notes

The service-account method requires property access to be granted separately in Search Console. Operations that submit or delete sitemaps, or otherwise require write access, should be used with care; destructive access is not enabled by default. The MCP client must support running a standard MCP server through a command such as uvx.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about MCP Gsc

mcp-gsc is an MCP server that connects AI assistants to Google Search Console and exposes tools for search analytics, URL inspection, property management, and sitemap operations. It supports OAuth or service-account authentication, allowing developers to investigate SEO performance and indexing data through natural-language requests in compatible MCP clients.

Install `uv` and configure your MCP client to run `uvx` with `mcp-search-console` as its argument. Add either `GSC_OAUTH_CLIENT_SECRETS_FILE` for OAuth or `GSC_CREDENTIALS_PATH` with `GSC_SKIP_OAUTH=true` for a service account.

Create a Google Cloud project, enable the Search Console API, and configure either a desktop OAuth client or a service account. OAuth opens a browser for sign-in; a service account must be added to the Search Console property with full access.

Yes, mcp-gsc works with Cursor through its MCP configuration file at `~/.cursor/mcp.json`. Configure Cursor to launch `uvx` with `mcp-search-console` and provide the appropriate Google credential environment variable.

Yes, the `batch_url_inspection` tool inspects up to 10 URLs in one request. The `check_indexing_issues` tool also checks multiple URLs for indexing problems, while `inspect_url_enhanced` provides detailed information for one URL.

Related MCP servers

All in Marketing All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMCP Gsc AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mcp-gsc-2?style=directory)](https://allmcps.com/mcp/mcp-gsc-2)
HTML Embed
<a href="https://allmcps.com/mcp/mcp-gsc-2"><img src="https://allmcps.com/api/badge/mcp-gsc-2?style=directory" alt="MCP Gsc on AllMCPs" /></a>