mcpField
G
gsc

gsc

Local
github.com/mikusnuzBusiness & Marketing8Updated 1w ago

About gsc

gsc is an MCP server for Google Search Console and Google Indexing APIs, aimed at site owners and agents working with search data. It covers API operations for properties, sitemaps, analytics, URL inspection, and eligible indexing notifications.

Key features

  1. 01List and manage Search Console sites
  2. 02List, inspect, submit, and delete sitemaps
  3. 03Query clicks, impressions, CTR, and position
  4. 04Inspect URL indexing and crawl details
  5. 05Publish eligible URLs individually or in batches

Use cases

  1. 01Review site search performance by query or device
  2. 02Find indexing or crawl issues on a page
  3. 03Submit a sitemap to Google
  4. 04Notify Google of eligible job or livestream URL changes

MCP support

Exposes Google Search Console and Indexing API operations as MCP tools, including site and sitemap management, analytics queries, URL inspection, and indexing notifications. Authentication supports OAuth2 refresh tokens or a service account.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"mikusnuz-gsc": {
"command": "npx",
"args": [
"-y",
"@mikusnuz/gsc-mcp"
],
"env": {
"GSC_CLIENT_ID": "<GSC_CLIENT_ID>",
"GSC_CLIENT_SECRET": "<GSC_CLIENT_SECRET>",
"GSC_REFRESH_TOKEN": "<GSC_REFRESH_TOKEN>",
"GSC_SERVICE_ACCOUNT_KEY_PATH": "<GSC_SERVICE_ACCOUNT_KEY_PATH>"
}
}
}
}
Run commandnpx -y @mikusnuz/gsc-mcp
Environment variables to set
GSC_CLIENT_IDSecretGoogle OAuth2 Client ID
GSC_CLIENT_SECRETSecretGoogle OAuth2 Client Secret
GSC_REFRESH_TOKENSecretGoogle OAuth2 Refresh Token
GSC_SERVICE_ACCOUNT_KEY_PATHSecretPath to Google service account JSON key file

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@mikusnuz/gsc-mcp1.3.6

Tools

13

Saved tool list · updated 1w ago

This tool takes no parameters.

Details

From the project README

gsc-mcp

npm version

English | 한국어

MCP Badge

MCP server for Google Search Console API and Google Indexing API — full API coverage.

Requires Node.js 20 or newer, matching the MCP SDK's installed runtime dependencies.

When to Use

TaskTool
"Check which queries my site ranks for"search_analytics_query
"Notify Google about an eligible job posting or livestream URL"indexing_publish
"Find pages with indexing errors"url_inspection_inspect
"Get search performance data for the last 30 days"search_analytics_query
"Compare click-through rates between mobile and desktop"search_analytics_query (group by device)
"Submit my sitemap to Google"sitemaps_submit
"Batch notify eligible job posting/livestream URLs"indexing_batch_publish

For AI agents: See llms.txt for a machine-readable summary. Copy templates/CLAUDE.md or templates/AGENTS.md into your project to teach your agent about this MCP.

Unlike other GSC MCP servers that only wrap searchAnalytics.query, this server exposes every endpoint available in the Google Search Console and Indexing APIs.

Tools (13)

Sites
ToolDescription
sites_listList all sites (properties) in your Search Console
sites_getGet details of a specific site
sites_addAdd a new site (property)
sites_deleteRemove a site
Sitemaps
ToolDescription
sitemaps_listList all submitted sitemaps for a site
sitemaps_getGet details of a specific sitemap
sitemaps_submitSubmit a sitemap
sitemaps_deleteDelete a sitemap
Search Analytics
ToolDescription
search_analytics_queryQuery search performance data (clicks, impressions, CTR, position) with filtering and grouping. Supports hourly data with the hour dimension.
URL Inspection
ToolDescription
url_inspection_inspectInspect a URL's index status, crawl info, rich results, and AMP (the deprecated mobile-usability field may be absent)
Indexing API
ToolDescription
indexing_publishNotify Google about an eligible JobPosting or BroadcastEvent URL update/removal
indexing_get_metadataGet latest notification metadata for an eligible URL (requires contentType; not index status)
indexing_batch_publishBatch notify up to 100 eligible URLs and report every embedded request status

Indexing API eligibility: Google supports this API only for pages with JobPosting structured data or livestream pages with BroadcastEvent embedded in a VideoObject. The tools require contentType so callers must identify which supported type applies. A successful API response confirms receipt of the notification; it does not guarantee that Google indexed the URL. Use url_inspection_inspect to check index status. See Google's Indexing API usage guide.

Indexing API quotas

Google's default per-project limits are 200 publish requests per day, 180 metadata requests per minute, and 380 requests per minute across endpoints. The daily limit resets at midnight Pacific Time. A batch of 100 URLs still consumes 100 requests; batching reduces connections, not quota usage. Check your project's actual quota before sending notifications. See the official quota reference.

Authentication

Two authentication methods are supported:

Option 1: OAuth2 Refresh Token
{
  "mcpServers": {
    "gsc-mcp": {
      "command": "npx",
      "args": ["-y", "@mikusnuz/gsc-mcp"],
      "env": {
        "GSC_CLIENT_ID": "your-client-id",
        "GSC_CLIENT_SECRET": "your-client-secret",
        "GSC_REFRESH_TOKEN": "your-refresh-token"
      }
    }
  }
}

Required OAuth2 scopes:

  • https://www.googleapis.com/auth/webmasters
  • https://www.googleapis.com/auth/indexing
Option 2: Service Account
{
  "mcpServers": {
    "gsc-mcp": {
      "command": "npx",
      "args": ["-y", "@mikusnuz/gsc-mcp"],
      "env": {
        "GSC_SERVICE_ACCOUNT_KEY_PATH": "/path/to/service-account-key.json"
      }
    }
  }
}

For Search Console read/write tools, add the service account as an owner or user with sufficient permission. For Indexing API tools, Google requires the service account to be added as a delegated owner of the property; user-level access is not sufficient.

Setup Guide

OAuth2 Setup
  1. Go to Google Cloud Console
  2. Create a project (or select existing)
  3. Enable Search Console API and Indexing API
  4. Create OAuth 2.0 credentials (Desktop app type)
  5. Use the OAuth Playground to generate a refresh token with scopes:
    • https://www.googleapis.com/auth/webmasters
    • https://www.googleapis.com/auth/indexing
Service Account Setup
  1. Go to Google Cloud Console
  2. Create a service account
  3. Download the JSON key file
  4. Enable Search Console API and Indexing API
  5. In Search Console, add the service account email as an owner for your sites

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.