Skip to main content
Glama
GidianB

QuerySail

by GidianB

QuerySail: Google Search Console MCP server

QuerySail is a hosted, read-only MCP server for Google Search Console. Connect it to ChatGPT, Claude, Codex, Cursor or VS Code, sign in, connect your Google account once, and ask about your search traffic in plain language. There is nothing to install and no API key to paste.

This repository holds the public listing files (MCP Registry server.json, a Claude Code plugin, client configs). The service itself is hosted at querysail.com; its source is not published here.

Tools

All tools are read-only. QuerySail cannot submit sitemaps, request indexing or change any Search Console setting.

Tool

What it does

list_properties

Lists the Search Console properties your connected Google accounts can read, with exact IDs and permission level.

get_performance

Clicks, impressions, CTR and average position, as totals or by date, hour, query, page, country, device or search appearance, with filters. Covers web, image, video, news, Discover and Google News results.

compare_performance

Compares two periods (previous period, same weekdays a year earlier, or custom dates) and lists the queries, pages, countries or devices that gained or lost the most.

inspect_urls

Inspects up to 20 URLs: whether each is on Google, why not, last crawl, robots.txt and noindex blocking, and the canonical Google chose.

list_sitemaps

Lists submitted sitemaps with when Google last read them, URL counts, errors and warnings.

Related MCP server: GSC Analyst Connector

Example prompts

  • Which of my pages got the most clicks from Google in the last 28 days?

  • What changed in my search traffic compared with the previous 28 days?

  • Is my homepage indexed on Google, and which canonical did Google choose?

  • Which queries rank on page two for my blog, sorted by impressions?

Setup

You need a QuerySail account with Google Search Console connected: sign up at https://querysail.com. Each client below opens a browser window to sign in the first time.

Claude Code

claude mcp add --transport http --scope user querysail-gsc https://mcp.querysail.com/gsc/mcp

Then run /mcp, choose querysail-gsc and sign in. Or install it as a plugin, which also adds a Search Console analysis skill:

/plugin marketplace add GidianB/querysail-gsc
/plugin install querysail-gsc@querysail

Claude Desktop and claude.ai

Open Customize → Connectors, select + Add → Add custom connector, name it QuerySail and paste https://mcp.querysail.com/gsc/mcp as the server URL.

ChatGPT

Turn on Developer mode under Settings → Security and login, go to chatgpt.com/plugins, select the plus button and paste the endpoint as the connection URL.

Codex

codex mcp add querysail-gsc --url https://mcp.querysail.com/gsc/mcp
codex mcp login querysail-gsc

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "querysail-gsc": { "url": "https://mcp.querysail.com/gsc/mcp" }
  }
}

VS Code

Run MCP: Add Server, choose HTTP and paste the endpoint, or add to mcp.json:

{
  "servers": {
    "querysail-gsc": { "type": "http", "url": "https://mcp.querysail.com/gsc/mcp" }
  }
}

Clients that only run local commands

Use the mcp-remote bridge (needs Node.js):

{
  "mcpServers": {
    "querysail-gsc": { "command": "npx", "args": ["mcp-remote", "https://mcp.querysail.com/gsc/mcp"] }
  }
}

Data and limits

License

The files in this repository are MIT licensed. The QuerySail service is subject to its terms.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Provides read-only access to Google Search Console data, allowing AI assistants to query site performance metrics like keywords, clicks, and rankings using natural language. It supports listing verified properties, querying search analytics with dimension filters, and retrieving sitemap information.
    3
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables querying Google Search Console data, including search analytics with advanced filtering, quick wins detection, and rich dimensions, through natural language.
    4,979 npm
    MIT