Skip to content
MCP server

Search Console MCP

One AI interface to Search Console, Bing, GA4 and AdSense data, with multi-account support

Runs locallyStatus and history
Pricing
Open source
Platforms
CLI, macOS, Windows
Runs
Locally
Version
2.1.4
Listing updated
2 days ago

About Search Console MCP

Search Console MCP is an open-source MCP server for web search and scraping. It runs locally on your machine and is started by your AI client.

The pitch is that the model should not guess at averages or trends, so the server calculates them. It connects Google Search Console, Bing Webmaster Tools, Google Analytics 4 and AdSense, supports several accounts at once and picks the right one per request, which makes side-by-side Google and Bing comparisons possible.

The site suggests prompts such as finding when a traffic drop began and which pages caused it, listing keywords ranking in positions 8 to 15 with at least 1,000 impressions, spotting keyword cannibalisation between pages, and running a weekly review split by brand and non-brand. The README names tools including analytics_query, genai_query_insights, adsense_report, sitemaps_submit and sitemaps_delete. The genai tool is a heuristic that flags conversational-style queries, since neither Google nor Bing offers official data on AI citations.

Version 2.1.4 resolves properties exactly when several verified properties share a hostname and fails with the list of matches instead of guessing. Setup is read-only by default; writes such as sitemap submission need an explicit extra permission. AdSense needs its own readonly OAuth scope and cannot use service accounts. The package is installed from npm over stdio, or as an .mcpb bundle; an SSE mode is deprecated.

Install

Run in a terminal

claude mcp add search-console-mcp --env GOOGLE_APPLICATION_CREDENTIALS='<GOOGLE_APPLICATION_CREDENTIALS>' --env BING_API_KEY='<BING_API_KEY>' --env PAGESPEED_API_KEY='<PAGESPEED_API_KEY>' -- npx -y search-console-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "search-console-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "search-console-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>",
        "BING_API_KEY": "<BING_API_KEY>",
        "PAGESPEED_API_KEY": "<PAGESPEED_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "search-console-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "search-console-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>",
        "BING_API_KEY": "<BING_API_KEY>",
        "PAGESPEED_API_KEY": "<PAGESPEED_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "search-console-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "search-console-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>",
        "BING_API_KEY": "<BING_API_KEY>",
        "PAGESPEED_API_KEY": "<PAGESPEED_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "search-console-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "search-console-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>",
        "BING_API_KEY": "<BING_API_KEY>",
        "PAGESPEED_API_KEY": "<PAGESPEED_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "search-console-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "search-console-mcp"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>",
        "BING_API_KEY": "<BING_API_KEY>",
        "PAGESPEED_API_KEY": "<PAGESPEED_API_KEY>"
      }
    }
  }
}

Configuration

  • GOOGLE_APPLICATION_CREDENTIALSGoogle Cloud Service Account JSON key content or path. Optional if OAuth setup is used.
  • BING_API_KEYBing API Key
  • PAGESPEED_API_KEYPageSpeed Insights API key for higher quota (25k/day). Optional.

Tools this server provides (5)

Taken from the project documentation; the running server may differ.

analytics_query
Queries search analytics data with a row limit.
genai_query_insights
Flags likely conversational or AI-mode queries across Google and Bing.
adsense_report
Reports AdSense earnings.
sitemaps_submit
Submits a sitemap to Search Console.
sitemaps_delete
Deletes a sitemap from Search Console.

What it does

Four data sources
Combines Search Console, Bing Webmaster Tools, GA4 and AdSense.
Multi-account
Connect several accounts and let the server choose per request.
Calculated analytics
Anomaly detection and time-series tools do the maths instead of the model.
Exact property matching
Ambiguous properties produce a list rather than a guess.
Read-only by default
Writes need an explicit permission step.
AdSense reports
Earnings, payments and account alerts via a separate scope.

Good for

  • Find when a traffic drop started and which pages caused it
  • List keywords ranking just off page one
  • Detect pages competing for the same query
  • Compare Google and Bing performance for a site
  • Run a weekly SEO health review

Pricing

Open source

Free package; Google, Bing and AdSense accounts are your own.

Prices change. Check searchconsolemcp.saurabh.app before you buy.

Search Console MCP FAQ

How is it installed?

From npm as search-console-mcp over stdio, or as an .mcpb bundle.

Can it change my Search Console?

Only with an explicit write permission; setup is read-only by default.

What credentials does it use?

A Google service account or OAuth, a Bing API key, and an optional PageSpeed key.

Does it show AI citation data?

No official data exists; the genai tool is a heuristic over query data.

What licence is it under?

The README badge shows MIT.

Is Search Console MCP free?

Yes. Search Console MCP is open source, so you can use and self-host it for free.

How do I add Search Console MCP to Claude Code?

Run this command in your terminal: claude mcp add search-console-mcp --env GOOGLE_APPLICATION_CREDENTIALS='<GOOGLE_APPLICATION_CREDENTIALS>' --env BING_API_KEY='<BING_API_KEY>' --env PAGESPEED_API_KEY='<PAGESPEED_API_KEY>' -- npx -y search-console-mcp

What are the best alternatives to Search Console MCP?

The closest alternatives to Search Console MCP are Scrapling MCP Server, Firecrawl MCP Server, Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP and SearXNG Search.

Alternatives to Search Console MCP

  1. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  2. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  3. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  4. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  5. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  6. Indian NSE and BSE stock market data for AI assistants through 48 MCP tools

    • 17 tools
    • Remote
    • Freemium
    • 150 GitHub stars
    • Finance and payments