@patchwindow/seo-mcp

MCP server for Google Search Console and Bing Webmaster Tools. Give your AI assistant live access to search performance data, indexing status, keyword research, crawl health, and more — directly in the chat.

Features

• 10 SEO tools across Google Search Console and Bing Webmaster Tools

• Keyword research via Bing — search volume and related keywords not available in GSC

• Traffic drop analysis — automatically compare two periods and surface the biggest drops

• Striking distance finder — identify queries in positions 4–20 ready for quick ranking gains

• Brand vs. non-brand split — segment traffic without leaving your AI chat

• Dual URL inspection — inspect any URL in both Google and Bing simultaneously

• Simple auth — Bing needs one env var; GSC uses a one-time OAuth2 flow with auto-refreshing tokens

• Config file defaults — set your site URL once, skip it on every tool call

Related MCP server: MCP by Amal Alexander

Installation

Install globally:

npm install -g @patchwindow/seo-mcp

Or run without installing:

npx @patchwindow/seo-mcp

Setup

Bing Webmaster Tools

Bing uses an API key. No OAuth required.

1. Go to Bing Webmaster Tools

2. Navigate to Settings → API Access

3. Generate an API key

4. Set the environment variable:

export BING_WEBMASTER_API_KEY="your-api-key"

That's it.

Google Search Console

GSC requires OAuth2. Service accounts do not work with the Search Console API — user credentials are required.

Step 1: Create a Google Cloud project

1. Go to Google Cloud Console

2. Create a new project (or select an existing one)

3. Go to APIs & Services → Library

4. Search for Google Search Console API and enable it

Step 2: Create OAuth2 credentials

1. Go to APIs & Services → Credentials → Create Credentials → OAuth 2.0 Client ID

2. Choose Web application as the application type

3. Under Authorized redirect URIs, add:

   http://localhost:3847/callback

4. Copy the Client ID and Client Secret

Step 3: Authenticate (one-time)

Set your credentials as environment variables, then run the auth command:

export GSC_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GSC_CLIENT_SECRET="your-client-secret"

npx @patchwindow/seo-mcp auth gsc

A browser window opens for Google login. After approving, the token is saved to ~/.seo-mcp/gsc-token.json. You only need to do this once — the token refreshes automatically.

Config File (optional)

Create ~/.seo-mcp/config.json to set default site URLs. This lets you skip the site_url parameter on every tool call:

{
  "gsc": {
    "default_site": "sc-domain:example.com"
  },
  "bing": {
    "default_site": "https://example.com/"
  },
  "output": {
    "max_rows": 500
  }
}

GSC site URL format: Use sc-domain:example.com for domain properties or https://example.com/ for URL prefix properties. Check which type you have in Search Console under your property settings.

Claude Desktop Integration

Add the following to your claude_desktop_config.json (typically at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "seo": {
      "command": "npx",
      "args": ["@patchwindow/seo-mcp"],
      "env": {
        "BING_WEBMASTER_API_KEY": "your-bing-api-key",
        "GSC_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
        "GSC_CLIENT_SECRET": "your-client-secret"
      }
    }
  }
}

Cursor / Windsurf (.cursor/mcp.json or mcp.json):

{
  "seo-mcp": {
    "command": "npx",
    "args": ["@patchwindow/seo-mcp"],
    "env": {
      "BING_WEBMASTER_API_KEY": "your-bing-api-key",
      "GSC_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
      "GSC_CLIENT_SECRET": "your-client-secret"
    }
  }
}

Restart your AI client after saving the config.

Tools Reference

* = not required if default_site is set in ~/.seo-mcp/config.json.

Google Search Console

Bing Webmaster Tools

Parameter details

Examples

Ask your AI assistant:

Find quick wins for content optimization:

"Show me my top striking distance queries for the last 90 days. I want queries where I'm ranking between 5 and 15 with at least 50 impressions."

Diagnose a traffic drop:

"Compare my search traffic for April 2025 vs April 2024 by page. Flag anything that dropped more than 30%."

Research a topic before writing:

"Research the keyword 'typescript performance' in Bing. Show me monthly search volume and the top related keywords."

Audit indexing:

"Inspect the URL https://example.com/blog/my-post and tell me its indexing status, canonical URL, and whether it's eligible for rich results."

Understand brand exposure:

"Split my search traffic for Q1 2025 into branded and non-branded. My brand terms are 'acme' and 'acmecorp'. Show me the top 10 queries for each segment."

Roadmap

Planned for v2:

• gsc_top_pages — top pages by traffic with trend comparison

• bing_link_counts — inbound link data (not available in GSC API)

• bing_url_submit — trigger reindexing for new or updated URLs

• gsc_batch_url_inspection — inspect a list of URLs with rate-limit handling

• bing_crawl_settings — read and update Bing crawl frequency settings

• Multi-site support — switch between properties without reconfiguring

Building from Source

git clone https://github.com/patchwindow/seo-mcp
cd seo-mcp
npm install
npm run build

Contributing

Issues and pull requests are welcome. Please open an issue before starting work on a significant change.

License

MIT — Patch Window