gsc-mcp-server

MCP server for Google Search Console. Query search performance, list properties, and inspect URL indexing status from Cursor, Claude Desktop, or any MCP-compatible client.

Tools

Related MCP server: google-search-console-mcp-python

Prerequisites

• Node.js 18+

• A Google Cloud project with the Search Console API enabled

• An OAuth 2.0 Desktop client (client ID + secret)

• A Google account with access to the Search Console properties you want to query

Google Cloud setup

1. Go to Google Cloud Console.

2. Create or select a project.

3. Open APIs & Services → Library and enable Google Search Console API.

4. Open APIs & Services → Credentials → Create Credentials → OAuth client ID.

5. Application type: Desktop app.

6. Add http://localhost:3336/callback as an authorized redirect URI (if prompted).

7. Copy the Client ID and Client secret.

Install and authenticate

Option A: From npm (after publish)

export GOOGLE_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GOOGLE_CLIENT_SECRET="your-client-secret"

npx gsc-mcp-auth

Option B: From source

git clone https://github.com/bykreth/gsc-mcp-server.git
cd gsc-mcp-server
npm install

cp .env.example .env
# Edit .env with your credentials, then:
export $(grep -v '^#' .env | xargs)
npm run auth

The auth flow opens a browser on port 3336. Sign in with the Google account that has Search Console access. Tokens are saved to ~/.config/gsc-mcp/tokens.json by default (override with GSC_TOKEN_PATH).

MCP client configuration

Cursor

Add to ~/.cursor/mcp.json (merge with existing servers):

{
  "mcpServers": {
    "google-search-console": {
      "command": "npx",
      "args": ["-y", "gsc-mcp-server"],
      "env": {
        "GOOGLE_CLIENT_ID": "YOUR_CLIENT_ID",
        "GOOGLE_CLIENT_SECRET": "YOUR_CLIENT_SECRET",
        "GSC_TOKEN_PATH": "/Users/you/.config/gsc-mcp/tokens.json"
      }
    }
  }
}

For local development, point command at Node directly:

{
  "mcpServers": {
    "google-search-console": {
      "command": "node",
      "args": ["/absolute/path/to/gsc-mcp-server/src/index.js"],
      "env": {
        "GOOGLE_CLIENT_ID": "YOUR_CLIENT_ID",
        "GOOGLE_CLIENT_SECRET": "YOUR_CLIENT_SECRET"
      }
    }
  }
}

See examples/cursor-mcp.json.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json on macOS (see examples/claude-desktop.json).

After changing MCP config, fully quit and restart your client so the server reloads tokens.

Example prompts

Once connected, you can ask your AI assistant:

• "List my Search Console properties"

• "What are the top 20 queries by clicks for https://example.com/ in the last 28 days?"

• "Show me pages with the most impressions last week"

• "Is https://example.com/blog/my-post indexed?"

Environment variables

Troubleshooting

Related MCP servers

• Google Analytics MCP — official GA4 server

• DataForSEO MCP — official DataForSEO server

License

MIT