M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
G

Google Search Console MCP Server

Community
Comprehensive access to Google Search Console via MCP, with advanced analytics and quick win detection.
How to install ↓ Compare GitHub source repository ↗
Category
Cloud Storage #1 of 15
Stars
★ 277 Popular
Transport
stdio (local process)
Runtime
Node.js 18+
Credentials
API key / credential required
Last commit
Tools
1
69FMRS · C

Based on the feature list in the README, the server appears feature-rich, but the source provides no user reviews or usage experience. As a third-party project, use with caution and ensure key security.

Strongest · Maintenance 15/20 Weakest · Reliability 11/20

Reliability
11/20
Security and permissions
15/20
Maintenance
15/20
Documentation
14/20
Setup experience
14/20
Why each score
Reliability 11/20
Based on the README, the server claims to provide enhanced search analytics and quick wins detection with detailed tool parameters. However, since this is a static review and no tests or CI are run, the actual behavior cannot be verified. The source code lacks evidence of tests and clear error handling, limiting the reliability score. Given the lack of verifiable execution evidence, the score is capped at 12 per calibration rules.
Security and permissions 15/20
The server uses Google service account credentials passed via the GOOGLE_APPLICATION_CREDENTIALS environment variable, which is a standard and relatively secure practice. No signs of malicious code or credential theft were found. However, the filter parameters and quick wins detection may involve complex logic that requires careful data boundary handling. There are no clear risks, but least privilege principles are not fully verified, so the score is not perfect.
Maintenance 15/20
The repository shows signs of activity with 256 stars, 1 open issue, and not archived. The README provides an MIT license, which is good. However, concrete evidence of commit history and release versions is not visible in the static analysis, so the maintenance score is moderately high.
Documentation 14/20
The README provides installation, authentication, usage examples, and tool parameter descriptions covering the main features. However, it lacks troubleshooting sections and more in-depth limitation disclosures. Overall, the documentation is readable but has room for improvement, hence a score of 14.
Setup experience 14/20
The installation steps are clear, including npm installation and Claude Desktop configuration examples. Prerequisites are explicit but require users to create Google Cloud projects and service accounts, adding complexity. Since this is a static review, the actual configuration cannot be tested, but the documentation provides sufficient guidance. Per calibration rules, the score is capped at 15, and I assign a 14.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • SEO professionals
  • Content marketers
  • Website owners
  • Developers integrating Search Console data into their applications or workflows.

Not for

  • Users without a Google Cloud project or Search Console access.
  • Those needing real-time data (default is final data, but 'all' option exists).
  • Non-technical users may find setup challenging due to required Google Cloud configuration.

Required permissions

  • Requires a Google Cloud service account key with access to the Search Console API.
  • The service account must be granted property administrator rights in Search Console.
  • The server reads the key via environment variable, typically for external services.

Risks and side effects

  • Credential leak risk: If the service account key is not stored securely, data may be exposed. Use secret management services.
  • Data access scope: The service account can access all authorized Search Console properties, including sensitive performance data.
  • This is a third-party project, not an official Google server, and may not have undergone security auditing. Evaluate trustworthiness before use.
  • Potential Google Cloud API costs, though Search Console API is usually free within quotas.

Setup

Before you start

Runtime：Node.js 18+

GOOGLE_APPLICATION_CREDENTIALS requiredsecret Local path to a Google Cloud service account JSON key; create the service account in Google Cloud Console and add its email as a Search Console property administrator.
  1. In Google Cloud Console, create a project and enable the Search Console API.
  2. Create a service account and generate a JSON key file.
  3. In Search Console, add the service account email as a property administrator.
  4. Install the npm package: npm install mcp-server-gsc
  5. Configure your client (e.g., Claude Desktop) to run the server with npx and set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the JSON key file path.
claude_desktop_config.json 
{
  "mcpServers": {
    "gsc": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-gsc"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/credentials.json"
      }
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "gsc": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-gsc"
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/path/to/credentials.json"
      }
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add gsc -e GOOGLE_APPLICATION_CREDENTIALS=/path/to/credentials.json -- npx -y mcp-server-gsc

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

The search_analytics tool should appear in the client's tool list; running a query against an authorized site confirms the connection works.

Troubleshooting

  1. Ensure the service account is added to Search Console and has permissions.
  2. Check that the JSON key file path is correct and the service account is enabled.
  3. Make sure the Search Console API is enabled.
  4. Verify date format is YYYY-MM-DD.
  5. If you encounter permission errors, confirm the service account email is added as a property administrator.

Things to try

Once connected, you can ask your AI assistant things like:

  • Show search analytics for example.com for January 2024 grouped by query and page, 5000 rows
  • Find quick wins on example.com with positions 4-15, at least 500 impressions and CTR above 2%
  • Search queries on example.com matching regex (AI|machine learning|ML) on MOBILE devices

Tools 1

search_analytics read-only
Fetches search performance data from Google Search Console, supporting advanced filtering, dimension grouping, and quick wins detection.

Use cases

Analyze website search performance including clicks, impressions, CTR, and average position.
Segment data by query, page, country, device, and search appearance.
Identify optimization opportunities (quick wins) by setting thresholds for position, impressions, and CTR.
Apply advanced filters using regex, e.g., to include or exclude specific query patterns.

Supported clients

Claude Desktop

Listed from the project's documentation, not tested by this site.

Overview

This is a Model Context Protocol (MCP) server that provides access to Google Search Console data. It offers enhanced analytics capabilities such as retrieving up to 25,000 rows of performance data, advanced filtering including regex patterns, quick wins detection, and rich dimensions like query, page, country, device, and search appearance.

Similar servers

Compare with other MCP servers

Source revision e428b20549a0 Data synced 2026-10-12 Read the FMRS scoring method