Skip to main content
Glama
ShogoOkamoto

Google Search MCP

by ShogoOkamoto
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

google-search-mcp

A Model Context Protocol (MCP) server that utilizes Google Custom Search (CSE) to retrieve information from the internet. By leveraging this MCP, the Large Language Model (LLM) is enabled to perform real-time Web searches.

Prerequisites

A Google Custom Search API key and Custom Search Engine ID are required:

  1. Get a Google API Key from the Google Cloud Console

  2. Create a Custom Search Engine at Programmable Search Engine

Related MCP server: Google Search MCP Server

Installation

pip install google-search-mcp

Or install from source:

pip install .

Configuration

Create a .env file in the project root directory:

cp .env.example .env

Then edit the .env file and add your credentials:

GOOGLE_API_KEY=your-api-key
GOOGLE_CSE_ID=your-custom-search-engine-id

Alternatively, you can set environment variables directly:

export GOOGLE_API_KEY="your-api-key"
export GOOGLE_CSE_ID="your-custom-search-engine-id"

Usage

As a CLI

google-search-mcp

With Claude Desktop

Add the following to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

For macOS/Linux:

{
  "mcpServers": {
    "google-search": {
      "command": "python",
      "args": ["-m", "google_search_mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-api-key",
        "GOOGLE_CSE_ID": "your-custom-search-engine-id"
      }
    }
  }
}

For Windows:

If python is in your PATH (check with where python), you can use the same configuration as macOS/Linux:

{
  "mcpServers": {
    "google-search": {
      "command": "python",
      "args": ["-m", "google_search_mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-api-key",
        "GOOGLE_CSE_ID": "your-custom-search-engine-id"
      }
    }
  }
}

If you need to use a specific Python installation, find the full path with:

python -c "import sys; print(sys.executable)"

Then use the full path in the configuration:

{
  "mcpServers": {
    "google-search": {
      "command": "C:\\Users\\YOUR_USERNAME\\AppData\\Local\\Microsoft\\WindowsApps\\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\\python.exe",
      "args": ["-m", "google_search_mcp"],
      "env": {
        "GOOGLE_API_KEY": "your-api-key",
        "GOOGLE_CSE_ID": "your-custom-search-engine-id"
      }
    }
  }
}

Note: Environment variables must be set in the Claude Desktop config env section for the server to access them.

Tools

search

Search the web using Google Custom Search.

Parameters:

  • query (string, required): The search query string

  • num_results (integer, optional): Number of results to return (1-10, default 10)

Development

Running Tests

Install development dependencies:

pip install -e ".[dev]"

Run the test suite:

pytest

Run tests with verbose output:

pytest -v

Run tests with coverage:

pytest --cov=google_search_mcp --cov-report=html

Test Coverage

The test suite includes comprehensive tests for:

  • Successful search requests

  • Environment variable validation

  • API error handling

  • JSON parsing errors

  • Empty search results

  • Input parameter validation (num_results clamping)

  • Result formatting

  • Request parameter verification

License

MIT License - see LICENSE for details.

Available Tools

1 tool

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedsearch
Deploy Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.3/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined as web searching, leaving no room for confusion or misselection.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'search' is straightforward and follows a simple verb pattern appropriate for its function.

Tool Count2/5

A single tool is too few for a server named 'Google Search MCP', which suggests a broader scope. While the tool covers basic search functionality, the server lacks additional operations like advanced search filters, image search, or news search, making it feel thin and underdeveloped for its apparent purpose.

Completeness2/5

The tool surface is severely incomplete for a Google Search domain. It only provides basic text search, missing essential features such as image search, video search, news search, or advanced query options. This creates significant gaps that will limit agent capabilities and lead to failures in handling diverse search-related tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Perplexity MCP Server

    jaacob
    A
    license
    B
    quality
    D
    maintenance
    Facilitates web search capabilities using Perplexity's API, allowing users to retrieve search results through Claude's interface.
    1
    8
    MIT

  • Google Search MCP Server

    renoscriptdev
    A
    license
    Not graded
    quality
    D
    maintenance
    A Model Context Protocol server that enables Claude to perform Google Custom Search operations by connecting to Google's search API.
    2
    MIT

  • Web Search MCP Server

    Mantraa-Zzz
    F
    license
    B
    quality
    D
    maintenance
    Enables web searching and content scraping through Google Custom Search API. Provides tools to search the internet, extract webpage content, and automatically scrape search results for comprehensive information gathering.
    3
    -