Skip to main content
Glama
pgzhang

MCP Google Server

by pgzhang
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

mcp-google-server A MCP Server for Google Custom Search and Webpage Reading

A Model Context Protocol server that provides web search capabilities using Google Custom Search API and webpage content extraction functionality.

Setup

Getting Google API Key and Search Engine ID

  1. Create a Google Cloud Project:

    • Go to Google Cloud Console

    • Create a new project or select an existing one

    • Enable billing for your project

  2. Enable Custom Search API:

    • Go to API Library

    • Search for "Custom Search API"

    • Click "Enable"

  3. Get API Key:

    • Go to Credentials

    • Click "Create Credentials" > "API Key"

    • Copy your API key

    • (Optional) Restrict the API key to only Custom Search API

  4. Create Custom Search Engine:

    • Go to Programmable Search Engine

    • Enter the sites you want to search (use www.google.com for general web search)

    • Click "Create"

    • On the next page, click "Customize"

    • In the settings, enable "Search the entire web"

    • Copy your Search Engine ID (cx)

Related MCP server: MCP Server for Google Search

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Features

Search Tool

Perform web searches using Google Custom Search API:

  • Search the entire web or specific sites

  • Control number of results (1-10)

  • Get structured results with title, link, and snippet

Webpage Reader Tool

Extract content from any webpage:

  • Fetch and parse webpage content

  • Extract page title and main text

  • Clean content by removing scripts and styles

  • Return structured data with title, text, and URL

Installation

Installing via Smithery

To install Google Custom Search Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @adenot/mcp-google-search --client claude

To use with Claude Desktop, add the server config with your Google API credentials:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "google-search": {
      "command": "npx",
      "args": [
        "-y",
        "@adenot/mcp-google-search"
      ],
      "env": {
        "SMARTSEARCH_ENDPOINT": "your-endpoint-here",
        "SMARTSEARCH_AK": "your-ak-here"
      }
    }
  }
}

Usage

Search Tool

{
  "name": "search",
  "arguments": {
    "query": "your search query",
    "num": 5  // optional, default is 5, max is 10
  }
}

Webpage Reader Tool

{
  "name": "read_webpage",
  "arguments": {
    "url": "https://example.com"
  }
}

Example response from webpage reader:

{
  "title": "Example Domain",
  "text": "Extracted and cleaned webpage content...",
  "url": "https://example.com"
}

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Available Tools

2 tools
read_webpageA

Fetch and extract text content from a webpage

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesURL of the webpage to read

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must cover behavioral traits. It only states basic purpose without mentioning rate limits, authentication, dynamic content handling, or error responses.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with action, no unnecessary words. Perfectly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description is adequate but lacks details on handling of large pages, timeouts, or what 'text content' entails (e.g., stripping HTML).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (single 'url' parameter described), so baseline is 3. The description adds no extra meaning beyond the schema, such as URL format or protocol support.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action ('Fetch and extract') and the resource ('text content from a webpage'), distinguishing it from sibling tool 'search' which is for querying.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The sibling 'search' suggests a different purpose, but the description does not clarify contexts or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 2 tool updates
    • First observedread_webpage
    • First observedsearch
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: read_webpage fetches and extracts text from a specific URL, while search performs a web search query. There is no overlap or ambiguity between these functions, making it easy for an agent to select the appropriate tool.

Naming Consistency5/5

Both tools follow a consistent verb-based naming pattern (read_webpage, search) with clear, descriptive names. They use snake_case uniformly, and the verbs accurately reflect their actions without deviation.

Tool Count2/5

With only 2 tools, the server feels thin for a 'Google Server' domain, which typically involves broader functionality like email, calendar, or drive operations. While the tools are useful, the count is too low to adequately cover the implied scope, suggesting an incomplete or narrowly focused implementation.

Completeness2/5

Given the server name 'MCP Google Server', there are significant gaps in coverage, such as missing tools for Google services like Gmail, Calendar, Drive, or authentication. The current tools only handle web-related tasks, making the surface severely incomplete for the expected domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers