MCP Serp

Official

by AceDataCloud · Python

MCP server for Google search results via SERP API

Retrieves Google search results via SERP API.

Topics

google-searchmcp-servermodel-context-protocolweb-searchdeveloper-toolsserp-api

README.md15 KBView on GitHub

SerpMCP

A Model Context Protocol (MCP) server for Google search using SERP API through the AceDataCloud API.

Perform Google searches and get structured results directly from Claude, VS Code, or any MCP-compatible client.

Features

Web Search - Regular Google web search with structured results
Image Search - Search for images with URLs and thumbnails
News Search - Get latest news articles on any topic
Video Search - Find videos from YouTube and other sources
Places Search - Search for local businesses and places
Maps Search - Find locations and geographic information
Knowledge Graph - Get structured entity information
Localization - Support for multiple countries and languages
Time Filtering - Filter results by time range

Tool Reference

Tool	Description
`serp_google_search`	Search Google and get structured results using the SERP API.
`serp_google_images`	Search Google Images and get image results.
`serp_google_news`	Search Google News and get news article results.
`serp_google_videos`	Search Google Videos and get video results.
`serp_google_places`	Search Google for local places and businesses.
`serp_google_maps`	Search Google Maps for locations.
`serp_list_search_types`	List all available Google search types.
`serp_list_countries`	List commonly used country codes for Google search.
`serp_list_languages`	List commonly used language codes for Google search.
`serp_list_time_ranges`	List available time range filters for Google search.
`serp_get_usage_guide`	Get a comprehensive guide for using the Google SERP tools.

Quick Start

1. Get Your API Token

Sign up at AceDataCloud Platform
Go to the API documentation page
Click "Acquire" to get your API token
Copy the token for use below

2. Use the Hosted Server (Recommended)

AceDataCloud hosts a managed MCP server — no local installation required.

Endpoint: https://serp.mcp.acedata.cloud/mcp

All requests require a Bearer token. Use the API token from Step 1.

Claude.ai

Connect directly on Claude.ai with OAuth — no API token needed:

Go to Claude.ai Settings → Integrations → Add More
Enter the server URL: https://serp.mcp.acedata.cloud/mcp
Complete the OAuth login flow
Start using the tools in your conversation

Claude Desktop

Add to your config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

json

{
  "mcpServers": {
    "serp": {
      "type": "streamable-http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cursor / Windsurf

Add to your MCP config (.cursor/mcp.json or .windsurf/mcp.json):

json

{
  "mcpServers": {
    "serp": {
      "type": "streamable-http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

VS Code (Copilot)

Add to your VS Code MCP config (.vscode/mcp.json):

json

{
  "servers": {
    "serp": {
      "type": "streamable-http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Or install the Ace Data Cloud MCP extension for VS Code, which registers the hosted MCP servers with one-click setup.

JetBrains IDEs

Go to Settings → Tools → AI Assistant → Model Context Protocol (MCP)
Click Add → HTTP
Paste:

json

{
  "mcpServers": {
    "serp": {
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Claude Code

Claude Code supports MCP servers natively:

bash

claude mcp add serp --transport http https://serp.mcp.acedata.cloud/mcp \
  -h "Authorization: Bearer YOUR_API_TOKEN"

Or add to your project's .mcp.json:

json

{
  "mcpServers": {
    "serp": {
      "type": "streamable-http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cline

Add to Cline's MCP settings (.cline/mcp_settings.json):

json

{
  "mcpServers": {
    "serp": {
      "type": "streamable-http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Amazon Q Developer

Add to your MCP configuration:

json

{
  "mcpServers": {
    "serp": {
      "type": "streamable-http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Roo Code

Add to Roo Code MCP settings:

json

{
  "mcpServers": {
    "serp": {
      "type": "streamable-http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Continue.dev

Add to .continue/config.yaml:

yaml

mcpServers:
  - name: serp
    type: streamable-http
    url: https://serp.mcp.acedata.cloud/mcp
    headers:
      Authorization: "Bearer YOUR_API_TOKEN"

Zed

Add to Zed's settings (~/.config/zed/settings.json):

json

{
  "language_models": {
    "mcp_servers": {
      "serp": {
        "url": "https://serp.mcp.acedata.cloud/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_TOKEN"
        }
      }
    }
  }
}

cURL Test

bash

# Health check (no auth required)
curl https://serp.mcp.acedata.cloud/health

# MCP initialize
curl -X POST https://serp.mcp.acedata.cloud/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

3. Or Run Locally (Alternative)

If you prefer to run the server on your own machine:

bash

# Install from PyPI
pip install mcp-serp
# or
uvx mcp-serp

# Set your API token
export ACEDATACLOUD_API_TOKEN="your_token_here"

# Run (stdio mode for Claude Desktop / local clients)
mcp-serp

# Run (HTTP mode for remote access)
mcp-serp --transport http --port 8000

Claude Desktop (Local)

json

{
  "mcpServers": {
    "serp": {
      "command": "uvx",
      "args": ["mcp-serp"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your_token_here"
      }
    }
  }
}

Docker (Self-Hosting)

bash

docker pull ghcr.io/acedatacloud/mcp-serp:latest
docker run -p 8000:8000 ghcr.io/acedatacloud/mcp-serp:latest

Clients connect with their own Bearer token — the server extracts the token from each request's Authorization header.

Available Tools

Search Tools

Tool	Description
`serp_google_search`	Flexible Google search with all options
`serp_google_images`	Search for images
`serp_google_news`	Search for news articles
`serp_google_videos`	Search for videos
`serp_google_places`	Search for local places/businesses
`serp_google_maps`	Search for map locations

Information Tools

Tool	Description
`serp_list_search_types`	List available search types
`serp_list_countries`	List country codes for localization
`serp_list_languages`	List language codes for localization
`serp_list_time_ranges`	List time range filter options
`serp_get_usage_guide`	Get comprehensive usage guide

Usage Examples

Basic Web Search

code

User: Search for information about artificial intelligence

Claude: I'll search for information about AI.
[Calls serp_google_search with query="artificial intelligence"]

News Search with Time Filter

code

User: What's the latest news about technology?

Claude: I'll search for recent tech news.
[Calls serp_google_news with query="technology", time_range="qdr:d"]

Localized Search

code

User: Find popular restaurants in Tokyo

Claude: I'll search for restaurants in Tokyo.
[Calls serp_google_places with query="popular restaurants Tokyo", country="jp"]

Image Search

code

User: Find images of the Northern Lights

Claude: I'll search for aurora borealis images.
[Calls serp_google_images with query="Northern Lights aurora borealis"]

Search Parameters

Search Types

Type	Description
`search`	Regular web search (default)
`images`	Image search
`news`	News articles
`maps`	Map results
`places`	Local businesses
`videos`	Video results

Time Range Filters

Code	Time Range
`qdr:h`	Past hour
`qdr:d`	Past day
`qdr:w`	Past week
`qdr:m`	Past month

Common Country Codes

Code	Country
`us`	United States
`uk`	United Kingdom
`cn`	China
`jp`	Japan
`de`	Germany
`fr`	France

Common Language Codes

Code	Language
`en`	English
`zh-cn`	Chinese (Simplified)
`ja`	Japanese
`es`	Spanish
`fr`	French
`de`	German

Response Structure

Regular Search Results

knowledge_graph: Entity information (company, person, etc.)
answer_box: Direct answers
organic: Regular search results with title, link, snippet
people_also_ask: Related questions
related_searches: Related queries

Image Search Results

images: Image results with URLs and thumbnails

News Search Results

news: News articles with source and date

Configuration

Environment Variables

Variable	Description	Default
`ACEDATACLOUD_API_TOKEN`	API token from AceDataCloud	Required
`ACEDATACLOUD_API_BASE_URL`	API base URL	`https://api.acedata.cloud`
`ACEDATACLOUD_OAUTH_CLIENT_ID`	OAuth client ID (hosted mode)	—
`ACEDATACLOUD_PLATFORM_BASE_URL`	Platform base URL	`https://platform.acedata.cloud`
`SERP_REQUEST_TIMEOUT`	Request timeout in seconds	`30`
`LOG_LEVEL`	Logging level	`INFO`

Command Line Options

bash

mcp-serp --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)

Development

Setup Development Environment

bash

# Clone repository
git clone https://github.com/AceDataCloud/SerpMCP.git
cd SerpMCP

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"

Run Tests

bash

# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest tests/test_integration.py -m integration

Code Quality

bash

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools

Build & Publish

bash

# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

Project Structure

code

SerpMCP/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for SERP API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   └── server.py          # MCP server initialization
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── search_tools.py    # Search tools
│   └── info_tools.py      # Information tools
├── prompts/                # MCP prompt templates
│   └── __init__.py
├── tests/                  # Test suite
│   ├── conftest.py
│   ├── test_client.py
│   └── test_config.py
├── deploy/                 # Deployment configs
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .env.example           # Environment template
├── .gitignore
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md

API Reference

This server wraps the AceDataCloud Google SERP API:

Google SERP API Documentation

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch (git checkout -b feature/amazing)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing)
Open a Pull Request

License

MIT License - see LICENSE for details.

Links

Made with love by AceDataCloud

Install

Configuration

Environment variables

ACEDATACLOUD_API_TOKENrequiredsecret

API token from Ace Data Cloud (https://platform.acedata.cloud)

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp-serp": {
      "command": "uvx",
      "args": [
        "mcp-serp"
      ],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "<YOUR_ACEDATACLOUD_API_TOKEN>"
      }
    }
  }
}