Serper MCP Server

Serper MCP Server

What is Serper MCP Server about?

Serper MCP Server enables large language models to perform Google searches, retrieve images, videos, news, shopping results, maps data, reviews, and more by exposing the Serper API as a set of MCP tools.

How to use Serper MCP Server?

1. Install the server (recommended via uv or pip, or using Smithery).
2. Configure an MCP client (e.g., Claude Desktop) with the server name serper and provide your Serper API key.
3. Call the desired tool (e.g., google_search, google_search_images, webpage_scrape) from the LLM prompt.

Installation examples:

• Smithery: npx -y @smithery/cli install @garylab/serper-mcp-server --client claude
• uv: add to claude_desktop_config.json:

{
  "mcpServers": {
    "serper": {
      "command": "uvx",
      "args": ["serper-mcp-server"],
      "env": { "SERPER_API_KEY": "<Your Serper API key>" }
    }
  }
}

• pip (project): add serper-mcp-server to requirements.txt then configure:

{
  "mcpServers": {
    "serper": {
      "command": "python3",
      "args": ["-m", "serper_mcp_server"],
      "env": { "SERPER_API_KEY": "<Your Serper API key>" }
    }
  }
}

Key features of Serper MCP Server

• Multiple specialized tools: normal web search, image, video, news, shopping, maps, reviews, scholar, places, lens, autocomplete, and webpage scraping.
• Full parameter control for each tool via JSON schemas.
• Easy installation through uv, pip, or Smithery.
• MIT‑licensed, lightweight Python package.
• Debuggable with the MCP inspector.

Use cases of Serper MCP Server

• Augmenting LLM agents with up‑to‑date web information.
• Building research assistants that fetch scholarly articles or news.
• Creating shopping comparison bots.
• Generating location‑based answers using maps and places data.
• Extracting content from arbitrary webpages for summarization.

FAQ from the Serper MCP Server

Q: Do I need a Serper account? A: Yes, a valid Serper API key is required and must be set in the SERPER_API_KEY environment variable.

Q: Which command should I use for the MCP server? A: The server works with uvx, python -m, or npx. The uv workflow is recommended for automatic dependency handling.

Q: Can I debug the server? A: Yes, use the MCP inspector, e.g., npx @modelcontextprotocol/inspector uvx serper-mcp-server.

Q: Is the server cross‑platform? A: It runs wherever Python (or uv) is available, including Windows, macOS, and Linux.

Q: What license governs the project? A: The project is released under the MIT License.

Serper MCP Server

A Model Context Protocol server that provides Google Search via Serper. This server enables LLMs to get search result information from Google.

Available Tools

• google_search - Set all the parameters
• google_search_images - Set all the parameters
• google_search_videos - Set all the parameters
• google_search_places - Set all the parameters
• google_search_maps - Set all the parameters
• google_search_reviews - Set all the parameters
• google_search_news - Set all the parameters
• google_search_shopping - Set all the parameters
• google_search_lens - Set all the parameters
• google_search_scholar - Set all the parameters
• google_search_parents - Set all the parameters
• google_search_autocomplete - Set all the parameters
• webpage_scrape - Set all the parameters

Usage

Installing via Smithery

To install Serper MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @garylab/serper-mcp-server --client claude

Using uv (recommended)

1. Make sure you had installed uv on your os system.

2. In your MCP client code configuration or Claude settings (file claude_desktop_config.json) add serper mcp server:

   {
       "mcpServers": {
           "serper": {
               "command": "uvx",
               "args": ["serper-mcp-server"],
               "env": {
                   "SERPER_API_KEY": "<Your Serper API key>"
               }
           }
       }
   }
   

   uv will download mcp server automatically using uvx from pypi.org and apply to your MCP client.

Using pip for project

1. Add serper-mcp-server to your MCP client code requirements.txt file.

   serper-mcp-server
   

2. Install the dependencies.

   pip install -r requirements.txt
   

3. Add the configuration for you client:

   {
       "mcpServers": {
           "serper": {
               "command": "python3",
               "args": ["-m", "serper_mcp_server"],
               "env": {
                   "SERPER_API_KEY": "<Your Serper API key>"
               }
           }
       }
   }
   

Using pip for globally usage

1. Make sure the pip or pip3 is in your os system.

   pip install serper-mcp-server
   # or
   pip3 install serper-mcp-server
   

2. MCP client code configuration or Claude settings, add serper mcp server:

   {
       "mcpServers": {
           "serper": {
               "command": "python3",
               "args": ["serper-mcp-server"],
               "env": {
                   "SERPER_API_KEY": "<Your Serper API key>"
               }
           }
       }
   }
   

Debugging

You can use the MCP inspector to debug the server. For uvx installations:

npx @modelcontextprotocol/inspector uvx serper-mcp-server

Or if you've installed the package in a specific directory or are developing on it:

git clone https://github.com/garylab/serper-mcp-server.git
cd serper-mcp-server
npx @modelcontextprotocol/inspector uv run serper-mcp-server -e SERPER_API_KEY=<the key>

License

serper-mcp-server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.