Serper MCP Server

To add the server to Cursor:

1. Open Cursor settings.
2. Go to "Features" settings.
3. In the "MCP Servers" section, click "Add new MCP Server".
4. Set the name and choose "command" as the "Type".
5. Enter the following command in the "Command" field:

env SERPER_API_KEY=your_api_key_here npx -y serper-search-scrape-mcp-server

To use the server in the Cline extension:

1. Open Cline extension settings.
2. Open the "MCP Servers" tab.
3. Click "Configure MCP Servers".
4. Add the following configuration. You can use disabled to toggle the server and autoApprove to allow specific tools to run without explicit user permission.

{
  "mcpServers": {
    "github.com/marcopesani/mcp-server-serper": {
      "command": "npx",
      "args": ["-y", "serper-search-scrape-mcp-server"],
      "env": {
        "SERPER_API_KEY": "your_api_key_here"
      },
      "disabled": false,
      "autoApprove": ["google_search", "scrape"]
    }
  }
}

You can run the server using Docker.

Build the image:

docker build -t mcp-server-serper .

Run the container with an API key:

docker run -e SERPER_API_KEY=your_api_key_here mcp-server-serper

Run using a .env file:

docker run --env-file .env mcp-server-serper

Run for development (mounting source code):

docker run -v $(pwd):/app --env-file .env mcp-server-serper

To manually add the server to Claude Desktop, edit your configuration file:

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

Add the following configuration object to the mcpServers section:

{
  "mcpServers": {
    "serper-search": {
      "command": "npx",
      "args": ["-y", "serper-search-scrape-mcp-server"],
      "env": {
        "SERPER_API_KEY": "your_api_key_here"
      }
    }
  }
}

To use this server, you must meet the following requirements:

• Node.js: Version 18 or higher.
• Serper API Key: You must obtain a key from Serper and provide it via the SERPER_API_KEY environment variable.

You can automatically install the server for Claude Desktop using the Smithery CLI:

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

Since MCP servers communicate over stdio, debugging can be difficult. Use the MCP Inspector to debug in your browser by running:

npm run inspector

The server provides two primary tools:

1. google_search: Performs web searches via the Serper API. It returns rich results including organic results, knowledge graph, "people also ask", and related searches. It supports region/language targeting and advanced search operators.

2. scrape: Extracts content from a specific URL. It provides plain text and optional markdown content, including JSON-LD and head metadata, while preserving document structure.

The google_search tool supports the following advanced search operators to refine results:

• site: Limit results to a specific domain
• filetype: Limit to specific file types (e.g., 'pdf', 'doc')
• inurl: Search for pages with a specific word in the URL
• intitle: Search for pages with a specific word in the title
• related: Find similar websites
• cache: View Google's cached version of a specific URL
• before: Date before in YYYY-MM-DD format
• after: Date after in YYYY-MM-DD format
• exact: Exact phrase match
• exclude: Terms to exclude from search results
• or: Alternative terms (OR operator)

Call listPrompts() on a SerperPrompts instance to retrieve a list of all available prompt templates. Each prompt object includes a name, a description, and an optional array of arguments that define what inputs the prompt expects.

const { prompts } = await serperPrompts.listPrompts();