Sandbox
@garylab/serper-mcp-server

MCP server for Google Search and scraping via Serper

This repo packages a Serper-backed MCP server that lets an agent query Google Search and related result types. It works by exposing named MCP tools such as `google_search`, `google_search_images`, `google_search_news`, and `webpage_scrape`, then returning the search data to the client.

38 stars15 forksPythonUpdated 10mo ago
Who it's for

Builders who want their agent to search the web, inspect pages, and use Google result types from one MCP server.

What it delivers

You can let your agent fetch search results and page content without leaving your MCP setup.

What it does

Search tools

Provides `google_search` for regular web search and special-purpose tools for images, videos, news, shopping, lenses, autocomplete, scholar, and patents.

Places, maps, and reviews

Includes `google_search_places`, `google_search_maps`, and `google_search_reviews` for local and location-based lookups.

Webpage scraping

Adds `webpage_scrape` so the agent can pull content from a page after finding it.

MCP client setup

Shows config examples for Claude Desktop and other MCP clients using `uvx`, `python3 -m`, or a pip install.

Debugging support

Documents how to run the server with the MCP inspector for local testing.

How to get it

  1. 1To install Serper MCP Server for Claude Desktop automatically via Smithery
    npx -y @smithery/cli install @garylab/serper-mcp-server --client claude
  2. 2Add serper-mcp-server to your MCP client code requirements.txt file.
    serper-mcp-server
  3. 3Install the dependencies.
    pip install -r requirements.txt
  4. 4Make sure the pip or pip3 is in your os system.
    pip install serper-mcp-server
    # or
    pip3 install serper-mcp-server

README

Serper MCP Server

PyPI version PyPI Downloads Monthly Downloads Python Version

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

Available Tools

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.

Files in the repo

Repository payload9 top-level entries
  • .github
  • src
  • .env.example
  • .gitignore
  • .python-version
  • Dockerfile
  • pyproject.toml
  • README.md
  • uv.lock

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k