Serper MCP Server

Serper MCP Server supporting search and webpage scraping

Local serverstdioTypeScript

What is the Serper MCP server?

Serper MCP server exists for a simple reason — assistants are far more useful when they can act on Serper directly instead of describing what you should do. Serper MCP Server supporting search and webpage scraping.

What you get

A TypeScript-based MCP server that provides web search and webpage scraping capabilities using the Serper API. This server integrates with Claude Desktop to enable powerful web search and content extraction features.

Setting it up

Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What the assistant can call

Once Serper is connected, these are the calls the assistant has available:

  • google_search — Perform web searches via Serper API
  • site — Limit results to specific domain
  • filetype — Limit to specific file types (e.g., 'pdf', 'doc')
  • inurl — Search for pages with word in URL
  • intitle — Search for pages with word in 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
  • scrape — Extract content from web pages

Configuration and credentials

You will need one environment variable: SERPER_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Node.js >= 18 - Serper API key (set as SERPER_API_KEY environment variable)

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Serper.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the serper mcp server does with a few real requests.

Choosing this one

Among the search and retrieval options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Serper's toolset — google_search, site, filetype and 11 more — is a fair guide to whether it matches your workflow. It is maintained by tahaswx; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
google_searchPerform web searches via Serper API
siteLimit results to specific domain
filetypeLimit to specific file types (e.g., 'pdf', 'doc')
inurlSearch for pages with word in URL
intitleSearch for pages with word in title
relatedFind similar websites
cacheView Google's cached version of a specific URL
beforeDate before in YYYY-MM-DD format
afterDate after in YYYY-MM-DD format
exactExact phrase match
excludeTerms to exclude from search results
scrapeExtract content from web pages
ToolsThe Tools tool exposed by this server.
DebuggingSince MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:

How to install the Serper MCP server

{
  "mcpServers": {
    "server-serper": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "SERPER_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js >= 18 - Serper API key (set as SERPER_API_KEY environment variable)
VariableDescriptionRequired
SERPER_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Serper to google search.
  • Use Serper to site.
  • Use Serper to filetype.

Frequently asked questions

It connects Serper to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (google_search, site, filetype, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Serper directly.