What it does

Wraps the Serper API for Google search results plus page scraping. It is the pragmatic route when you need actual SERP data and do not have Google's API access. Cost and terms are the constraints worth reading before building a workflow on it.

Install

Terminal

npx -y serper-search-scrape-mcp-server

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

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

Use it for

Google results as structured data when you cannot use the official API

Skip it if

High-volume scraping; you pay per query and the terms are strict

When to use it

Reach for this when the task needs search inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Serper MCP