mcpField
S
Serpapi

Serpapi

Remote
pipeworx.ioSearch0Updated 5w ago

About Serpapi

Serpapi wraps SerpApi search engines as an MCP server for users needing academic, maps, trends, jobs, news, or shopping results. Calls require the user's own SerpApi API key; it is available through the Pipeworx gateway or as a local stdio server.

Key features

  1. 01Google Scholar paper search
  2. 02Google Maps business search
  3. 03Google Trends interest data
  4. 04Google Jobs listings search
  5. 05Google News and Shopping search

Use cases

  1. 01Find papers and citation details
  2. 02Search local businesses and contact details
  3. 03Check keyword trends by region
  4. 04Find jobs, news, or products

MCP support

Exposes SerpApi academic, maps, trends, jobs, news, and shopping search tools to MCP clients. Calls require a user-provided SerpApi API key; the server can be reached through Pipeworx or run locally over stdio.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/serpapi/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-serpapi

SerpApi MCP — wraps SerpApi (serpapi.com) search engines

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolDescription
serpapi_google_scholarSearch Google Scholar for academic papers on <topic> — returns title, link, snippet, publication info, and citation count via SerpApi. Example: serpapi_google_scholar({ q: "graph neural networks", as_ylo: 2020, num: 10, _apiKey: "your-serpapi-key" })
serpapi_google_mapsFind local businesses on Google Maps for <query> — returns name, address, rating, reviews, phone, website, and GPS coordinates via SerpApi. Example: serpapi_google_maps({ q: "coffee shops", ll: "@40.7,-74.0,14z", _apiKey: "your-serpapi-key" })
serpapi_google_trendsGet Google Trends interest-over-time for <terms> — returns the requested trends block (interest over time, by region, or related queries) via SerpApi. Example: serpapi_google_trends({ q: "bitcoin,ethereum", date: "today 12-m", geo: "US", _apiKey: "your-serpapi-key" })
serpapi_google_jobsSearch Google Jobs for <query> — returns title, company, location, source, posted date, schedule, description, and apply link via SerpApi. Example: serpapi_google_jobs({ q: "data engineer", location: "Austin, TX", _apiKey: "your-serpapi-key" })
serpapi_google_newsSearch Google News for <query> — returns headline, source, link, date, and snippet via SerpApi. Example: serpapi_google_news({ q: "openai", gl: "us", hl: "en", _apiKey: "your-serpapi-key" })
serpapi_google_shoppingSearch Google Shopping for <query> — returns product title, price, source, rating, reviews, product ID, and link via SerpApi. Example: serpapi_google_shopping({ q: "wireless earbuds", gl: "us", hl: "en", _apiKey: "your-serpapi-key" })

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "serpapi": {
      "url": "https://gateway.pipeworx.io/serpapi/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/serpapi/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

This pack takes your own API key (_apiKey) — we don't front one for it, so there's no curl here that would run without it. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/serpapi_google_scholar. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "serpapi": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-serpapi"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-serpapi

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Serpapi data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.