What are the dependencies for running SerpApi Mcp?
Python 3.13+, `uv`, and a valid SerpApi API key. For self‑hosting, clone the repository and run `uv sync && uv run src/server.py`.
@serpapi
基本信息
SerpApi MCP Server for Google and other search engine results
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"serpapi": {
"url": "https://mcp.serpapi.com/YOUR_SERPAPI_API_KEY/mcp"
}
}
}Universal search tool supporting all SerpApi engines and result types. This tool consolidates weather, stock, and general search functionality into a single interface. It processes multiple result types and returns structured JSON output. Args: params: Dictionary of engine-specific parameters. Common parameters include: - q: Search query (required for most engines) - engine: Search engine to use (default: "google_light") - location: Geographic location filter - num: Number of results to return mode: Response mode (default: "complete") - "complete": Returns full JSON response with all fields - "compact": Returns JSON response with metadata fields removed Returns: A JSON string containing search results or an error message. Examples: Weather: {"params": {"q": "weather in London", "engine": "google"}, "mode": "complete"} Stock: {"params": {"q": "AAPL stock", "engine": "google"}, "mode": "complete"} General: {"params": {"q": "coffee shops", "engine": "google_light", "location": "Austin, TX"}, "mode": "complete"} Compact: {"params": {"q": "news"}, "mode": "compact"} Supported engines: - google - google_light - google_flights - google_hotels - google_images - google_news - google_local - google_shopping - google_jobs - bing - yahoo - duckduckgo - youtube_search - baidu - ebay
SerpApi Mcp is a Model Context Protocol (MCP) server that integrates with SerpApi to provide search engine results and data extraction. It supports multiple search engines and returns structured JSON responses.
Configure Claude Desktop to use the hosted server at https://mcp.serpapi.com by providing your SerpApi API key in the URL path. For self-hosting, clone the repo, run uv sync && uv run src/server.py, then configure Claude Desktop to point to http://localhost:8000. The server exposes a single search tool that accepts parameters like q, engine, location, and mode.
Python 3.13+, `uv`, and a valid SerpApi API key. For self‑hosting, clone the repository and run `uv sync && uv run src/server.py`.
Two methods: path‑based (`/YOUR_API_KEY/mcp`) or header‑based (`Authorization: Bearer YOUR_API_KEY`). The hosted server at `mcp.serpapi.com` uses the same approach.
Streamable HTTP transport. When testing with the MCP Inspector, select “Streamable HTTP transport” and provide the URL with your API key.
Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and many more listed on the SerpApi search engine APIs page.
Wait before making additional requests or upgrade your SerpApi plan to increase your rate limit.

Search city council meetings, votes, and documents across U.S. cities, with citations to the official record.

Search 500,000+ active jobs worldwide, discover employers and explore remote, part-time and flexible work. Read full postings and open original application links for free. OAuth with scoped permissions; optional confirme

Free SEO Audit MCP server for Claude - captures and stores all the raw data you need for a complete technical SEO audit. Google Search Console + a first-party crawl + DataForSEO + Majestic SEO merged into one prioritised

Official read-only MCP access to Aguasto's public GPU, model and infrastructure research. Search published descriptions and retrieve canonical source links. Anonymous Streamable HTTP; GPU rental and token-based inference

Search papers on arXiv by research topic and exact announcement date, then read full-text paper briefs. An arXiv paper search and literature search tool for AI agents: search_papers returns titles, authors and abstracts
评论