MCP Directory

Web Search MCP Server

Free web search via Google results scraping — no API keys required.

Unverified
stdio (local)
No auth
Stale
JavaScript
View repo 452

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run
npm install && npm run build

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "web-search-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/web-search/build/index.js"
      ]
    }
  }
}

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

  • Node.js (to run the built server with `node`)
  • Clone or download the repository, then run `npm install` and `npm run build`

About Web Search MCP Server

Web Search MCP Server lets an MCP client perform free web searches using Google search results without any API key or authentication. It provides one tool, search, which returns structured results (title, URL, description) for a query, with a configurable result limit (default 5, max 10). The server runs locally over stdio and is built from source with npm.

Tools & capabilities (1)

search

Performs a web search using Google search results. Accepts `query` (string, the search query) and optional `limit` (number, results to return — default 5, max 10). Returns an array of results, each with `title`, `url`, and `description`.

What this server can do

Web Search MCP Server provides tools for these capabilities — tap one to see every MCP server that does the same:

Search the web

When to use it

  • Give an AI assistant free web search without signing up for a paid search API
  • Fetch current web results (titles, URLs, descriptions) to ground answers
  • Look up references or sources for a query directly from a Claude/Cursor/VSCode client

Security notes

Works by scraping Google search result HTML. Google may temporarily block requests if too many searches are performed in a short time; keep search frequency reasonable and consider adding delays. The parser depends on Google's HTML structure and may break if it changes. Intended for personal use only — respect Google's terms of service.

Web Search MCP Server FAQ

Do I need an API key?

No. The server uses free Google search results and requires no API keys or authentication.

How many results can I get per search?

Use the optional `limit` parameter. The default is 5 results and the maximum is 10.

Why might searches fail or return incomplete data?

It scrapes Google's HTML, so Google may rate-limit requests if too many run quickly, and changes to Google's HTML structure can cause missing descriptions or other parsing issues. Keep searches to a reasonable frequency.

#web-search#google#search#no-api-key#scraping

Alternatives to Web Search MCP Server

Compare all alternatives →
Fetch (Reference)
Search & Web
87k

Official MCP reference server that fetches a URL and returns its content as clean Markdown, with chunking.

Verified
stdio (local)
No auth
Python
2 tools
Updated 13 days agoRepo
Firecrawl
Search & Web
6.6k

Official Firecrawl MCP server — scrape, crawl, map, search, and structured extraction for any LLM client.

Verified
stdio (local)
API key
TypeScript
8 tools
Updated 11 days agoRepo
Exa Search
Search & Web
4.6k

Exa's neural web search and crawling MCP server — runs locally via npx or as a hosted remote endpoint.

Verified
stdio (local)
API key
TypeScript
6 tools
Updated 12 days agoRepo

Compare Web Search MCP Server with:

vs Fetch (Reference)vs Firecrawlvs Exa Searchvs Perplexity