Advertise
MCP.so
Sign In

MCP Web Search Crawler

@tomas-hanzlik

Repository

Basic information

Category

Search

Transports

stdio

Author

tomas-hanzlik

About MCP Web Search Crawler

A lightweight MCP server for web searching via DuckDuckGo and extracting page content as Markdown.

#mcp#web-crawler#duckduckgo

MCP Web Search Crawler config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-web-search-crawl": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/tomas-hanzlik/mcp-web-search-crawl",
        "mcpsearchcrawl"
      ]
    }
  }
}

MCP Web Search Crawler tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Web Search Crawler?

MCP Web Search Crawler is a Model Context Protocol server that provides web search and crawling capabilities. It enables AI assistants and other MCP clients to search the web using DuckDuckGo and crawl specific URLs to extract content in markdown format.

How to use MCP Web Search Crawler?

Clone the repository, then configure the server in your MCP client using the uv command with a directory argument, or use uvx from the GitHub repository. It exposes a tool called search_links that accepts a query parameter. The server can be run with --transport sse or --transport stdio.

Key features of MCP Web Search Crawler

  • Web Search via DuckDuckGo returning links, titles, and body snippets
  • URL crawling returning content as markdown
  • Configurable via MCP client JSON
  • Programmatic testing with Python client (fastmcp)
  • Supports SSE and stdio transports

Use cases of MCP Web Search Crawler

  • AI assistants searching the web for current information
  • Crawling specific web pages to extract markdown content
  • Combining search and crawl for research tasks
  • Integrating with MCP-compatible clients for automated web data retrieval

Frequently asked questions

1

What dependencies are required?

Requires `uv` and Python. The server uses DuckDuckGo as its search backend and does not need API keys.

2

How do I test the server programmatically?

Use the provided Python script with the `fastmcp` Client, then call tools like `search_links` with a query parameter.

3

What transport options are available?

The server supports SSE and stdio transports. Run it with `--transport sse` or `--transport stdio`.

4

How can I debug the server?

Use MCP Inspector with the command: `uv run fastmcp dev src/mcp_web_search_crawl/server.py:mcp --with-editable .`

Comments

More Search MCP servers

Alien Probe who

bbrysonelite-max

MCP server: resolve a company name, domain or LEI to its GLEIF legal entity for $0.05 via x402 — one tool, spend caps, free terms preview

Fitralo

Fitralo

Search Europe's road freight carriers from your AI assistant: find carriers by route, equipment and certificates among 15,700+ checked carriers in 32 countries, in 14 languages. Read-only, no account needed for searching

patent-literature-search-mcp

patsnap

A professional tool for searching Patsnap’s global patent and literature databases using natural language, semantic, or keyword queries. It supports precise filtering and retrieves bibliographic data in Markdown format.

1

CUQU找搭子 MCP（粗趣）

cuqu-net

CUQU找搭子官方 Agent Skill：让任意 AI Agent（Claude Code/Codex/Cursor/WorkBuddy）代用户找同城线下局、报名、支付、发局。MCP Streamable HTTP + 个人 API Key 网关 agent.cuqu.net

Aguasto Research

Aguasto

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

Advertise