mcpField
D
duck-duck-scrape-mcp

duck-duck-scrape-mcp

Local
github.com/mmkalSearch1Updated 81w ago
Repository

About duck-duck-scrape-mcp

duck-duck-scrape-mcp is an MCP server that obtains web search results by scraping DuckDuckGo. It is intended for MCP clients that need search results; usage should follow DuckDuckGo's terms of service.

Key features

  1. 01DuckDuckGo web search
  2. 02Scrapes search results

Use cases

  1. 01Retrieve web search results through an MCP client
  2. 02Add search access to an MCP setup

MCP support

Exposes DuckDuckGo search results to MCP clients as a server. The README shows stdio configuration.

#duckduckgo#search#scraping

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "duck-duck-scrape": {
      "command": "npx",
      "args": [
        "-y",
        "github:mmkal/duck-duck-scrape-mcp"
      ]
    }
  }
}
Run commandnpx -y github:mmkal/duck-duck-scrape-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmgithub:mmkal/duck-duck-scrape-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

duck-duck-scrape-mcp

An MCP server for (free!) search results via duckduckgo

This is like the Brave search mcp server, but it's just scraping duckduckgo. Consult duckduckgo's tos before using.

How to use

It's not currently published to npm, so use the github: directive:

.mcp.json:

{
  "mcpServers": {
    "duckduckgo-web-search": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "github:mmkal/duck-duck-scrape-mcp"
      ]
    }
  }
}

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.