DuckDuckGo Search

Provides DuckDuckGo-powered web search via SerpAPI for rich, region-aware results.
  • typescript

3

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "spences10-mcp-duckduckgo-search": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-duckduckgo-search"
      ],
      "env": {
        "SERPAPI_KEY": "your-serpapi-api-key"
      }
    }
  }
}

You can extend your LLM capabilities with this MCP Server that lets you perform comprehensive web searches using DuckDuckGo via SerpAPI. It returns rich results such as knowledge panels, organic results, news, videos, images, and related queries, with options to filter by region, date, and safety level. This makes it easy to surface up-to-date web information inside your AI workflows.

How to use

You connect to the DuckDuckGo search MCP by configuring your MCP client to launch the local server. Once connected, you invoke the tool to perform web searches and fetch diverse result types for your prompts. You can tailor searches by region, safety level, and date range, then paginate through results as needed. Use it to enrich responses with timely web data, multimedia results, and related searches.

How to install

Prerequisites: Node.js and npm or an environment that can run npx and wsl.exe if you are using Windows Subsystem for Linux.

# Install dependencies and prepare the MCP tool (example flow)
pnpm install -g pnpm
pnpm install
pnpm build

Configuration

Configure your MCP client to run the DuckDuckGo search server using one of the provided runtime options. Both configurations assume you have a SerpAPI key ready as SERPAPI_KEY.

{
  "mcpServers": {
    "duckduckgo_search": {
      "command": "npx",
      "args": ["-y", "mcp-duckduckgo-search"],
      "env": {
        "SERPAPI_KEY": "your-serpapi-api-key"
      }
    }
  }
}

Additional configuration examples

If you are running in a WSL environment (Windows), you can start the server via a shell command that sets the key inline and uses npx to run the MCP tool.

{
  "mcpServers": {
    "duckduckgo_search": {
      "command": "wsl.exe",
      "args": [
        "bash",
        "-c",
        "source ~/.nvm/nvm.sh && SERPAPI_KEY=your-serpapi-api-key /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-duckduckgo-search"
      ]
    }
  }
}

API and capabilities

This MCP tool exposes a single capability to perform web searches. You can customize the search with region, safe_search, and date_filter parameters, and you can request different result types like knowledge graphs, organic results, news, videos, images, and related searches.

Available tools

ddg_search

Perform a web search using the DuckDuckGo engine through SerpAPI. Returns knowledge graph data, organic results, news, videos, images, related searches, and metadata with options for region, safe search, date filtering, and pagination.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational