Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

duckduckgo-web-search

MCP.Pizza Chef: Sunwood-ai-labs

The duckduckgo-web-search MCP Server is a TypeScript-based server that integrates DuckDuckGo's web search capabilities into the Claude Desktop environment. It provides a simple, privacy-focused web search implementation by leveraging the DuckDuckGo API. This server exposes structured search results as resources accessible via MCP, allowing models to query and retrieve real-time web data securely and efficiently. It supports core MCP concepts such as resource management, tool invocation, and prompt generation, enabling advanced workflows like creating notes from search results and summarizing collected information. The server is easy to install and develop with, featuring commands for building and live-reloading during development.

Use This MCP server To

Integrate real-time DuckDuckGo search results into AI workflows Enable LLMs to perform privacy-focused web searches Retrieve and structure web search data for analysis Create notes from web search results within MCP environment Summarize aggregated web search content using LLM prompts

README

duckduckgo-web-search MCP Server

duckduckgo-web-search

This is a TypeScript-based MCP server that implements a simple notes system. It demonstrates core MCP concepts by providing:

  • Resources representing text notes with URIs and metadata
  • Tools for creating new notes
  • Prompts for generating summaries of notes

Features

Resources

  • List and access notes via note:// URIs
  • Each note has a title, content and metadata
  • Plain text mime type for simple content access

Tools

  • create_note - Create new text notes
    • Takes title and content as required parameters
    • Stores note in server state

Prompts

  • summarize_notes - Generate a summary of all stored notes
    • Includes all note contents as embedded resources
    • Returns structured prompt for LLM summarization

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "duckduckgo-web-search": {
      "command": "/path/to/duckduckgo-web-search/build/index.js"
    }
  }
}

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

duckduckgo-web-search FAQ

How do I install the duckduckgo-web-search MCP server?
Install dependencies with 'npm install', then build the server using 'npm run build'. For development, use 'npm run watch' for auto-rebuild.
Can I use this server with LLMs other than Claude?
Yes, while designed for Claude Desktop, the server can be integrated with other LLMs like OpenAI's GPT-4 and Anthropic's Claude via MCP.
How does the server handle privacy in web searches?
It uses DuckDuckGo's API, which emphasizes user privacy by not tracking searches or storing personal data.
What types of resources does the server expose?
It exposes web search results as structured resources accessible via MCP URIs, enabling models to query and manipulate search data.
Can I extend the server with custom tools or prompts?
Yes, the server architecture supports adding new tools and prompts to enhance functionality, such as note creation and summarization.
Is the server written in a specific programming language?
Yes, it is implemented in TypeScript, facilitating easy development and integration in modern JavaScript environments.
How do I contribute to the development of this MCP server?
You can fork the GitHub repository, make changes, and submit pull requests. Use the provided build and watch scripts for development.