mcpField
D
DuckDuckGo MCP Server

DuckDuckGo MCP Server

Local
github.com/shgsousaSearch3Updated 73w ago
Repository

About DuckDuckGo MCP Server

DuckDuckGo MCP Server is a Python and Gradio web search app for people who need search results and page content in a browser or MCP client. It combines configurable result counts, Markdown page extraction, and optional AI summarization.

Key features

  1. 01DuckDuckGo web search
  2. 02Configurable result count
  3. 03Full page content extraction
  4. 04Markdown-formatted output
  5. 05Optional AI summarization

Use cases

  1. 01Search the web through a browser interface
  2. 02Retrieve page text for downstream use
  3. 03Summarize search content with an API

MCP support

It provides search and page-retrieval tools for MCP clients, including Claude Desktop integration.

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "ddg_mcp_server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "build"
      ]
    }
  }
}
Run commanddocker run -i --rm build

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
ocibuild

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

DuckDuckGo MCP Server

A web-based search interface using DuckDuckGo's search API, built with Python and Gradio.

Docker Setup

Prerequisites
  • Docker installed on your system
  • Git (optional, for cloning the repository)
Building the Docker Image
  1. Clone the repository (if you haven't already):
git clone <repository-url>
cd ddg_mcp_server
  1. Build the Docker image:
docker build -t ddg-mcp-server .
Running the Container

Run the container with port 7860 mapped to your host:

docker run -p 7860:7860 ddg-mcp-server

The application will be available at:

Troubleshooting

If you cannot connect to the application:

  1. Verify the container is running:
docker ps
  1. Check the container logs:
docker logs $(docker ps -q)
  1. Try stopping any existing containers and starting fresh:
docker stop $(docker ps -q)
docker run -p 7860:7860 ddg-mcp-server

Features

  • Web-based search interface using DuckDuckGo
  • Real-time search results with full content
  • Markdown-formatted output
  • Configurable number of results
  • AI-powered content summarization (see SUMMARIZATION.md for details)

Development

The application is built with:

  • Python 3.10
  • Gradio for the web interface
  • DuckDuckGo Search API
  • BeautifulSoup4 for web scraping
  • Markdownify for content conversion

API Configuration for Summarization

This application supports content summarization using OpenAI's API or any compatible API service. To enable this feature:

  1. Copy the .env.example file to .env:
cp .env.example .env
  1. Edit the .env file and set your API credentials:
OPENAI_API_URL=https://api.openai.com/v1
ACCESS_TOKEN=your_api_key_here

Notes:

  • OPENAI_API_URL defaults to the official OpenAI API server if not specified
  • ACCESS_TOKEN is required for the summarization feature to work
  • You can use any OpenAI-compatible API by changing the OPENAI_API_URL
Running with Docker and API Credentials

To run the Docker container with your API credentials:

docker run -p 7860:7860 \
  -e OPENAI_API_URL="https://api.openai.com/v1" \
  -e ACCESS_TOKEN="your_api_key_here" \
  ddg-mcp-server
Testing the API Connection

After configuring your API credentials, you can test if the connection works correctly:

python main.py --test-api

This will validate your API credentials without starting the full server.

Model Configuration

The AI model used for summarization can be configured in the config.py file:

# Default model to use for summarization
DEFAULT_MODEL = "gpt-4.1-turbo"

For detailed instructions on model configuration, see SUMMARIZATION.md.

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.