Skip to main content
Glama

DuckDuckGo MCP Server

by rkampani
GitHub
Python
  • Apple
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

DuckDuckGo MCP Server

A Model Context Protocol (MCP) server that enables AI assistants and language models to perform real-time web searches using DuckDuckGo's privacy-focused search engine.

Tools

1. web_search

Search the web using DuckDuckGo.

Parameters:

  • query (string, required): The search query

  • max_results (integer, optional): Maximum number of results (default: 10, max: 50)

  • region (string, optional): Region code (e.g., 'us-en', 'uk-en', 'wt-wt' for worldwide)

  • safe_search (boolean, optional): Enable safe search filtering

Example:

{ "query": "Python async programming", "max_results": 5, "region": "us-en", "safe_search": true }

2. fetch_page_content

Fetch and extract clean content from a web page.

Parameters:

  • url (string, required): The URL to fetch

Example:

{ "url": "https://example.com/article" }

3. suggest_related_searches

Get related search suggestions.

Parameters:

  • query (string, required): The search query

  • max_suggestions (integer, optional): Maximum suggestions (default: 5, max: 10)

Example:

{ "query": "machine learning", "max_suggestions": 5 }

Installation

Prerequisites

  • Python 3.10 or higher

  • pip or uv package manager

Local Development

  1. Clone the repository:

git clone <repository-url> cd duckduckgo-mcp

  1. Create a virtual environment:

python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate

  1. Install dependencies:

pip install -r requirements.txt

  1. Run the server:

python python run_mcp_server.py

Using with Claude Desktop

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "duckduckgo-search": { "command": "python", "args": [ "-m", "src.main" ], "cwd": "/path/to/duckduckgo-mcp", "env": {} } } }

Deploy to Apify

  1. Create an account at Apify

  2. Install Apify CLI:

npm install -g apify-cli

  1. Login to Apify:

apify login

  1. Deploy the Actor:

apify push

Configuration

Configure the Actor through the input schema:

{ "mode": "stdio", "searchRateLimit": 30, "fetchRateLimit": 20, "maxResultsDefault": 10, "safeModeDefault": true, "enableLogging": true, "enableCaching": false, "cacheExpiryMinutes": 60 }

Configuration Options

Option

Type

Default

Description

mode

string

"stdio"

Server mode: "stdio" or "http"

searchRateLimit

integer

30

Max search requests per minute

fetchRateLimit

integer

20

Max fetch requests per minute

maxResultsDefault

integer

10

Default number of search results

safeModeDefault

boolean

true

Enable safe search by default

enableLogging

boolean

true

Enable detailed logging

enableCaching

boolean

false

Cache search results

cacheExpiryMinutes

integer

60

Cache expiry time

Architecture

duckduckgo-mcp/ ├── .actor/ │ ├── actor.json # Actor configuration │ ├── input_schema.json # Input validation schema │ └── Dockerfile # Container definition ├── src/ │ ├── __init__.py │ ├── main.py # Entry point │ ├── mcp_server.py # MCP protocol implementation │ ├── search_handler.py # DuckDuckGo search wrapper │ └── utils/ │ ├── rate_limiter.py # Rate limiting logic │ ├── content_parser.py # HTML parsing │ └── formatter.py # Result formatting ├── tests/ ├── requirements.txt ├── pyproject.toml └── README.md

Development

Running Tests

pytest tests/

Code Formatting

black src/ ruff check src/

Type Checking

mypy src/

Rate Limits

The server implements rate limiting to prevent abuse:

  • Search: 30 requests per minute (configurable)

  • Fetch: 20 requests per minute (configurable)

Rate limiting uses a token bucket algorithm that refills over time.

Error Handling

The server provides comprehensive error handling:

  • Network failures are caught and reported

  • Rate limit violations are queued

  • Invalid inputs are validated

  • All errors return structured messages

Use Cases

For AI Developers

  • Build chatbots with web search capabilities

  • Create research assistants

  • Develop fact-checking tools

For Software Engineers

  • Integrate search into applications

  • Build custom search interfaces

  • Create data collection pipelines

For Researchers

  • Combine AI reasoning with real-time data

  • Perform automated research

  • Analyze search trends

Privacy & Terms

This Actor:

  • Uses DuckDuckGo's privacy-focused search engine

  • Does not track user queries

  • Is for educational and research purposes

  • Should respect DuckDuckGo's Terms of Service

  • Is not affiliated with DuckDuckGo

Important: This tool is not intended for commercial use that violates DuckDuckGo's Terms of Service.

Contributing

Contributions are welcome! Please:

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests

  5. Submit a pull request

License

MIT License - see LICENSE file for details

Support

For issues, questions, or contributions:

  • Open an issue on GitHub

  • Check existing documentation

  • Review the code examples

Changelog

Version 1.0.0

  • Initial release

  • Web search functionality

  • Content fetching and parsing

  • Search suggestions

  • Rate limiting

  • MCP protocol support

  • Apify Actor integration

Roadmap

Future enhancements:

  • HTTP server mode

  • News search

  • Image search

  • Video search

  • Advanced caching

  • Search history

  • Analytics and metrics

  • Multi-language support

Credits

Built with:

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Enables AI assistants to perform real-time web searches, fetch webpage content, and get search suggestions using DuckDuckGo's privacy-focused search engine.

  1. Tools
    1. 1. web_search
    2. 2. fetch_page_content
    3. 3. suggest_related_searches
  2. Installation
    1. Prerequisites
    2. Local Development
    3. Using with Claude Desktop
    4. Deploy to Apify
  3. Configuration
    1. Configuration Options
  4. Architecture
    1. Development
      1. Running Tests
      2. Code Formatting
      3. Type Checking
    2. Rate Limits
      1. Error Handling
        1. Use Cases
          1. For AI Developers
          2. For Software Engineers
          3. For Researchers
        2. Privacy & Terms
          1. Contributing
            1. License
              1. Support
                1. Changelog
                  1. Version 1.0.0
                2. Roadmap
                  1. Credits

                    New MCP Servers

                    MCP directory API

                    We provide all the information about MCP servers via our MCP API.

                    curl -X GET 'https://glama.ai/api/mcp/v1/servers/rkampani/duckduckgo-mcp'

                    If you have feedback or need assistance with the MCP directory API, please join our Discord server