a2a mcp
☰
Back to MCP Servers
duckduckgo-mcp logo
mcp-server369

duckduckgo-mcp

A Model Context Protocol (MCP) server that provides privacy-focused web search, content fetching, and parsing through DuckDuckGo, with LLM-ready formatting and rate limiting.

Overview

DuckDuckGo MCP is a lightweight Model Context Protocol (MCP) server that integrates DuckDuckGo's search engine into AI assistants and agents. It enables real-time web searches, webpage content retrieval, and intelligent parsing without relying on tracking-heavy alternatives.

Built primarily in Python (with TypeScript forks available), it is designed for seamless integration with tools like Claude Desktop, Cursor, VS Code, and other MCP-compatible environments.

Features

  • Web Search Tool: Perform searches via DuckDuckGo with support for advanced parameters, safe search, and result limits.
  • Content Fetching & Parsing: Retrieve and convert full webpages into clean Markdown or structured JSON, often using readers like Jina for LLM-friendly output.
  • Rate Limiting & Reliability: Built-in protections against abuse and error handling for robust performance.
  • LLM-Optimized Formatting: Results are structured with metadata, summaries, and clean text ideal for large language models.
  • Privacy-Focused: Leverages DuckDuckGo's no-tracking philosophy.
  • Easy Installation: Quick start with uvx duckduckgo-mcp-server or Docker images.

Quick Start

# Install and run via uvx
uvx duckduckgo-mcp-server

# Or add to Claude/Code
claude mcp add ddg-search uvx duckduckgo-mcp-server

Available as a PyPI package (pip install duckduckgo-mcp-server) and community Docker images.

Use Cases

  • Enhancing AI coding assistants with up-to-date documentation and library references.
  • Real-time research and fact-checking in conversational agents.
  • Building autonomous agents that need web access for news, articles, or data gathering.
  • Privacy-conscious workflows avoiding Google or Bing APIs.

Technical Details

The server implements the MCP specification to expose tools that AI clients can discover and call dynamically. It supports multiple search types (web, news, images, videos in some variants) and includes configurable options for region, date filtering, and pagination.

Multiple community implementations exist, including the popular nickclyde version and TypeScript ports.

Alternatives

Other MCP search servers exist for different providers (e.g., Exa, Tavily), but DuckDuckGo stands out for its simplicity, privacy, and zero-cost API access.

Note: This is a community project and not officially affiliated with DuckDuckGo.

Tags

mcpduckduckgoweb-searchsearchllm-toolpythonai-agentprivacy

Related Entries

Keep exploring similar tools and resources in this category.

Browse MCP Servers
SerpApi MCP Server logo

SerpApi MCP Server

MCP Servers

SerpApi MCP exposes search engine results to AI assistants through SerpApi, supporting live research and structured search data retrieval.

Jina AI MCP Server logo

Jina AI MCP Server

MCP Servers

Jina AI MCP exposes Jina’s web reading and search capabilities to AI assistants through an official remote server.

Parallel MCP Servers logo

Parallel MCP Servers

MCP Servers

Parallel MCP integrations let AI assistants use Parallel web search and research task capabilities without writing a custom API integration.

Hyper3D MCP logo

Hyper3D MCP

MCP Servers

Hyper3D MCP is Hyper3D's hosted Rodin MCP server for creating 3D assets from natural-language instructions or supported references, checking asynchronous generation progress, and retrieving model download links inside AI coding clients. Official setup is documented for Codex, Claude Code, and Kimi Code CLI.

Semrush MCP Server logo

Semrush MCP Server

MCP Servers

Semrush MCP connects AI assistants to Semrush APIs for keyword, backlink, website traffic and market research.

Browserbase MCP Server logo

Browserbase MCP Server

MCP Servers

Browserbase MCP gives AI agents browser automation tools powered by Stagehand and Browserbase browser sessions.

a2a mcp

Search the directory

Find entries, skills, articles, and categories. Use arrow keys to select and Enter to open.