DDGS

v1.0.0Search & Data Extractionstable

A metasearch library that aggregates results from diverse web search services

apiddgsdhtmcpmcp-server
Share:
2,658
Stars
0
Downloads
0
Weekly
0/5

What is DDGS?

DDGS is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to metasearch library that aggregates results from diverse web search services

A metasearch library that aggregates results from diverse web search services

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A metasearch library that aggregates results from diverse we

Use Cases

Aggregate web search results from multiple services.
Perform metasearch queries across diverse sources.
deedy5

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx ddgs

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use DDGS

DDGS (Dux Distributed Global Search) is a Python metasearch library and MCP server that aggregates results from ten web search backends including Bing, Brave, DuckDuckGo, Google, Startpage, Yandex, and Yahoo, as well as image, video, news, and book search. It exposes six MCP tools — text search, image search, news search, video search, book search, and URL content extraction — making it a drop-in web search capability for any MCP-compatible AI agent. Developers and AI application builders use it to give Claude or other agents real-time access to the web without requiring vendor-specific API keys.

Prerequisites

  • Python 3.10+
  • pip package manager
  • An MCP-compatible client such as Claude Desktop or Cursor
  • Optional: a SOCKS5/HTTP proxy if you need to route requests through one
1

Install the DDGS MCP server package

Install ddgs with the mcp extra to include the MCP server dependencies (based on stdio transport).

pip install -U ddgs[mcp]
2

Verify the CLI is available

Confirm the ddgs command is on your PATH and the mcp subcommand is accessible.

ddgs --help
ddgs mcp --help
3

Test the MCP server manually

Start the MCP server in stdio mode to confirm it launches without errors before wiring it into a client.

ddgs mcp
4

Add DDGS to your MCP client configuration

Register the server in your MCP client config file so it is available as a set of search tools.

5

Optional: run with a proxy

If you need requests routed through a SOCKS5 proxy (e.g. Tor), pass the -pr flag.

ddgs mcp -pr socks5h://127.0.0.1:9150

DDGS Examples

Client configuration

Add DDGS as an MCP server in Claude Desktop or Cursor. No API keys are required.

{
  "mcpServers": {
    "ddgs": {
      "command": "ddgs",
      "args": ["mcp"]
    }
  }
}

Prompts to try

Example prompts to try in Claude once DDGS is connected as an MCP server.

- "Search the web for the latest news about the Anthropic Claude API and summarise the top 5 articles."
- "Find images of the northern lights taken in Iceland this winter."
- "Search YouTube for video tutorials on LangGraph and list the most viewed ones."
- "Extract the main content from https://example.com/article and summarise it in bullet points."

Troubleshooting DDGS

ddgs command not found after installation

The ddgs binary is installed in your Python environment's bin directory. If you used pip install --user, add ~/.local/bin to your PATH. If you used a virtual environment, activate it first. You can also find the path with python -m ddgs.

Search requests return empty results or time out

DDGS uses multiple backends automatically (backend='auto'). If results are empty, one or more backends may be rate-limiting your IP. Try using a proxy (ddgs mcp -pr http://proxy:port) or wait a few minutes before retrying. You can also test a specific backend: ddgs mcp will internally try alternatives.

extract_content tool returns an error for a specific URL

Some URLs block automated access or require JavaScript rendering. The extract tool fetches the raw HTTP response — it does not execute JavaScript. For JS-heavy pages, the extracted content may be empty or incomplete. Use the search tools to find an alternative source instead.

Frequently Asked Questions about DDGS

What is DDGS?

DDGS is a Model Context Protocol (MCP) server that metasearch library that aggregates results from diverse web search services It connects AI assistants to external tools and data sources through a standardized interface.

How do I install DDGS?

Follow the installation instructions on the DDGS GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with DDGS?

DDGS works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is DDGS free to use?

Yes, DDGS is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "ddgs": { "command": "npx", "args": ["-y", "ddgs"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use DDGS?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides