DuckDuckGo Search MCP š
@OEvortex
About DuckDuckGo Search MCP š
A powerful Model Context Protocol (MCP) server for web search and URL content extraction using DuckDuckGo.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ddg_search": {
"command": "npx",
"args": [
"-y",
"@oevortex/ddg_search@latest",
"your search query"
]
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is DuckDuckGo Search MCP š?
A command-line and MCP server that provides web search via DuckDuckGo and AIāpowered answers via IAsk AI or Monica AI. No API keys are required. It is designed for developers and AI agents who need fast, private search and AI answers directly from a terminal or MCPācompatible clients like Claude Desktop.
How to use DuckDuckGo Search MCP š?
Run searches from the command line using npx -y @oevortex/ddg_search@latest "query" or the globally installed ddg command. For MCP integration, start the server with ddg --server and configure it in your MCP client using the provided JSON config (command npx -y @oevortex/ddg_search@latest). Use flags like -m ai for AI answers and -b monica to switch AI backends.
Key features of DuckDuckGo Search MCP š
- No API keys or registration required
- Three backends: DuckDuckGo, IAsk AI, Monica AI
- Single unified MCP tool
web-searchwith configurable parameters - Supports both web results and AIāgenerated answers
- Proxy support via
HTTP_PROXY/HTTPS_PROXYenvironment variables - Userāagent rotation for reliable scraping
Use cases of DuckDuckGo Search MCP š
- Adding realātime web search to an AI agentās toolset
- Quick factual lookups from the command line without opening a browser
- Integrating AIāpowered answers into MCP clients (e.g., Claude Desktop)
- Academic research using IAskās academic mode with configurable detail levels
FAQ from DuckDuckGo Search MCP š
What search backends are supported?
DuckDuckGo for web results, and IAsk AI or Monica AI for AIāgenerated answers.
Do I need any API keys to use this server?
No. All backends are accessed without API keys or registration.
How do I run it as an MCP server with Claude Desktop?
Start the server with ddg --server or via npx -y @oevortex/ddg_search@latest. Then add the provided JSON configuration to your Claude Desktop mcpServers setting.
Does the server support proxies?
Yes. It respects the HTTP_PROXY, HTTPS_PROXY, and NO_PROXY environment variables automatically.
What transport does the MCP server use?
The MCP server uses stdio transport. No authentication is required.
Frequently asked questions
What search backends are supported?
DuckDuckGo for web results, and IAsk AI or Monica AI for AIāgenerated answers.
Do I need any API keys to use this server?
No. All backends are accessed without API keys or registration.
How do I run it as an MCP server with Claude Desktop?
Start the server with `ddg --server` or via `npx -y @oevortex/ddg_search@latest`. Then add the provided JSON configuration to your Claude Desktop `mcpServers` setting.
Does the server support proxies?
Yes. It respects the `HTTP_PROXY`, `HTTPS_PROXY`, and `NO_PROXY` environment variables automatically.
What transport does the MCP server use?
The MCP server uses stdio transport. No authentication is required.
Basic information
More Search MCP servers
Everything Search MCP Server
mamertofabianGoogle Search MCP Server
mixelpixxMCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites
Google Search Console MCP Server
ahonnA Model Context Protocol (MCP) server providing access to Google Search Console
Google Search Console MCP server for SEOs
AminForouGoogle Search Console Insights with Claude AI for SEOs
Web Scout MCP Server
pinkpixel-devA powerful MCP server extension providing web search and content extraction capabilities. Integrates DuckDuckGo search functionality and URL content extraction into your MCP environment, enabling AI assistants to search the web and extract webpage content programmatically.
Comments