duckduckgo-search MCP Server
English | 中文
A Model Context Protocol server for DuckDuckGo Search
This is a TypeScript-based MCP server that provides DuckDuckGo search functionality. It demonstrates core MCP concepts through:
- Integration with DuckDuckGo Search
- Easy-to-use search tool interface
- Rate limiting and error handling support
Features
Search Tool
duckduckgo_search- Perform web searches using DuckDuckGo API- Required parameter:
query(search query, max 400 characters) - Optional parameter:
count(number of results, 1-20, default 10) - Optional parameter:
safeSearch(safety level: strict/moderate/off, default moderate) - Returns formatted Markdown search results
- Required parameter:
Rate Limits
- Maximum 1 request per second
- Maximum 15000 requests per month
Development
Prerequisites
- Node.js >= 18
- pnpm >= 8.0.0
Installation
# Install pnpm if not already installed
npm install -g pnpm
# Install project dependencies
pnpm install
Build and Run
Build the server:
pnpm run build
For development with auto-rebuild:
pnpm run watch
Setup in Claude Desktop
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
# online
{
"mcpServers": {
"duckduckgo-search": {
"command": "npx",
"args": [
"-y",
"duckduckgo-mcp-server"
]
}
}
}
# local
{
"mcpServers": {
"duckduckgo-search": {
"command": "node",
"args": [
"/path/to/duckduckgo-search/build/index.js"
]
}
}
}
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
pnpm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Recommend MCP Servers 💡
memcord
AI Memory Management for Claude Desktop, providing intelligent summarization, search, and organization of chat history as a self-hosted MCP server.
aperag-mcp
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
sheffler/mcp-server-lims
An MCP server for Laboratory Information Management System (LIMS) enabling AI agents to manage lab workflow data and interact with simulated instruments
gqai
Turn any GraphQL endpoint into a set of MCP tools
smart-tree
Smart Tree: not just a tree, a philosophy. A context-aware, AI-crafted replacement for 20+ tools with MEM8 quantum compression, semantic search, AST-smart editing, and partnership memory. Crafted with care by human + AI—accept no knock-offs.
needle
Needle MCP Server organizes and stores documents, enabling powerful semantic search and retrieval for LLMs via Claude's Desktop Application, acting as long-term memory for RAG.