DuckDuckGo Search with MCP Agent
About
This project demonstrates how to use DuckDuckGo MCP Server with a LangChain Groq LLM agent to perform intelligent search tasks via MCP (Micro Component Protocol).
Details
- Author
- alihassanml
- GitHub stars
- 1
- Downloads
- 413
- Categories
- Search
Jump to
- DuckDuckGo MCP Server integration
- Groq LLM (deepseek-r1-distill-llama-70b) for reasoning
- Async Python execution
- Simple and modular code structure
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
DuckDuckGo Search with MCP AgentCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, install dependencies with pip install -r requirements.txt, set your GROQ_API_KEY in a .env file, install the MCP server via uvx -y duckduckgo-mcp-server, and run python main.py. The script starts an MCP client, connects to the DuckDuckGo MCP server, and uses the Groq LLM to perform a smart search.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"duckduckgo search with mcp agent": {
"Duckduckgo-with-MCP": {
"command": "uvx",
"args": [
"-y",
"duckduckgo-mcp-server"
]
}
}
}
}McpServers
{
"Duckduckgo-with-MCP": {
"command": "uvx",
"args": [
"-y",
"duckduckgo-mcp-server"
]
}
}DuckDuckGo Search with MCP Agent
This project demonstrates how to use DuckDuckGo MCP Server with a LangChain Groq LLM agent to perform intelligent search tasks via MCP (Micro Component Protocol).
---
Features
- MCP Server Integration (DuckDuckGo search) - Groq LLM (deepseek-r1-distill-llama-70b) for reasoning
- Async Python execution
- Simple and modular
---
Installation
1. Clone the repository:
git clone https://github.com/alihassanml/Duckduckgo-with-MCP.git
cd Duckduckgo-with-MCP
2. Install dependencies:
pip install -r requirements.txt
langchain_groq, python-dotenv, etc. in your requirements.txt.)
3. Set up your .env file:
GROQ_API_KEY=your_groq_api_key_here
4. Install the MCP Server:
uvx -y duckduckgo-mcp-server
(Make sure uvx is installed. If not, install it.)
---
Usage
Run the main script:
python main.py
This will:
- Start the MCP client
- Connect to the duckduckgo-mcp-server
- Use the Groq LLM to perform a smart search
- Print the result
---
Example Code
import asyncio
import os
from dotenv import load_dotenv
from langchain_groq import ChatGroq
from mcp_use import MCPAgent, MCPClient
async def main():
load_dotenv()
config = {
"mcpServers": {
"ddg-search": {
"command": "uvx",
"args": ["-y", "duckduckgo-mcp-server"]
}
}
}
client = MCPClient.from_dict(config)
llm = ChatGroq(model="deepseek-r1-distill-llama-70b")
agent = MCPAgent(llm=llm, client=client, max_steps=30)
result = await agent.run("Find the best restaurant in San Francisco")
print(f"\nResult: {result}")
if __name__ == "__main__":
asyncio.run(main())
---
Resources
- DuckDuckGo MCP Server - LangChain Groq Documentation - Micro Component Protocol (MCP)---
License
This project is licensed under the MIT License.Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
