This project implements a suite of AI tools built on the Machine Communication Protocol (MCP) framework. Each tool leverages large language models through a client-server architecture to provide specialized functionality for search, mathematics, and news retrieval operations.
- DuckDuckGo Search Engine: Web search with content extraction capabilities
- Mathematical Operations Engine: Basic arithmetic with natural language processing
- Tech News Aggregator: Real-time technology news from reputable sources
- Python 3.8+
- UV package manager
- Groq API key
If you don't have UV installed, install it first:
# Install UV using curl
curl -sSf https://install.ultraviolet.rs | sh
# Or with pip
pip install uvClone the repository and install dependencies using the existing pyproject.toml:
# Clone the repository
git clone https://github.com/rahulsamant37/mcp-tools.git
cd mcp-tools
# Create and activate a virtual environment
uv venv
# On Windows:
.venv\Scripts\activate
# On macOS/Linux:
source .venv/bin/activate
# Install dependencies from pyproject.toml
uv pip syncIf you need to install dependencies without an existing pyproject.toml:
# Install directly (will update pyproject.toml and uv.lock)
uv pip install mcp langchain-mcp-adapters langchain-groq langgraph httpx beautifulsoup4 python-dotenvCreate a .env file in the project root:
GROQ_API_KEY=your_groq_api_key_here
Each tool can be tested independently by running its client script, which automatically launches the corresponding server component.
python duckduckgo_client.pyThis tool provides:
- Web search functionality via DuckDuckGo
- Content extraction from websites
- Rate-limited requests to prevent IP blocking
- Formatted search results optimized for LLM consumption
python math_client.pyThis tool enables:
- Basic arithmetic operations (addition, multiplication)
- Natural language processing of mathematical expressions
- Integration with ReAct agents for complex problem solving
python weather_client.pyThis tool delivers:
- Latest articles from Ars Technica
- Content parsing and summarization
- Structured data output for LLM processing
The project implements a microservices architecture using MCP:
- Implements domain-specific functionality
- Exposes capabilities through standardized MCP interfaces
- Handles rate limiting and error management
- Processes raw data into LLM-friendly formats
- Establishes connections to server components
- Creates LangChain-compatible tool interfaces
- Integrates with ReAct agents for reasoning
- Manages conversation context and state
- Leverages Groq's Qwen-2.5-32b model for reasoning
- Implements ReAct (Reasoning + Acting) methodology
- Supports asynchronous operations for improved performance
| Issue | Solution |
|---|---|
| Connection errors | Check that no other processes are using required ports |
| Authentication failures | Verify Groq API key in .env file |
| Rate limiting | Implement exponential backoff between requests |
| Timeout errors | Increase timeout values in httpx client configurations |
| Dependency issues | Run uv pip list to verify installations |
| UV sync errors | Check if pyproject.toml exists and is valid |
To extend this project with new tools:
- Create a server file implementing your tool's functionality
- Expose methods using the
@mcp.tool()decorator - Develop a client file that establishes connections and loads tools
- Integrate with the ReAct agent framework
This project is licensed under the GNU License - see the LICENSE file for details.
- Machine Communication Protocol team
- langchain-mcp-adapters framework
- Groq for LLM API access