MCP Multi-Service Agent
A collection of Model Context Protocol (MCP) servers providing various AI-powered services, designed to work with Hugging Face's tiny-agents framework.
Features
Core Services
- Weather Service: Get weather information for any location
- Web Search: Search the web for information (with special support for Hugging Face inference providers)
- Sentiment Analysis: Analyze text sentiment with polarity and subjectivity scores
Integration Features
- AI Agent Integration: Works seamlessly with tiny-agents for conversational AI
- MCP Inspector Support: Debug and inspect server capabilities
- Gradio Web Interface: Interactive web UI for sentiment analysis
Prerequisites
- Python 3.10 or higher
- uv package manager
- Node.js (for MCP inspector)
- Hugging Face account (for tiny-agents)
Installation
-
Clone or download this project
git clone https://github.com/Deon62/mcp.git cd mcps -
Install Python dependencies
uv pip install mcp[cli] requests -
Install tiny-agents (if not already installed)
pip install tiny-agents -
Install sentiment analysis dependencies
cd mcp-sentiment python -m venv venv venv\Scripts\activate # On Windows # source venv/bin/activate # On Linux/Mac pip install -r requirements.txt
Quick Start
1. Run the MCP Server
Start the MCP server in one terminal:
uv run --with mcp mcp run server.py
The server will start and wait for connections.
2. Run the AI Agent
In another terminal, start the agent:
tiny-agents run agent.json
You should see:
Agent loaded with 3 tools:
• get_weather
• web_search
• get_hf_inference_providers
»
3. Run Sentiment Analysis Web App
For the sentiment analysis service, run the Gradio web interface:
cd mcp-sentiment
venv\Scripts\activate # On Windows
# source venv/bin/activate # On Linux/Mac
python app.py
The web interface will be available at http://localhost:7860
4. Chat with the Agent
Once the agent is running, you can interact with it:
» Hello! Can you help me find information about Hugging Face inference providers?
Available Tools
1. Weather Service
» What's the weather like in New York?
2. Web Search
» Search for "Hugging Face inference providers"
3. HF Inference Providers
» Get me the list of Hugging Face inference providers
4. Sentiment Analysis
» Analyze the sentiment of this text: "I love this new product!"
Web Interface Features:
- Polarity Score: -1 (negative) to +1 (positive)
- Subjectivity Score: 0 (objective) to 1 (subjective)
- Assessment: Positive, Negative, or Neutral classification
- Real-time Analysis: Instant sentiment analysis as you type
Configuration
Agent Configuration (agent.json)
{
"model": "Qwen/Qwen2.5-72B-Instruct",
"provider": "nebius",
"servers": [
{
"type": "stdio",
"command": "uv",
"args": ["run", "--with", "mcp", "mcp", "run", "server.py"]
}
]
}
Server Configuration (server.py)
The server provides three main tools:
get_weather(location)- Returns weather informationweb_search(query)- Performs web searchesget_hf_inference_providers()- Returns comprehensive list of HF inference providers
MCP Inspector Setup
The MCP Inspector allows you to debug and test your MCP server directly.
1. Install MCP Inspector
npm install -g @modelcontextprotocol/inspector
2. Run the Inspector
mcp-inspector
3. Connect to Your Server
In the inspector:
- Click "Add Server"
- Choose "stdio" transport
- Set command:
uv - Set args:
["run", "--with", "mcp", "mcp", "run", "server.py"] - Click "Connect"
4. Test Tools
Once connected, you can:
- View available tools in the sidebar
- Test each tool with different parameters
- See the JSON-RPC communication
- Debug any issues
Example Usage
Weather Queries
» What's the weather in Tokyo?
» Get weather for London
» How's the weather in San Francisco?
Web Search Queries
» Search for "latest AI developments"
» Find information about "MCP protocol"
» Look up "Hugging Face inference providers"
Specific HF Provider Queries
» Show me all Hugging Face inference providers
» What inference providers does HF support?
» List the available HF deployment options
Sentiment Analysis Examples
» Analyze the sentiment of: "This product is amazing and I love it!"
» What's the sentiment of: "I'm not sure about this decision"
» Check the sentiment of: "The weather is okay today"
Example Output:
{
"polarity": 0.8,
"subjectivity": 0.9,
"assessment": "positive"
}
Troubleshooting
Common Issues
-
"ModuleNotFoundError: No module named 'mcp'"
uv pip install mcp[cli] -
"KeyError: 'command'"
- Check your
agent.jsonconfiguration - Ensure the server configuration is correct
- Check your
-
"Connection closed" errors
- Make sure the MCP server is running
- Check that all dependencies are installed
-
Agent shows "0 tools"
- Verify the server is running
- Check the agent.json configuration
- Ensure the server command is correct
-
Sentiment Analysis Import Errors
- Ensure virtual environment is activated
- Install NLTK data:
python -c "import nltk; nltk.download('punkt'); nltk.download('brown')" - Check TextBlob installation:
python -c "from textblob import TextBlob; print('OK')"
-
Gradio Interface Issues
- Update Gradio:
pip install --upgrade gradio - Check for port conflicts (default: 7860)
- Verify MCP server parameter compatibility
- Update Gradio:
Debug Steps
-
Test the server directly:
python server.py -
Check MCP server with inspector:
mcp-inspector -
Verify dependencies:
uv pip list | grep mcp -
Test sentiment analysis:
cd mcp-sentiment venv\Scripts\activate python -c "from textblob import TextBlob; print(TextBlob('Hello world').sentiment)"
Project Structure
mcps/
├── server.py # Main MCP server implementation
├── agent.json # Agent configuration
├── requirements.txt # Python dependencies
├── uv.lock # Dependency lock file
├── app.py # Main application entry point
├── mcp-sentiment/ # Sentiment analysis service
│ ├── app.py # Gradio web interface for sentiment analysis
│ ├── requirements.txt # Sentiment analysis dependencies
│ └── venv/ # Virtual environment for sentiment analysis
└── README.md # This file
Development
Adding New Tools
To add a new tool to the server:
@mcp.tool()
def your_new_tool(param: str) -> str:
"""Description of what this tool does"""
return f"Result for {param}"
Modifying Agent Configuration
Edit agent.json to:
- Change the AI model
- Add more MCP servers
- Modify server configurations
Hugging Face Inference Providers
The server includes comprehensive information about HF inference providers:
- Amazon SageMaker - Serverless inference with custom Inferentia2 chips
- Novita AI - Integrated serverless inference directly on model pages
- Together AI - Serverless inference with competitive pricing
- Nscale - Official HF provider with high-performance GPU clusters
- Inference Endpoints - Dedicated, fully managed infrastructure
- Google Cloud - Vertex AI and other deployment options
- Microsoft Azure - Azure Machine Learning services
- Replicate - Easy-to-use model deployment platform
- Banana - Serverless GPU inference platform
- Modal - Serverless compute platform
- RunPod - GPU cloud computing
- Lambda Labs - GPU cloud infrastructure
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Test with both the agent and inspector
- Submit a pull request
License
[Add your license information here]
Support
For issues and questions:
- Check the troubleshooting section
- Use the MCP inspector to debug
- Open an issue on GitHub
- Check the MCP documentation
**Happy coding! **