Content
# 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](https://docs.astral.sh/uv/) package manager
- Node.js (for MCP inspector)
- Hugging Face account (for tiny-agents)
## Installation
1. **Clone or download this project**
```bash
git clone https://github.com/Deon62/mcp.git
cd mcps
```
2. **Install Python dependencies**
```bash
uv pip install mcp[cli] requests
```
3. **Install tiny-agents (if not already installed)**
```bash
pip install tiny-agents
```
4. **Install sentiment analysis dependencies**
```bash
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:
```bash
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:
```bash
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:
```bash
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`)
```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 information
- `web_search(query)` - Performs web searches
- `get_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
```bash
npm install -g @modelcontextprotocol/inspector
```
### 2. Run the Inspector
```bash
mcp-inspector
```
### 3. Connect to Your Server
In the inspector:
1. Click "Add Server"
2. Choose "stdio" transport
3. Set command: `uv`
4. Set args: `["run", "--with", "mcp", "mcp", "run", "server.py"]`
5. 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:**
```json
{
"polarity": 0.8,
"subjectivity": 0.9,
"assessment": "positive"
}
```
## Troubleshooting
### Common Issues
1. **"ModuleNotFoundError: No module named 'mcp'"**
```bash
uv pip install mcp[cli]
```
2. **"KeyError: 'command'"**
- Check your `agent.json` configuration
- Ensure the server configuration is correct
3. **"Connection closed" errors**
- Make sure the MCP server is running
- Check that all dependencies are installed
4. **Agent shows "0 tools"**
- Verify the server is running
- Check the agent.json configuration
- Ensure the server command is correct
5. **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')"`
6. **Gradio Interface Issues**
- Update Gradio: `pip install --upgrade gradio`
- Check for port conflicts (default: 7860)
- Verify MCP server parameter compatibility
### Debug Steps
1. **Test the server directly:**
```bash
python server.py
```
2. **Check MCP server with inspector:**
```bash
mcp-inspector
```
3. **Verify dependencies:**
```bash
uv pip list | grep mcp
```
4. **Test sentiment analysis:**
```bash
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:
```python
@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:
1. **Amazon SageMaker** - Serverless inference with custom Inferentia2 chips
2. **Novita AI** - Integrated serverless inference directly on model pages
3. **Together AI** - Serverless inference with competitive pricing
4. **Nscale** - Official HF provider with high-performance GPU clusters
5. **Inference Endpoints** - Dedicated, fully managed infrastructure
6. **Google Cloud** - Vertex AI and other deployment options
7. **Microsoft Azure** - Azure Machine Learning services
8. **Replicate** - Easy-to-use model deployment platform
9. **Banana** - Serverless GPU inference platform
10. **Modal** - Serverless compute platform
11. **RunPod** - GPU cloud computing
12. **Lambda Labs** - GPU cloud infrastructure
## Contributing
1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test with both the agent and inspector
5. Submit a pull request
## License
[Add your license information here]
## Support
For issues and questions:
1. Check the troubleshooting section
2. Use the MCP inspector to debug
3. Open an issue on GitHub
4. Check the [MCP documentation](https://modelcontextprotocol.io/)
---
**Happy coding! **
