Model Context Protocol Server

Model Context Protocol (MCP) Server

A FastAPI-based server implementing the Model Context Protocol for providing contextual information to AI models. This server acts as a middleware between AI models and various data sources, intelligently routing queries to the most appropriate data provider.

Features

Intelligent query routing based on query analysis
Support for multiple data sources (Database, GraphQL, REST)
Integration with Ollama models (Mistral, Qwen, Llama2)
Environment-aware configuration (Development/Production)
Comprehensive logging and error handling
Health check endpoints
Mock data support for development

Prerequisites

Python 3.8+
Ollama installed and running locally
Required Ollama models:
- mistral
- qwen
- llama2

Installation

Clone the repository:

git clone <repository-url>
cd mcp-server

Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

Install dependencies:

pip install -r requirements.txt

Create a .env file:

cp .env.example .env

Update the .env file with your configuration:

ENVIRONMENT=development
OLLAMA_MODEL=mistral
OLLAMA_BASE_URL=http://localhost:11434

Running the Server

Start Ollama (if not already running):

ollama serve

Start the MCP server:

python main.py

The server will be available at http://localhost:8000

API Endpoints

Get Context

curl -X POST http://localhost:8000/context \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Tell me about iPhone 15",
    "model": "mistral"
  }'

List Available Models

curl http://localhost:8000/models

Health Check

curl http://localhost:8000/health

Project Structure

mcp-server/
├── context_providers/     # Data source providers
│   ├── database.py       # Database provider
│   ├── graphql.py        # GraphQL provider
│   ├── rest.py          # REST API provider
│   └── provider_factory.py
├── model_providers/      # AI model providers
│   ├── base.py          # Base model provider
│   ├── ollama.py        # Ollama integration
│   └── provider_factory.py
├── main.py              # FastAPI application
├── query_analyzer.py    # Query analysis logic
├── logger_config.py     # Logging configuration
├── requirements.txt     # Project dependencies
└── README.md           # Project documentation

Development

Adding New Providers

Create a new provider class in the appropriate directory
Implement the required interface methods
Register the provider in the factory

Adding New Models

Add the model to the AVAILABLE_MODELS dictionary in model_providers/ollama.py
Update the model validation logic if needed

Contributing

Fork the repository
Create a feature branch
Commit your changes
Push to the branch
Create a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

This server cannot be installed

security - not tested

license - not found

quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A middleware server that intelligently routes AI model queries to appropriate data sources, providing contextual information to enhance AI responses.

Related MCP Servers

OmniMCP
OpenAdaptAI
-
security
F
license
-
quality
A server that provides rich UI context and interaction capabilities to AI models, enabling deep understanding of user interfaces through visual analysis and precise interaction via Model Context Protocol.
Last updated -
24
Python
Playwright MCP Server
Kotelberg
-
security
F
license
-
quality
A server that enables AI systems to browse, retrieve content from, and interact with web pages through the Model Context Protocol.
Last updated -
Crawl4AI MCP Server
BjornMelin
-
security
F
license
-
quality
High-performance server enabling AI assistants to access web scraping, crawling, and deep research capabilities through Model Context Protocol.
Last updated -
4
TypeScript
MCP Framework
Viking1726
-
security
A
license
-
quality
A middleware system that connects large language models (LLMs) with various tool services through an OpenAI-compatible API, enabling enhanced AI assistant capabilities with features like file operations, web browsing, and database management.
Last updated -
3
Python
MIT License

View all related MCP servers