Overview of MCP Server for MCP Servers

The MCP Server for MCP Servers is a beginner-friendly template designed to simplify the process of building MCP servers. It features a PostgreSQL connector and clean, easy-to-understand code, making it perfect for developers new to the Model Context Protocol (MCP). With minimal setup, developers can experiment and create their own AI tool connectors, leveraging the power of MCP to interact with external tools and data.

What is MCP?

The Model Context Protocol (MCP) is an open standard that allows Large Language Models (LLMs) to interact with external tools and data sources. It acts as a bridge, enabling AI models to execute commands, access resources, and generate consistent instructions through prompts. MCP facilitates seamless integration and interaction between AI models and external systems, making it a crucial component for building intelligent applications.

Key Features of MCP Server

1. Tools

   • execute_query: Run SQL queries against your database.
   • test_connection: Verify the database connection is working.

2. Resources

   • db://tables: List of all tables in the schema.
   • db://tables/{table_name}: Schema information for a specific table.
   • db://schema: Complete schema information for all tables in the database.

3. Prompts

   • Query generation templates.
   • Analytical query builders.

Use Cases

Developer Experimentation

The MCP Server template is ideal for developers who want to experiment with MCP and create custom AI tool connectors. Its simplicity and clear code structure make it accessible to those new to the protocol, allowing them to quickly get up to speed and start building.

AI Tool Integration

By using the MCP Server, developers can integrate AI tools with external data sources, enabling AI models to execute commands and access resources. This integration is essential for building intelligent applications that leverage AI capabilities to interact with external systems.

Custom AI Tool Development

The MCP Server provides a foundation for developing custom AI tools that interact with external data sources. Developers can extend the template to create their own MCP servers, tailoring the functionality to meet specific requirements.

Prerequisites

• Python 3.8+
• uv - Modern Python package manager and installer
• npx (included with Node.js)
• PostgreSQL database you can connect to

Quick Setup

1. Create a virtual environment and install dependencies:

   uv venv
   source .venv/bin/activate  # On Windows: .venvScriptsactivate
   uv pip install -r requirements.txt
   

2. Run the server with the MCP Inspector:

   npx @modelcontextprotocol/inspector uv --directory . run postgres -e DSN=postgresql://username:password@hostname:port/database -e SCHEMA=public
   

3. Using the Inspector:

   • Click the “Connect” button in the interface.
   • Explore the “Tools”, “Resources”, and “Prompts” tabs.

UBOS Platform

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. Our platform helps orchestrate AI Agents, connect them with enterprise data, and build custom AI Agents with LLM models and Multi-Agent Systems. The MCP Server template complements UBOS by providing a foundation for integrating AI tools with external data sources, enhancing the capabilities of AI Agents developed on the platform.

Next Steps

To extend this project with your own MCP servers:

1. Create a new directory under /src (e.g., /src/my-new-mcp).
2. Implement your MCP server following the PostgreSQL example.
3. Add your new MCP to pyproject.toml.

The MCP Server for MCP Servers is a powerful tool for developers looking to harness the capabilities of the Model Context Protocol. With its beginner-friendly design and robust features, it serves as an excellent starting point for building intelligent applications that interact with external systems.