pymcp is a Python project based on the FastMCP framework that allows AI agents to interact with MySQL databases. It provides a server-client architecture for querying, analyzing, and leveraging data.

What are the system requirements for pymcp?

pymcp requires Python 3.13 or higher. You also need to install the necessary dependencies using `pip install -r requirements.txt`.

How do I install pymcp?

You can install pymcp by cloning the repository and running `pip install -r requirements.txt` in your terminal.

How do I run the pymcp server?

Navigate to the project directory in your terminal and run `python main.py`. The server will start on `0.0.0.0:8080` by default.

How do I run the pymcp client?

In a separate terminal, navigate to the project directory and run `python client.py`. The client will connect to the server and allow you to execute commands.

How do I configure the MySQL connection settings?

You can configure the MySQL connection settings in the `src/env.py` (for local environment) or `src/env_dev.py` (for development environment) files. You can set environment variables like `APP_ENV` to switch between environments.

What tools are available in pymcp?

The server provides tools like `describe_tools` (to list available tools) and `query_mysql(sql: str)` (to execute SQL queries).

How do I execute a SQL query using pymcp?

Use the `query_mysql` tool with the SQL query as a string. For example: `query_mysql("SELECT * FROM users LIMIT 10;")`.

Can I use pymcp with the UBOS platform?

Yes, pymcp can be integrated with UBOS to provide AI agents with access to MySQL databases. UBOS offers tools for orchestrating AI agents and connecting them to enterprise data.

How do I set the environment (local/development)?

You can set the environment using the `APP_ENV` environment variable. For example, `export APP_ENV=dev` sets the environment to development.

What if I encounter issues during installation or execution?

Refer to the project's README.md for detailed instructions and troubleshooting tips. You can also consult the pymcp documentation for further assistance.

pymcp MySQL Integration Server – Overview

UBOS Asset Marketplace: pymcp - Your Gateway to MySQL Data for AI Agents

In the burgeoning landscape of AI-driven applications, the ability for AI agents to seamlessly access and interact with external data sources is paramount. The pymcp MCP server, now available on the UBOS Asset Marketplace, provides a robust and efficient solution for connecting AI agents to MySQL databases. Built upon the FastMCP framework, pymcp is a Python-based project designed to facilitate communication between servers and clients, enabling AI agents to query, analyze, and leverage data stored in MySQL databases.

What is MCP and Why is it Important?

MCP, or Model Context Protocol, is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). It acts as a bridge, enabling AI models to access and interact with external data sources, tools, and APIs. Without a standardized protocol like MCP, integrating AI agents with existing systems becomes a complex and time-consuming endeavor, hindering the widespread adoption of AI in enterprise environments.

Pymcp leverages the MCP framework to provide a secure and standardized way for AI agents to interact with MySQL databases. This simplifies the integration process, reduces development time, and ensures that AI agents have access to the information they need to perform their tasks effectively.

Use Cases for pymcp

Pymcp opens up a wide range of possibilities for AI-powered applications that require access to MySQL data. Here are a few key use cases:

AI-Powered Data Analysis: AI agents can use pymcp to query MySQL databases and extract data for analysis, identifying trends, patterns, and insights that would be difficult or impossible to uncover manually. For example, a marketing AI agent could analyze customer purchase history to identify high-value customers and personalize marketing campaigns accordingly.
Automated Reporting: Pymcp enables AI agents to automatically generate reports based on data stored in MySQL databases. This can save significant time and effort compared to manual report creation, and ensure that reports are always up-to-date and accurate. For instance, a sales AI agent could generate daily sales reports, highlighting key performance indicators and identifying areas for improvement.
Real-Time Data Integration: AI agents can use pymcp to access real-time data from MySQL databases, enabling them to make informed decisions based on the latest information. For example, a supply chain AI agent could monitor inventory levels and adjust production schedules in response to changing demand.
Customer Service Automation: AI agents can use pymcp to access customer data stored in MySQL databases, enabling them to provide personalized and efficient customer service. For instance, a customer service AI agent could access customer purchase history and support tickets to quickly resolve customer issues.
Fraud Detection: AI agents can analyze financial transactions stored in MySQL databases to identify fraudulent activity. By leveraging machine learning algorithms, AI agents can detect patterns and anomalies that would be difficult for humans to identify, helping to prevent financial losses.
Personalized Recommendations: E-commerce platforms can use AI agents and pymcp to access customer purchase history and browsing behavior, providing personalized product recommendations to increase sales and customer satisfaction.

Key Features of pymcp

Pymcp offers a comprehensive set of features designed to facilitate seamless integration with MySQL databases and empower AI agents to perform a wide range of tasks. Here are some of its key features:

Python-Based: Pymcp is written in Python, a popular and versatile programming language that is widely used in the AI and data science communities. This makes it easy to integrate pymcp into existing Python-based AI agent development workflows.
FastMCP Framework: Pymcp is built upon the FastMCP framework, which provides a foundation for efficient and reliable communication between servers and clients.
MySQL Database Interaction: Pymcp provides a set of tools for interacting with MySQL databases, including the ability to execute SQL queries and retrieve data.
Server-Client Architecture: Pymcp follows a server-client architecture, allowing AI agents to connect to a central server and access MySQL data remotely.
Environment Configuration: Pymcp supports different environment configurations, allowing developers to easily switch between local, development, and production environments. This simplifies the development and deployment process.
Tool-Based Approach: Pymcp provides a set of pre-built tools that AI agents can use to perform common tasks, such as querying the database and describing available tools. This reduces the amount of custom code that developers need to write.
Secure Communication: Pymcp supports secure communication between the server and client, ensuring that sensitive data is protected.
Comprehensive Documentation: Pymcp comes with comprehensive documentation, making it easy for developers to understand how to use the project and integrate it into their AI agent development workflows.
Easy Installation: Installing pymcp is straightforward using pip install -r requirements.txt.

Integrating pymcp with UBOS

UBOS is a full-stack AI Agent Development Platform designed to empower businesses to build and deploy AI agents across various departments. By integrating pymcp with UBOS, you can unlock even greater potential for your AI agents.

UBOS provides a comprehensive set of tools and services for orchestrating AI agents, connecting them with enterprise data, building custom AI agents with your own LLM models, and creating multi-agent systems. With UBOS, you can:

Orchestrate AI Agents: UBOS provides a visual interface for designing and managing complex AI agent workflows. You can easily connect different AI agents together and define the flow of data between them.
Connect to Enterprise Data: UBOS provides connectors for a wide range of enterprise data sources, including MySQL, PostgreSQL, MongoDB, and more. This makes it easy to connect your AI agents to the data they need to perform their tasks.
Build Custom AI Agents: UBOS allows you to build custom AI agents using your own LLM models. You can train your models on your own data and deploy them directly to the UBOS platform.
Create Multi-Agent Systems: UBOS allows you to create multi-agent systems, where multiple AI agents work together to solve complex problems. This is particularly useful for tasks that require collaboration and coordination.

By leveraging pymcp within the UBOS platform, you can seamlessly integrate your AI agents with MySQL databases and unlock the full potential of your data. This allows you to build more intelligent, responsive, and effective AI-powered applications that drive business value.

Getting Started with pymcp on UBOS

To get started with pymcp on UBOS, simply follow these steps:

Install pymcp: Install pymcp using pip install -r requirements.txt.
Configure pymcp: Configure pymcp to connect to your MySQL database by setting the appropriate environment variables in src/env.py or src/env_dev.py.
Deploy pymcp: Deploy the pymcp server to your UBOS environment.
Connect your AI Agents: Connect your AI agents to the pymcp server and start querying your MySQL database.

Conclusion

Pymcp is a powerful and versatile tool that enables AI agents to seamlessly access and interact with MySQL databases. By leveraging the MCP framework and integrating with the UBOS platform, pymcp provides a robust and efficient solution for connecting AI agents to the data they need to perform their tasks effectively. Whether you’re building AI-powered data analysis tools, automated reporting systems, real-time data integration solutions, or customer service automation applications, pymcp can help you unlock the full potential of your MySQL data and drive business value.