Chatdata MCP Server

🚀 ChatData MCP Server

ChatData MCP Server is a service application based on the Model Control Protocol (MCP), integrating a rich set of tools and a prompt system to enhance the capabilities of large language models.

🚀 Quick Start

ChatData MCP Server is a flexible framework that enables interaction with large language models via the MCP protocol. It comes with the following core features:

• Execute Tool Functions: Offers a variety of predefined tools such as network operations and data processing.
• Use Prompt Templates: Incorporates multiple prompt templates to facilitate the rapid generation of high - quality responses.
• Access Resources: Allows direct access to text, binary data, and dynamically generated content.
• Communication Modes: Supports both stdio and SSE communication modes.

✨ Features

Tool System

The tool system is divided into several categories:

• Network Tools: Include web page scraping, IP information query, and HTTP client.
• Data Processing Tools: Provide data conversion, text summarization, and calculator functions.
• Development Assistance Tools: Support code formatting and PostgreSQL database queries.
• Multimedia Tools: Can generate images.
• Utility Tools: Include functions like translation and weather query.

Prompt System

The prompt system provides a variety of preset templates for quickly generating high - quality responses. Each prompt has a specific description and parameter explanation.

Resource System

The resource system allows direct access to various types of data:

• Text Resources
• Binary Resources
• Dynamically Generated Resources

Server Components

The server supports two communication modes:

• Default stdio Mode: Can be used directly without additional configuration.
• SSE Mode: Start by specifying a port.

📦 Installation

1. Create and activate a virtual environment.
2. Install project dependencies using pip.
3. Start the server by choosing a communication mode as needed:
   • Default stdio mode: python main.py
   • SSE mode: python main.py --sse-port 8000

📚 Documentation

Adding New Tools

1. Create a new file in the tools/ directory.
2. Implement the main function and calling function of the tool.
3. Return the tool definition for system recognition.

Example code:

import mcp.types as types

def my_tool_function(args):
    # Tool implementation
    pass

def get_tools():
    return [
        types.Tool(
            name="my_tool",
            description="Tool description",
            func=my_tool_function,
            args={
                "arg1": {
                    "type": "string",
                    "description": "Argument description"
                }
            }
        )
    ]

Adding New Prompts

1. Create a new file in the prompts/ directory.
2. Implement the prompt generation function.
3. Return the prompt definition.

Example code:

import mcp.types as types

def my_prompt(context=None, topic=None):
    # Prompt implementation
    pass

def get_prompts():
    return [
        types.Prompt(
            name="my_prompt",
            description="Prompt description",
            func=my_prompt,
            args={
                "context": {
                    "type": "string",
                    "description": "Context information"
                }
            }
        )
    ]

Adding New Resources

1. Create a new file in the resources/ directory.
2. Define the resource content and reading function.
3. Return the resource definition.

Example code:

import mcp.types as types

RESOURCES = {
    "my_resource": "Resource content"
}

def get_resources():
    return [
        types.Resource(
            uri=f"file://{name}.txt",
            name=name,
            description="Resource description",
            mimeType="text/plain"
        )
        for name in RESOURCES.keys()
    ]

def read_resource(name: str) -> str | bytes:
    return RESOURCES.get(name)

📄 License

This project is licensed under the MIT License, allowing free use and modification.