Mcplite

🚀 MCPlite

MCPlite is a Python MCP server framework similar to FastAPI. It enables developers to easily define and expose server-side functions (such as tools, functions, or resource access) that can be programmatically invoked by AI agents in the host application.

✨ Features

Core Concept

MCPlite aims to be a Python MCP server framework, similar to FastAPI. Its main purpose is to allow developers to easily define and expose server-side functions (such as tools, functions, or resource access), which can be programmatically invoked by AI agents in the host application.

graph LR
    subgraph "Client"
        A[Agent] -- Uses --> C[Client Library]
    end

    subgraph "Server"
        MCPF[MCPlite Framework] -- Uses --> SP[MCPlite Server Process]
        SP -- Listens on --> T[Transport Layer]
        SP -- Executes --> Logic[Server Logic]
        C -- Sends requests via --> T
        T -- Passes requests to --> SP
        SP -- Routes requests to --> Logic
        Logic -- Returns results --> SP
        SP -- Sends responses via transport layer --> T
        T -- Passes responses to --> C
        C -- Returns results --> A
    end

    style MCPF fill:#ccf,stroke:#333,stroke-width:2px,color:#333
    style SP fill:#e7cfff,stroke:#333,stroke-width:2px,color:#333
    style T fill:#f9f,stroke:#333,stroke-width:1px,color:#333
    style A fill:#ddd,stroke:#333,stroke-width:1px,color:#333
    style C fill:#ddd,stroke:#333,stroke-width:1px,color:#333
    style Logic fill:#fff,stroke:#333,stroke-width:1px,color:#333

Transmission Mode

• Core Concepts:
  • Server-side functions include tools, functions, or resource access, which can be invoked by agents.
  • The client library is responsible for communicating with the server, handling requests and responses.

Overall Goal

The MCPlite framework aims to connect high-level agent logic (possibly driven by LLMs) with specific server-side functions. It provides a standardized way for developers to expose functions and reliably discover and invoke these functions through the client library.

📦 Installation

No installation steps provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

# 从mcplite模块导入Server类
from mcplite import Server

class MyServer(Server):
    def add(self, a: int, b: int) -> int:
        return a + b

server = MyServer()
server.run()

Advanced Usage

Function Registration

• Each function has a unique identifier on the server.
• Supports various data types, such as integers, strings, and custom objects.

Client Communication

The client library interacts with the server through the JSON request format.

Example Request:

{
    "function": "add",
    "parameters": {
        "a": 5,
        "b": 3
    }
}

Function Discovery

The client can request the server to obtain a list of all available functions.

Example Response:

[
    {
        "name": "add",
        "parameters": ["a", "b"],
        "return_type": "int"
    }
]

Parameter Setting

client = MCPliteClient("http://localhost:8000")
result = client.call_function("add", a=5, b=3)
print(result)  # Output: 8

📚 Documentation

The overall goal of the MCPlite framework is to connect high-level agent logic (possibly driven by LLMs) with specific server-side functions. It provides a standardized way for developers to expose functions and reliably discover and invoke these functions through the client library.

🔧 Technical Details

No technical details provided in the original document, so this section is skipped.

📄 License

No license information provided in the original document, so this section is skipped.