MCP 伺服器中的 Prompts

Model Context Protocol（MCP）入門

James Chapman

AI Curriculum Manager, DataCamp

什麼是 MCP Prompts？

Prompts：可重用範本，用來最佳化 LLM 執行特定任務

工作流程與行為
降低使用者的提示負擔

為何需要 Prompting

時區轉換器的 Prompt

You are a timezone conversion engine.

Your task is to:
1. Extract the source datetime from the user's natural language input.
2. Identify the source timezone (explicit or inferred).
3. Convert the datetime into the target timezone.

Rules:
- If the date is ambiguous (e.g., "next Friday"), resolve it relative to the provided datetime.
- If the input cannot be resolved confidently, seek clarification.

→ 將此 prompt 暴露為時區轉換任務

定義 MCP 伺服器 Prompts

@mcp.prompt(title="Timezone Conversion")

def convert_timezone_prompt(user_input: str) -> str:

    return f"""You are a timezone conversion engine.

Your task is to:
1. Extract the source datetime...

Rules:
- If the date is ambiguous (e.g., "next Friday"), resolve it relative to the provided datetime.
- If the input cannot be resolved confidently, seek clarification.

    User's timezone conversion request: {user_input}"""

本機 MCP 伺服器：timezone_server.py

from mcp.server.fastmcp import FastMCP

mcp = FastMCP("Timezone Converter")

# Tools and resources from before...

@mcp.prompt(title="Timezone Conversion")
def convert_timezone_prompt(timezone_request: str) -> str:
    # ...

if __name__ == "__main__":
    mcp.run(transport="stdio")

用戶端：列出 Prompts

async def list_prompts():
    """List all available prompts from the MCP server."""
    params = StdioServerParameters(command=sys.executable, args=["timezone_server.py"])

    async with stdio_client(params) as (reader, writer):
        async with ClientSession(reader, writer) as session:
            await session.initialize()

            # List available prompts
            prompts = await session.list_prompts()
            print(f"Available prompts: {[p.name for p in prompts.prompts]}")

用戶端：列出 Prompts

print(asyncio.run(list_prompts()))

Available prompts: ['convert_timezone_prompt']

Prompt 的 name 與 title 不同

@mcp.prompt(title="Timezone Conversion")
def convert_timezone_prompt(timezone_request: str) -> str:
    # ...

用戶端：列出 Prompts

print(asyncio.run(list_prompts()))

Available prompts: ['convert_timezone_prompt']

Prompt 的 name 與 title 不同

# List available prompts
prompts = await session.list_prompts()
print(f"Available prompts: {[p.name for p in prompts.prompts]}")

在用戶端使用 .name 屬性（不是 .title）

用戶端：讀取 Prompts

async def read_prompt(user_input: str, prompt_name: str = "convert_timezone_prompt") -> str:
    """Retrieve a prompt from the MCP server with user input."""
    params = StdioServerParameters(command=sys.executable, args=["timezone_server.py"])

    async with stdio_client(params) as (reader, writer):
        async with ClientSession(reader, writer) as session:
            await session.initialize()

            prompts = await session.list_prompts()

            # Retrieve the prompt
            if prompts.prompts:
                prompt = await session.get_prompt(prompt_name, arguments={"timezone_request": user_input})

                print(f"Prompt result: {prompt.messages[0].content.text}")

            return prompt.messages[0].content.text

print(asyncio.run(read_prompt(user_input="It is 9:50 AM in the UK in January. What time is
    it in Lisbon, Portugal?")))

You are a timezone conversion engine.

Your task is to:
1. Extract the source datetime from the user's natural language input.
2. Identify the source timezone (explicit or inferred).
3. Convert the datetime into the target timezone.

Rules:
- If the date is ambiguous (e.g., "next Friday"), resolve it relative to the...
- If the input cannot be resolved confidently, seek clarification.

User's timezone conversion request: It is 9:50 AM in the UK in January. What time is it in
Lisbon, Portugal?

一起來練習吧！

Model Context Protocol（MCP）入門