Prompts in MCP-Servern

Einführung in das Model Context Protocol (MCP)

James Chapman

AI Curriculum Manager, DataCamp

Was sind MCP-Prompts?

Prompts: wiederverwendbare Vorlagen, die LLMs für bestimmte Aufgaben optimieren

Workflows und Verhaltensweisen
Reduziert die Prompt-Last für Nutzer

Prompts

Warum braucht es Prompts?

mehrdeutige Eingaben

Der Zeitzonen-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.

→ Diesen Prompt für die Zeitzonenumrechnung bereitstellen

MCP-Server-Prompts definieren

@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}"""

Lokaler MCP-Server: 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")

Client: Prompts auflisten

async def list_prompts():
    """Alle verfügbaren Prompts vom MCP-Server auflisten."""
    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()

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

Client: Prompts auflisten

print(asyncio.run(list_prompts()))

Available prompts: ['convert_timezone_prompt']

Der Prompt-name ist nicht dasselbe wie der title

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

Client: Prompts auflisten

print(asyncio.run(list_prompts()))

Available prompts: ['convert_timezone_prompt']

Der Prompt-name ist nicht dasselbe wie der title

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

Im Client das Attribut .name verwendet (nicht .title)

Client: Prompts abrufen

async def read_prompt(user_input: str, prompt_name: str = "convert_timezone_prompt") -> str:
    """Einen Prompt mit Nutzereingabe vom MCP-Server abrufen."""
    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()

            # Prompt abrufen
            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?

Lass uns üben!

Einführung in das Model Context Protocol (MCP)