Prompts dans les serveurs MCP

Introduction au Model Context Protocol (MCP)

James Chapman

AI Curriculum Manager, DataCamp

Qu'est-ce qu'un prompt MCP ?

Prompts : modèles réutilisables qui optimisent les LLM pour des tâches spécifiques

Flux et comportements
Réduisent la charge de prompt pour les utilisateurs

Le besoin de prompting

Le prompt du convertisseur de fuseau horaire

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.

→ Exposez ce prompt pour la tâche de conversion de fuseau horaire

Définir des prompts côté serveur MCP

@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}"""

Serveur MCP local : 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 : lister les prompts

async def list_prompts():
    """Lister tous les prompts disponibles depuis le serveur MCP."""
    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()

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

Client : lister les prompts

print(asyncio.run(list_prompts()))

Available prompts: ['convert_timezone_prompt']

Le name du prompt n'est pas identique au title

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

Client : lister les prompts

print(asyncio.run(list_prompts()))

Available prompts: ['convert_timezone_prompt']

Le name du prompt n'est pas identique au title

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

Utilise l'attribut .name côté client (pas .title)

Client : récupérer des prompts

async def read_prompt(user_input: str, prompt_name: str = "convert_timezone_prompt") -> str:
    """Récupérer un prompt du serveur MCP avec une saisie utilisateur."""
    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()

            # Récupérer le 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?

Passons à la pratique !

Introduction au Model Context Protocol (MCP)