Prompturi în serverele MCP

Introducere în Model Context Protocol (MCP)

James Chapman

AI Curriculum Manager, DataCamp

Ce sunt prompturile MCP?

 

Prompturi: șabloane reutilizabile care optimizează LLM-urile pentru sarcini specifice

  • Fluxuri de lucru și comportamente
  • Reduce sarcina de promptare a utilizatorilor

prompts.png

Introducere în Model Context Protocol (MCP)

Necesitatea promptării

ambiguous_inputs.png

Introducere în Model Context Protocol (MCP)

Promptul pentru conversia fusurilor orare

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.

→ Expunerea acestui prompt pentru sarcina de conversie a fusurilor orare

Introducere în Model Context Protocol (MCP)

Definirea prompturilor în serverul 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}"""
Introducere în Model Context Protocol (MCP)

Server 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")
Introducere în Model Context Protocol (MCP)

Client: Listarea prompturilor

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]}")
Introducere în Model Context Protocol (MCP)

Client: Listarea prompturilor

print(asyncio.run(list_prompts()))
Available prompts: ['convert_timezone_prompt']

name-ul promptului nu este același cu title-ul

@mcp.prompt(title="Timezone Conversion")
def convert_timezone_prompt(timezone_request: str) -> str:
    # ...
Introducere în Model Context Protocol (MCP)

Client: Listarea prompturilor

print(asyncio.run(list_prompts()))
Available prompts: ['convert_timezone_prompt']

name-ul promptului nu este același cu title-ul

# List available prompts
prompts = await session.list_prompts()
print(f"Available prompts: {[p.name for p in prompts.prompts]}")
  • S-a folosit atributul .name în client (nu .title)
Introducere în Model Context Protocol (MCP)

Client: Recuperarea prompturilor

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
Introducere în Model Context Protocol (MCP)
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?
Introducere în Model Context Protocol (MCP)

Să exersăm!

Introducere în Model Context Protocol (MCP)

Preparing Video For Download...