Fetch Resource and Prompt from MCP

Your currency server exposes a resource (file://currencies.txt) and a prompt (convert_currency_prompt) that combine the user's request with task-specific context and rules. To feed an LLM, the client must fetch both in one go. Implement a helper function called get_context_from_mcp() that returns the resource text and the prompt text (with the user's query already in it) so the caller can build the message.

The currency_server.py file is available with a tool, resource, and prompt. Use the same session to read the resource and get the prompt with the user's input.

Diese Übung ist Teil des Kurses

<Kurs>Introduction to Model Context Protocol (MCP)</Kurs>

Kurs ansehen

Übungsanweisungen

Inside the session, call the method to read the resource at "file://currencies.txt".
Call the method to get the prompt by name with the user's input: use prompt name "convert_currency_prompt" and an arguments dict with key "currency_request" and value user_query.

Interaktive praktische Übung

Versuche dich an dieser Übung, indem du diesen Beispielcode vervollständigst.

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

async def get_context_from_mcp(user_query: str) -> tuple[str, str]:
    """Fetch resource content and prompt text from the MCP server."""
    params = StdioServerParameters(command=sys.executable, args=["currency_server.py"])

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

            # Read the resource (supported currencies)
            resource_result = await session.____("file://currencies.txt")
            resource_text = resource_result.contents[0].text

            # Get the prompt with the user's query
            prompt_result = await session.____("convert_currency_prompt",
                arguments={"currency_request": user_query})
            prompt_text = prompt_result.messages[0].content.text

            return resource_text, prompt_text

print(asyncio.run(get_context_from_mcp("How much is 50 GBP in euros?")))

Code bearbeiten und ausführen