support loading text prompts

[mr-brobot]

details in #11

any feedback welcome, including nits :)

usage example:

# math_server.py
from mcp.server.fastmcp import FastMCP

mcp = FastMCP("Math")

@mcp.tool()
def add(a: int, b: int) -> int:
    """Add two numbers"""
    return a + b

@mcp.tool()
def multiply(a: int, b: int) -> int:
    """Multiply two numbers"""
    return a * b

@mcp.prompt()
def quiz() -> str:
    return "what's (3 + 5) x 12?"

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

# Create server parameters for stdio connection
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client

from langchain_mcp_adapters.tools import load_mcp_tools
from langgraph.prebuilt import create_react_agent

from langchain_openai import ChatOpenAI
model = ChatOpenAI(model="gpt-4o")

server_params = StdioServerParameters(
    command="python",
    # Make sure to update to the full absolute path to your math_server.py file
    args=["/path/to/math_server.py"],
)

async with stdio_client(server_params) as (read, write):
    async with ClientSession(read, write) as session:
        # Initialize the connection
        await session.initialize()

        # Get tools
        tools = await load_mcp_tools(session)

        # Get prompt
        messages = await load_mcp_prompt(session, "quiz")

        # Create and run the agent
        agent = create_react_agent(model, tools)
        agent_response = await agent.ainvoke(messages)

[vbarda]

Thanks for adding -- looks good overall! Added a few small comments - could you add usage example to the PR description?

[mr-brobot]

@vbarda thanks for the feedback. i think i addressed everything. lmk if there's anything else i can do to help

[vbarda]

Thank you!