I am trying to use MCP adapters for Langgraph but I am running into an error:
server-1 | Traceback (most recent call last):
server-1 | File "/app/server.py", line 43, in <module>
server-1 | @asynccontextmanager
server-1 | NameError: name 'asynccontextmanager' is not defined
server-1 exited with code 1
when I place the following reference code for using the mcp adapters
# graph.py
from contextlib import asynccontextmanager
from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic
model = ChatAnthropic(model="claude-3-5-sonnet-latest")
@asynccontextmanager
async def make_graph():
async with MultiServerMCPClient(
{
"math": {
"command": "python",
# Make sure to update to the full absolute path to your math_server.py file
"args": ["/path/to/math_server.py"],
"transport": "stdio",
},
"weather": {
# make sure you start your weather server on port 8000
"url": "http://localhost:8000/sse",
"transport": "sse",
}
}
) as client:
agent = create_react_agent(model, client.get_tools())
yield agent.
langchain-ai/langchain-mcp-adapters
Does anyone know why I am getting this error:
NameError: name 'asynccontextmanager' is not defined
发布者：admin，转转请注明出处：http://www.yc00.com/questions/1744301301a4567515.html
评论列表（0条）