Forums

Articles
Create
cancel
Showing results for 
Search instead for 
Did you mean: 

Integrating with Langgraph Agents

KishoreKumar_D
I'm New Here
I'm New Here
Those new to the Atlassian Community have posted less than three times. Give them a warm welcome!
December 18, 2025

Run this in the terminal:
npx -y mcp-remote https://mcp.atlassian.com/v1/sse

You will have to to do this:

  1. When a supported MCP client connects to the Rovo MCP Server, it launches a browser window.

  2. You will be prompted to log in using your Atlassian account.

  3. After logging in, you will be asked to select the apps you want and approve a list of scopes (permissions) that the client needs.

  4. Once authorized, the client receives an access token scoped to your user and cloud site.

  5. This token is used to authenticate and stream content securely.

And this is my sample client code that i created:

from langchain_mcp_adapters.client import MultiServerMCPClient
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
import asyncio

load_dotenv()

async def main():
client = MultiServerMCPClient(
{
"atlassian": {
"transport": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-remote",
]
}
}
)

tools = await client.get_tools()
# print(tools)
agent = create_agent("openai:gpt-4o-mini", tools)
response = await agent.ainvoke({"messages": " Create a Jira ticket for a bug in the login page at sample space"})
#print last AIMessage
# print(response["messages"])
print(response["messages"][-1].content)
if __name__ == "__main__":
asyncio.run(main())


This created a ticket in the Jira dashboard


0 comments

Comment

Log in or Sign up to comment
TAGS
AUG Leaders

Atlassian Community Events