How to Use the Jira Service Management (JSM) MCP in LangChain

Q: Can I trace Jira Service Management (JSM) tool usage in LangChain with LangSmith?

Yes. Every tool call, such as getrequest or listqueues, is recorded as a run in LangSmith. You can monitor latency, input arguments, and raw JSON outputs directly in your tracing dashboard.

Q: What LangChain packages do I need to install for this setup?

Install langchain-mcp-adapters and langgraph via pip. This gives you the adapter classes to convert the server's tools into standard LangChain tools.

Run multi-step support chains in LangChain by connecting your agent directly to Jira Service Management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jira Service Management (JSM) MCP to LangChain

Create your Vinkius account to connect Jira Service Management (JSM) to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Jira Service Management (JSM) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain triage steps with absolute precision

`list_service_desks` identifies target support portals before your agent pulls active tickets. Your LangChain agent runs this check first, then pipes the ID directly into `list_requests` to gather summaries and keys. This chain removes human step-by-step intervention when sorting high-priority backlogs. You get full execution logs in LangSmith for every single tool call. When the agent uses `get_request` to fetch customer fields, you see the exact latency and payload size in your dashboard.

Build autonomous routing pipelines

`list_queues` reveals backlog counts and triage structures for your support desks. Your ReAct agent checks queue density and calls `list_request_types` to map incoming tickets to the correct team catalog. This setup lets your pipeline make routing decisions on the fly. Combining these MCP tools with your existing database integrations lets LangChain match incoming customer issues against known database records. The agent runs these checks in a single, unified execution graph.

Connect LangChain agents to JSM endpoints

`list_knowledge_bases` pulls down documentation links associated with your specific service desk configuration. Your LangChain agent reads this list via our MCP Server and matches the articles against active customer inquiries. The agent uses `list_customers` alongside `list_organizations` to pinpoint the exact account context. This ensures that the documentation retrieved matches the customer's actual service level agreement.

Setup guide

Set up Jira Service Management (JSM) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Jira Service Management (JSM) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "jira-service-management-jsm-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Jira Service Management (JSM) transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Jira Service Management. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Jira Service Management (JSM) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Jira Service Management (JSM) MCP in LangChain

LangChain uses the MultiServerMCPClient to connect directly to the managed endpoint. The agent resolves which tool, like `list_requests`, to call based on the prompt, executing it via standard HTTP transport.

Yes. Every tool call, such as `get_request` or `list_queues`, is recorded as a run in LangSmith. You can monitor latency, input arguments, and raw JSON outputs directly in your tracing dashboard.

You pass multiple MCP server configurations to the MultiServerMCPClient initialization block. This allows your agent to query `list_service_desks` from JSM while simultaneously pulling context from your other connected systems.

Install `langchain-mcp-adapters` and `langgraph` via pip. This gives you the adapter classes to convert the server's tools into standard LangChain tools.

All JSM requests, customer IDs, and queue lists are processed within a zero-trust, ephemeral V8 Isolate sandbox. Your API token never persists on disk, and the endpoint handles authentication over a single secure token, preventing exposure of raw credentials.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript