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

Q: How do I configure the Jira Service Management (JSM) MCP Server using Pydantic AI?

Use MCPToolset with your Vinkius HTTP endpoint. Pass this toolset into the Agent constructor to give your model access to tools like listrequests and listqueues.

Q: Is the legacy HTTP client supported for this server?

No, use the unified MCPToolset approach. The legacy HTTP client is deprecated, so stick to the modern toolset import for your connection.

Validate Jira Service Management ticket structures and queues at runtime using type-safe Pydantic AI agent toolsets.

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 Pydantic AI

Create your Vinkius account to connect Jira Service Management (JSM) to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe ticket retrieval in Pydantic AI

The `get_request` tool retrieves full ticket descriptions and custom fields, validating the raw payload against strict Pydantic models. If JSM returns unexpected schemas, your Pydantic AI agent fails immediately instead of processing corrupted data using our MCP Server tool definitions. This strict parsing ensures your code never encounters null errors when reading ticket participants. You get absolute type safety when inspecting individual customer inquiries.

Validate queues and service desks

The `list_queues` tool pulls active queues for a service desk, ensuring the queue names and backlog counts match your Python schemas. Your Pydantic AI agent uses this clean data to safely route tickets. To find the right desk first, the agent runs `list_service_desks`. This ensures your agent is targeting a valid project key before attempting to query any queues via the MCP protocol.

Structured customer tracking

The `list_customers` tool fetches all users associated with a service desk, enforcing strict type validation on email and account structures. This prevents your agent from handling malformed customer profiles. For corporate tiers, `list_organizations` validates the business entities linked to those customers. Your agent can safely group support requests without risk of silent data corruption.

Setup guide

Set up Jira Service Management (JSM) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "jira-service-management-jsm-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Jira Service Management (JSM) tools.",
)

result = await agent.run("List recent Jira Service Management (JSM) transactions")
print(result.output)

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 Pydantic AI

Use `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset into the `Agent` constructor to give your model access to tools like `list_requests` and `list_queues`.

The framework raises a validation error at runtime. This prevents your agent from hallucinating properties or executing logic on malformed JSM ticket payloads.

Yes. Because Pydantic AI is model-agnostic, you can connect your JSM toolset to OpenAI, Anthropic, or local LLMs while maintaining strict schema validation.

No, use the unified `MCPToolset` approach. The legacy HTTP client is deprecated, so stick to the modern toolset import for your connection.

Your knowledge base metadata and ticket keys are validated entirely within your local runtime. The Vinkius MCP Server handles authorization token exchange securely over HTTPS, never caching your JSM content.

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