How to Use the Jitbit MCP in OpenAI Agents SDK

Q: How do I connect the Jitbit MCP Server to the OpenAI Agents SDK?

Instantiate the MCPServerStreamableHttp client with your Vinkius endpoint URL inside your Python script. Pass that server instance inside the mcpservers list when initializing your OpenAI Agents SDK agent to auto-discover all Jitbit ticket and user tools instantly.

Q: How does the OpenAI Agents SDK handle ticket categories in Jitbit?

Your agent calls listticketcategories to fetch the current setup from your Jitbit helpdesk. The OpenAI Agents SDK then uses that specific list to classify new issues before executing createsupportticket, ensuring no tickets end up uncategorized.

Run safe, production-grade IT support workflows that manage Jitbit tickets using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jitbit MCP to OpenAI Agents SDK

Create your Vinkius account to connect Jitbit to OpenAI Agents SDK 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 Jitbit with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded ticket creation in production

Keep your Jitbit support queue clean. This integration lets your OpenAI Agents SDK run safety checks before invoking `create_support_ticket` via the MCP. If an incoming user request passes your OpenAI Agents SDK validation layer, the agent grabs the context and opens the issue in the right Jitbit category. This prevents the typical mess of automated triaging systems, keeping your Jitbit SLA response times low.

Smart agent handoffs for complex IT issues

Some Jitbit tickets need a tier-two engineer, not an automated script. When your primary OpenAI Agents SDK run spots a critical infrastructure failure inside `get_ticket_details`, it instantly hands the conversation off to a specialized technical agent. This handoff happens entirely within your OpenAI Agents SDK environment, passing the full Jitbit ticket history along. The new agent can query `list_kb_articles` to find known workarounds or assign the issue to the correct staff member without losing the thread.

Audit Jitbit MCP Server actions via OpenAI dashboard

Monitoring what your agents do in your helpdesk is critical for compliance. Because this MCP Server exposes direct Jitbit tools like `list_tickets` and `list_account_users`, every single call shows up in your OpenAI tracing dashboard. You can inspect the exact parameters the OpenAI Agents SDK sent and see the raw JSON returned from your Jitbit helpdesk. It makes debugging failed API calls straightforward and ensures your automated support pipelines remain completely transparent.

Setup guide

Set up Jitbit MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Jitbit tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Jitbit tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Jitbit tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Jitbit Agent",
            instructions="You have access to Jitbit tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Jitbit. 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 Jitbit 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 Jitbit MCP in OpenAI Agents SDK

Instantiate the `MCPServerStreamableHttp` client with your Vinkius endpoint URL inside your Python script. Pass that server instance inside the `mcp_servers` list when initializing your OpenAI Agents SDK agent to auto-discover all Jitbit ticket and user tools instantly.

Yes. You can control this by setting up distinct agent roles in your OpenAI Agents SDK Python code. For instance, restrict your tier-one agent so it only calls `list_kb_articles` and `get_ticket_details`, keeping write tools like `create_support_ticket` locked down.

Your agent calls `list_ticket_categories` to fetch the current setup from your Jitbit helpdesk. The OpenAI Agents SDK then uses that specific list to classify new issues before executing `create_support_ticket`, ensuring no tickets end up uncategorized.

The OpenAI Agents SDK raises an exception that your Python code can catch. You can configure fallback behaviors, like routing the conversation to a human agent, if `get_ticket_details` or `list_tickets` returns a Jitbit API error.

We run your connection in a secure V8 sandbox. Your Jitbit ticket descriptions, user emails, and internal KB articles never store on our platform, passing directly between your OpenAI Agents SDK system and your helpdesk instance over encrypted channels.

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