How to Use the Desku.io MCP in OpenAI Agents SDK

Q: How do I connect the Desku.io MCP to OpenAI Agents SDK?

Install the package via pip and configure MCPServerStreamableHttp with your Vinkius URL. Pass it into the mcpservers array in your Agent constructor. Set cacheToolsList=True to speed up initialization.

Q: Can OpenAI Agents SDK read Desku.io ticket history?

Yes. The agent calls listconversations to pull the thread for any specific ticket ID. It then uses that context to draft a reply or summarize the issue.

Build production customer support systems with OpenAI Agents SDK and the Desku.io MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Desku.io MCP to OpenAI Agents SDK

Create your Vinkius account to connect Desku.io 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 Desku.io with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe ticket routing with OpenAI Agents SDK

Desku.io handles your inbound queue while your agent decides who takes the case. You plug the MCP Server into your agent constructor and let it pull the queue using `list_tickets`. The framework's built-in guardrails ensure the agent assigns the right priority before calling `update_ticket`. Handoffs between specialized agents work perfectly here. A billing agent checks `get_customer` for payment history, then passes the context to a technical agent that reads `list_conversations` to formulate a reply. You see the entire chain in your OpenAI dashboard.

Formulate replies with full context

Support agents hate reading endless threads. Your deployed product does it instantly. When a new message hits, the system triggers `get_ticket` to grab the metadata. Then it digs deep. Calling `list_conversations` pulls the entire back-and-forth history. The agent formulates a response, checks it against your safety constraints, and fires off `create_conversation` to reply directly to the user.

Map workloads across your team

Assigning cases blindly creates bottlenecks. Your OpenAI system can check who is actually available by calling `list_agents`. It maps the incoming issue type to the right human. Once the match is made, the agent runs `update_ticket` to set the assignee. Every action happens through the Vinkius endpoint token, keeping your auth completely isolated from the raw script.

Setup guide

Set up Desku.io 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 Desku.io tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Desku.io 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="Desku.io Agent",
            instructions="You have access to Desku.io 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 Desku.io. 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 Desku.io 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 Desku.io MCP in OpenAI Agents SDK

Install the package via pip and configure `MCPServerStreamableHttp` with your Vinkius URL. Pass it into the `mcp_servers` array in your Agent constructor. Set `cacheToolsList=True` to speed up initialization.

Yes. The agent calls `list_conversations` to pull the thread for any specific ticket ID. It then uses that context to draft a reply or summarize the issue.

The framework handles the handoff, while the server provides the tools. A triage agent can use `get_ticket` and then transfer execution to a specialized agent to run `create_conversation`.

You define strict guardrails in your OpenAI setup. If you only want an agent reading data, you write rules preventing it from executing `update_ticket` or `create_ticket`.

Vinkius runs this MCP Server in an ephemeral V8 Isolate Sandbox. When your agent pulls names and emails via `get_customer`, the data passes through a zero-trust tunnel directly to your client. No data persists on our infrastructure after the session closes.

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