How to Use the Sobot MCP in OpenAI Agents SDK

Build production agents with OpenAI Agents SDK that manage customer support via Sobot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sobot MCP to OpenAI Agents SDK

Create your Vinkius account to connect Sobot to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sobot with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Manage Support Tickets

When a user needs help, your agent handles the whole lifecycle. It can use `create_ticket` to log new issues and then check details using `get_ticket_details`. This ensures no request falls through the cracks. You can also pull a list of existing customer reports with `list_tickets` or find out who needs help right now by checking agent status via `get_agent_status`. It keeps your operational view clean.

Know Your Users and Agents

Need context on the people involved? The SDK lets you pull a roster of users using `list_users` or check who's available in support with `list_agents`. This gives your agent immediate visibility into its workforce. For deep background checks, it pulls organizational summaries via `get_org_summary`, giving your AI client the full picture before making a recommendation. It’s solid context for complex interactions.

Access Knowledge and History

The agent doesn't have to guess. You can load up all available information using `list_knowledge` or grab specific articles with `get_knowledge_detail`. This ensures the response is always backed by company data. Plus, you get full conversational history through `list_chat_history`, so your AI client never forgets what was said earlier. It’s built for continuous, reliable conversations.

Setup guide

Set up Sobot 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 Sobot tools at runtime.
3

Create your Agent

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

Run the agent

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

Sobot exposes all its functionality as auto-discoverable tools that your agent can call. Your AI client just needs to know the tool name, and it handles the rest of the execution flow.

The built-in guardrails validate agent actions before running them. If an action fails—say, updating a ticket—the agent stops and reports the precise failure point, preventing data corruption.

The MCP Server touches user details, specifically customer names and email addresses. You maintain control over how your agent uses this PII via the structured calls to `list_users`.

Absolutely. The architecture is designed for production use, not just testing. Full tracing in the dashboard lets you audit every single action your agent takes against the MCP Server.

You get full visibility through the dedicated OpenAI dashboard. Every tool call, every guardrail check, and every successful operation is logged for review.

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