Sobot MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Sobot through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Sobot Assistant",
instructions=(
"You help users interact with Sobot. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Sobot"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Sobot MCP Server
Empower your AI agent to orchestrate your customer service with Sobot (智齿科技), the premier AI-driven customer support platform in China. By connecting Sobot to your agent, you transform complex ticketing management and agent coordination into a natural conversation. Your agent can instantly list your work orders, retrieve agent statuses, browse knowledge base articles, and even audit chat histories without you ever needing to navigate the comprehensive web interface. Whether you are managing a high-volume support team or a specific high-priority ticket, your agent acts as a real-time support operations assistant, keeping your data accurate and your customers satisfied.
The OpenAI Agents SDK auto-discovers all 10 tools from Sobot through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Sobot, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Ticket Management — List all active work orders, get detailed information, and create new tickets instantly.
- Agent Coordination — Browse support agents and monitor their real-time online/busy status.
- Knowledge Retrieval — List and retrieve content from your Sobot knowledge base to assist with customer queries.
- Chat Audit — Browse historical chat records and transcripts to track customer engagement.
- Service Insights — Retrieve high-level summaries of organization-wide support activity and performance.
The Sobot MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Sobot to OpenAI Agents SDK via MCP
Follow these steps to integrate the Sobot MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from Sobot
Why Use OpenAI Agents SDK with the Sobot MCP Server
OpenAI Agents SDK provides unique advantages when paired with Sobot through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Sobot + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Sobot MCP Server delivers measurable value.
Automated workflows: build agents that query Sobot, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Sobot, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Sobot tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Sobot to resolve tickets, look up records, and update statuses without human intervention
Sobot MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Sobot to OpenAI Agents SDK via MCP:
create_ticket
Create a new ticket
get_agent_status
Get agent online status
get_knowledge_detail
Get knowledge article details
get_org_summary
Get organization activity summary
get_ticket_details
Get ticket details
list_agents
List support agents
list_chat_history
List chat history
list_knowledge
List knowledge base articles
list_tickets
List customer support tickets
list_users
List customers/users
Example Prompts for Sobot in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Sobot immediately.
"List all active support tickets from Sobot."
"Check if agent 'Mario' is currently online."
"Search the knowledge base for 'refund policy'."
Troubleshooting Sobot MCP Server with OpenAI Agents SDK
Common issues when connecting Sobot to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Sobot + OpenAI Agents SDK FAQ
Common questions about integrating Sobot MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Sobot with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Sobot to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.