How to Use the ThinkStack MCP in OpenAI Agents SDK

Q: How do I monitor bot performance with ThinkStack and OpenAI Agents SDK?

You track everything through conversation history. The listconversations tool lets you see a full log of chat sessions, making it easy to find usage patterns or bottlenecks.

Q: Can I list available bots using ThinkStack and OpenAI Agents SDK?

Yep, just call listbots. It gives your agent a clean manifest of every chatbot registered on the platform. You can then drill down into individual bot details with getbot.

Q: How do I add new data sources for ThinkStack and OpenAI Agents SDK?

You use the addsource tool. It crawls the content you point it toward, indexes it automatically, and makes that knowledge available to your deployed agents.

Q: Is there a way to see what actions are configured for ThinkStack and OpenAI Agents SDK?

Absolutely. The listactions tool shows you every defined action set. It’s crucial for understanding the operational scope of any bot your agent interacts with.

Deploy production AI systems using OpenAI Agents SDK: Reliable, traced bot management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ThinkStack MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run and monitor chatbot sessions

You can execute a query by sending input directly to the agent via `send_query`. This tool handles all chat logic, letting your AI client get immediate responses. It also keeps track of history through `list_conversations` and gives you details on specific chats with `get_conversation`, making auditing simple.

Manage bot definitions

`list_bots` lets your agent see every chatbot available in the system. If you need to know more about one, call `get_bot`. Beyond just listing them, `list_actions` shows exactly what those bots can do—read data, send messages, whatever it is. It’s essential for building reliable automation.

Control knowledge sources

Keep your agent's brain fresh by managing its source material. Use `add_source` to crawl and index new content automatically. You can also clean up old data using `delete_source`. Always check what you’ve got with `list_sources`; it shows every knowledge base connected to the MCP Server.

Setup guide

Set up ThinkStack 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 ThinkStack tools at runtime.
3

Create your Agent

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

Run the agent

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

You track everything through conversation history. The `list_conversations` tool lets you see a full log of chat sessions, making it easy to find usage patterns or bottlenecks.

Yep, just call `list_bots`. It gives your agent a clean manifest of every chatbot registered on the platform. You can then drill down into individual bot details with `get_bot`.

This server touches conversation details, which includes user inputs and chat history. When dealing with sensitive info, remember that the agent's actions must be logged and audited.

You use the `add_source` tool. It crawls the content you point it toward, indexes it automatically, and makes that knowledge available to your deployed agents.

Absolutely. The `list_actions` tool shows you every defined action set. It’s crucial for understanding the operational scope of any bot your agent interacts with.

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