How do I query my chatbot via AI agent?

Use the `send_query` tool with the bot ID and your message. The chatbot responds based on its trained knowledge base.

Can I manage knowledge sources programmatically?

Yes. Use `add_source` to add new URLs, `list_sources` to browse, and `delete_source` to remove outdated sources from any chatbot.

How do I review chat conversations?

Use `list_conversations` to see all chats for a bot, then `get_conversation` to read the full message history of any specific session.

INSTANT PLUG AND PLAY

ThinkStack MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 10 tools to Add Source, Check Thinkstack Status, Delete Source, and more

Name: ThinkStack
Availability: InStock
Author: Vinkius

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect ThinkStack through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Use with Your AI Agent

Ask AI about this App Connector for OpenAI Agents SDK

Open in ChatGPT Open in Claude Open in Perplexity

The ThinkStack app connector for OpenAI Agents SDK is a standout in the Productivity category — giving your AI agent 10 tools to work with, ready to go from day one.

Vinkius delivers Streamable HTTP and SSE to any MCP client

python

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="ThinkStack Assistant",
            instructions=(
                "You help users interact with ThinkStack. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from ThinkStack"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 ThinkStack MCP Server

Connect your ThinkStack account to any AI agent and manage your chatbots, knowledge bases, and conversations through natural language.

The OpenAI Agents SDK auto-discovers all 10 tools from ThinkStack through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries ThinkStack, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Chatbot Management u2014 List and configure all AI chatbots in your account
Knowledge Base u2014 Add, list, and remove knowledge sources (URLs, documents) for any chatbot
Live Queries u2014 Send messages to your chatbots and receive AI-generated responses in real time
Conversation History u2014 Review all chat sessions with full message history and user metadata
Actions & Webhooks u2014 View all configured REST API actions for your chatbots

The ThinkStack 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.

All 10 ThinkStack tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to ThinkStack through Vinkius, your AI agent gets direct access to every tool listed below — spanning thinkstack, chatbot-api, ai-manage, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.

add_source

The content will be crawled and indexed automatically. Add a knowledge source

check_thinkstack_status

Verify ThinkStack API connectivity

delete_source

Remove a knowledge source

get_bot

Get chatbot details

get_conversation

Get conversation details

list_actions

List bot actions

list_bots

List all chatbots

list_conversations

List conversations

list_sources

List knowledge sources

send_query

Query a chatbot

Connect ThinkStack to OpenAI Agents SDK via MCP

Follow these steps to wire ThinkStack into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.

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 ThinkStack

Why Use OpenAI Agents SDK with the ThinkStack MCP Server

OpenAI Agents SDK provides unique advantages when paired with ThinkStack 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

ThinkStack + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the ThinkStack MCP Server delivers measurable value.

Automated workflows: build agents that query ThinkStack, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries ThinkStack, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through ThinkStack tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query ThinkStack to resolve tickets, look up records, and update statuses without human intervention

Example Prompts for ThinkStack in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with ThinkStack immediately.

"List all my chatbots in ThinkStack."

"Ask my Support Bot: 'How do I reset my password?'"

"Add docs.example.com as a knowledge source for my Sales bot."

Troubleshooting ThinkStack MCP Server with OpenAI Agents SDK

Common issues when connecting ThinkStack to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

ThinkStack + OpenAI Agents SDK FAQ

Common questions about integrating ThinkStack MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use 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?

Yes. Pass a list of 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?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.