How to Use the Botsonic MCP in OpenAI Agents SDK

Q: How do I connect Botsonic to the OpenAI Agents SDK?

Install openai-agents first. Initialize the MCP connection using MCPServerStreamableHttp with your Vinkius endpoint, then pass the server instance directly into your Agent constructor's mcpservers list.

Q: Can my OpenAI Agents SDK setup create new Botsonic bots dynamically?

Yes. Your agent can call createbot to set up fresh support bots for different departments or clients. It can then immediately populate them with data using the training tools.

Q: Does the Botsonic MCP Server support tool caching in OpenAI Agents SDK?

Yes, you can set cacheToolsList=True during setup. This keeps your OpenAI Agents SDK runs fast by avoiding redundant tool discovery calls on every single agent loop.

Q: How do I check if my Botsonic connection is alive?

Run the checkbotsonicstatus tool. Your agent can call this at startup to confirm the API credentials and connection are solid before handling user requests.

Connect OpenAI Agents SDK to Botsonic to spin up, train, and track custom support bots directly from your autonomous agent runs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Botsonic MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Bot Training with OpenAI Agents SDK

This MCP Server exposes tools like `add_knowledge_url` and `update_bot` so your agent can update support bots on the fly. When your system notices a new help doc or API change, the agent writes it straight to the bot's memory without human intervention. You don't have to copy-paste URLs into a dashboard anymore. Your agent handles the training pipeline, then runs `check_botsonic_status` to make sure the updates went through before routing live traffic.

Real-Time Conversation Routing

Your agent uses `get_conversation` and `list_conversations` to pull active user chats directly into your Python runtime. This lets your backend monitor ongoing support threads, analyze user sentiment, or flag issues that need a human handoff. Instead of polling APIs manually, your agent checks user messages via `send_message` to test bot responses. It keeps your support quality high by spotting bad answers before your customers do.

Lead and Analytics Extraction

The `list_leads` tool lets your agent pull contact info captured by your chat widgets directly into your CRM. No manual CSV exports, no broken webhooks, just clean lead data extracted by your automated pipeline. You can also query `get_bot_analytics` to track how well your support bots are performing over time. The agent reads the raw metrics, flags drops in resolution rates, and alerts your team when a bot needs better training data.

Setup guide

Set up Botsonic 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 Botsonic tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` first. Initialize the MCP connection using `MCPServerStreamableHttp` with your Vinkius endpoint, then pass the server instance directly into your Agent constructor's `mcp_servers` list.

Yes. Your agent can call `create_bot` to set up fresh support bots for different departments or clients. It can then immediately populate them with data using the training tools.

Yes, you can set `cacheToolsList=True` during setup. This keeps your OpenAI Agents SDK runs fast by avoiding redundant tool discovery calls on every single agent loop.

Run the `check_botsonic_status` tool. Your agent can call this at startup to confirm the API credentials and connection are solid before handling user requests.

Vinkius runs this MCP Server inside an isolated, ephemeral V8 sandbox. All captured leads, conversation histories, and bot analytics are processed securely, meaning Vinkius never persists your raw customer support logs or API tokens on its own servers.

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