How to Use the IBM watsonx MCP in OpenAI Agents SDK

Q: Can I use IBM watsonx with OpenAI Agents SDK to track tuning jobs?

Yes. You can invoke startmodeltuning to kick off a job and then poll gettuningstatus to monitor progress. It integrates into your agent's background tasks.

Q: Does IBM watsonx work with OpenAI Agents SDK for prompt management?

It does. You can use listprompts and createprompt to manage your assets directly from the agent. This allows your system to version control its own instructions.

Connect IBM watsonx to your OpenAI Agents SDK pipeline to get deterministic model responses and verified agent actions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBM watsonx MCP to OpenAI Agents SDK

Create your Vinkius account to connect IBM watsonx 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 IBM watsonx with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated model discovery for OpenAI Agents SDK

Your agent automatically maps the full watsonx toolset upon initialization. By passing the server configuration to your constructor, the system exposes `list_models` and `get_model_details` to the agent's logic layer immediately. This setup removes manual wiring. You get direct access to model metadata, allowing the agent to choose the right foundation model based on current availability and capability requirements.

Production-grade text generation and chat

Trigger `generate_text` or `generate_chat` directly from your agent's execution loop. These tools provide the raw output needed for your multi-turn conversations without leaving the OpenAI environment. Since you are using the SDK, your guardrails catch malformed outputs before they hit your downstream systems. It keeps the interaction grounded in the data returned by the watsonx API.

Embeddings for semantic agent memory

Plug `generate_embeddings` into your agent’s retrieval workflow to build smarter context. It turns unstructured input into vector data that your agent can use for similarity search across your internal datasets. This creates a tighter loop for your agent's knowledge base. You avoid the overhead of custom embedding pipelines by using the native watsonx endpoint directly within your agent process.

Setup guide

Set up IBM watsonx 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 IBM watsonx tools at runtime.
3

Create your Agent

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

Run the agent

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

Vinkius handles the auth layer, so you only need to manage the endpoint token. Keep this token in your environment variables and inject it into the MCP server configuration before the agent starts.

Yes. You can invoke `start_model_tuning` to kick off a job and then poll `get_tuning_status` to monitor progress. It integrates into your agent's background tasks.

It does. You can use `list_prompts` and `create_prompt` to manage your assets directly from the agent. This allows your system to version control its own instructions.

The connection is ephemeral and managed by Vinkius. Every request is isolated, ensuring no state leakage between your agent runs.

The server treats your text payloads as transient data. It only processes what you send to the endpoints, and Vinkius enforces a strict zero-trust sandbox for all traffic.

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