How to Use the IBM watsonx MCP in AutoGen

Q: Are prompts managed via IBM watsonx in AutoGen?

Yes, agents can use listprompts and createprompt to manage their own instruction sets. This allows agents to evolve their behavior by saving and loading prompts based on previous successes.

Enable multi-agent debate with IBM watsonx tools inside your AutoGen conversation workflows.

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 AutoGen

Create your Vinkius account to connect IBM watsonx to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate watsonx outputs in AutoGen

Assign `generate_chat` to a specialized agent tasked with generating content, then have another agent critique it. AutoGen manages the negotiation between these agents using the tools provided by this server. This creates a system where model outputs are challenged and refined before being finalized. It is ideal for tasks requiring high accuracy through internal verification.

Orchestrate watsonx tuning with agents

Use an administrative agent to trigger `start_model_tuning` and monitor the status via `get_tuning_status`. If a job fails, the agent can decide whether to retry or alert a human user. This automates the maintenance of your custom models within the agentic workflow. It removes the need for manual oversight during the training lifecycle.

Manage watsonx projects with agents

Allow your agents to explore your account structure using `list_projects` and `list_prompts`. They can dynamically adjust their environment based on the available resources they find. This makes your multi-agent system self-configuring and aware of the available foundation models. It ensures your agents are always operating within the correct project boundaries.

Setup guide

Set up IBM watsonx MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes IBM watsonx tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="IBM watsonx_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent IBM watsonx data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="IBM watsonx_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent IBM watsonx data")
    print(result.messages[-1].content)

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 AutoGen

Configure the MCP adapter with your server URL and pass the resulting tool list to your AssistantAgent. The agents will automatically detect the functions and negotiate their use during the conversation.

Yes, by providing the watsonx tools to the agents, they can call them to perform text generation or embedding tasks during the debate process. This allows for real-time model interaction within the multi-agent loop.

AutoGen logs all tool calls and agent messages to your console or configured storage. You can monitor the interaction history to see exactly when and why the agents triggered a watsonx tool.

Yes, agents can use `list_prompts` and `create_prompt` to manage their own instruction sets. This allows agents to evolve their behavior by saving and loading prompts based on previous successes.

The server implements strict point-to-point communication for all tool calls. We ensure that your chat history and model tuning data are only accessible via your authorized credentials during the agent session.

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