How to Use the watsonx Discovery MCP in AutoGen

Achieve consensus on complex tasks using watsonx Discovery with AutoGen agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect watsonx Discovery MCP to AutoGen

Create your Vinkius account to connect watsonx Discovery 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 watsonx Discovery with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulate Debate and Consensus

AutoGen lets multiple agents discuss the best approach. One agent might use `list_available_enrichments` to identify potential risk models, while another uses `get_component_settings` to check operational stability. The final answer isn't just from one tool; it’s a consensus derived from competing perspectives.

Multi-Agent Data Investigation

Need to assess data comprehensively? You can set up agents whose job is to check different facets. One agent calls `list_discovery_collections` to map the landscape, and a second agent uses `query_discovery_content` against that mapped collection. This simulates a full-scope investigation where multiple perspectives are required.

Structured Information Gathering

The agents can work together to gather precise details. One might query the status of documents using `get_document_details`, while another uses `list_collection_documents` to verify volume. They debate which findings are most critical. This process ensures all necessary checks—metadata, volume, and status—are covered before a final decision is reached.

Setup guide

Set up watsonx Discovery 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 watsonx Discovery 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="watsonx Discovery_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent watsonx Discovery 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="watsonx Discovery_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent watsonx Discovery 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 watsonx Discovery. 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 watsonx Discovery 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 watsonx Discovery MCP in AutoGen

AutoGen passes the MCP Server tools to its agents. The agents then decide, through conversation and deliberation, which tool—like `list_discovery_collections` or `query_discovery_content`—to call and in what order.

Yes. By assigning roles to agents (e.g., 'Security Analyst,' 'Performance Checker'), you force them to debate the findings, leading to a higher quality decision than any single tool call could provide.

The server touches metadata, component configurations, and document identifiers. The agents use these pieces of information to formulate their arguments and reach a final conclusion.

It is highly reliable because the deliberation process acts as an internal validation loop. Agents check each other's work, ensuring that single points of failure or misinterpretation are caught before the answer is finalized.

You pass all available tools from various MCP Servers to the AssistantAgent constructor. This lets the agents treat the entire toolset as a shared resource pool during their debate.

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