How to Use the watsonx Discovery MCP in OpenAI Agents SDK

Q: How do I use watsonx Discovery with the OpenAI Agents SDK?

Your agent uses the MCP tools, like querydiscoverycontent, to interact with watsonx Discovery. It's designed for agents that need real-time, document-backed answers rather than just general LLM knowledge.

Q: Can I list all available data collections using watsonx Discovery and the OpenAI Agents SDK?

Absolutely. The listdiscoverycollections tool lets your agent gather a full manifest of every collection in the project. This is how you keep track of where to run your queries.

Q: Does watsonx Discovery support sentiment analysis when using the OpenAI Agents SDK?

Yes, it does. The listavailableenrichments tool shows what NLP models are active, including Sentiment and Entities. This means your agent can enrich its search results before presenting them.

Run sophisticated searches on corporate data using watsonx Discovery with OpenAI Agents SDK.

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 OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Querying Complex Data

You pass a collection ID and the query text to `query_discovery_content`. This lets your agent run natural language queries or DQL against any specific discovery collection. The result is an analysis of complex data, providing AI-powered insights from watsonx Discovery. It's perfect for building agents that need to answer questions based on indexed corporate documents and structured data sets.

Managing Data Sources

Want to know what collections exist? Use `list_discovery_collections` to get a list of all available data collections in the project. This step lets your agent narrow down where it needs to search, preventing scope creep. Need to check specific documents? The `list_collection_documents` tool gets you a full inventory of every file indexed within a given collection.

Checking Component Health

`get_component_settings` retrieves the configuration and health settings for any project component. This lets your agent validate whether the underlying search infrastructure is running correctly before attempting a query. It's essential for building reliable agents; you can check status alongside using `get_document_details` to confirm metadata and indexing status on specific files.

Setup guide

Set up watsonx Discovery 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 watsonx Discovery tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent uses the MCP tools, like `query_discovery_content`, to interact with watsonx Discovery. It's designed for agents that need real-time, document-backed answers rather than just general LLM knowledge.

Absolutely. The `list_discovery_collections` tool lets your agent gather a full manifest of every collection in the project. This is how you keep track of where to run your queries.

Yes, it does. The `list_available_enrichments` tool shows what NLP models are active, including Sentiment and Entities. This means your agent can enrich its search results before presenting them.

You can run queries against structured data sets within a collection, using natural language or DQL. The system analyzes complex documents while keeping your agent's workflow tight.

It handles document metadata and configuration settings via tools like `get_document_details`. This lets your agent know not only *what* was found, but also its specific indexing status.

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