How to Use the watsonx Discovery MCP in Pydantic AI

Q: How does Pydantic AI interact with watsonx Discovery?

Pydantic ensures the data coming out of watsonx Discovery is correct. When your agent uses tools like querydiscoverycontent, it validates that the response structure matches your Python models, preventing runtime errors.

Q: Can I list all available data collections using watsonx Discovery and Pydantic AI?

Yes. The listdiscoverycollections tool provides a validated list of every collection in the project. You'll always get predictable results, which is what you want.

Q: Does watsonx Discovery support enrichment models with Pydantic AI?

It does. The listavailableenrichments tool lets your agent see applied NLP models like Sentiment and Entities. This information is validated, so you know exactly what kind of analysis the results contain.

Q: What data types can I query with watsonx Discovery and Pydantic AI?

You run queries using querydiscoverycontent. The core benefit here is that even when querying complex documents, the final output structure you receive from the MCP Server is reliable.

Q: What kind of metadata does watsonx Discovery handle when using Pydantic AI?

It handles system settings and document metadata. The getdocumentdetails tool retrieves this information, and Pydantic guarantees that the data types—like status and date fields—are correct.

Build guaranteed correct search workflows with watsonx Discovery and Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect watsonx Discovery to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Running Type-Safe Queries

To query data, your agent calls `query_discovery_content` by passing a collection ID and the query text. Because of Pydantic validation, you're guaranteed that any output structure from watsonx Discovery matches exactly what your code expects. This removes silent failures. It’s perfect for building production systems where data integrity is non-negotiable.

Managing Data Sources

Need to know what collections exist? Use `list_discovery_collections` to get a validated list of all available data collections. The results pass through Pydantic, meaning you don't have to worry about unexpected field names. When you need file-level visibility, `list_collection_documents` gives you an accurate inventory of documents in a collection.

Validating System Components

`get_component_settings` retrieves the configuration and health status for any project component. This tool output is immediately validated, confirming system readiness before your agent proceeds to query data. Checking specific files uses `get_document_details`, ensuring that all metadata retrieved adheres strictly to defined Python models.

Setup guide

Set up watsonx Discovery MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "watsonx-discovery-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to watsonx Discovery tools.",
)

result = await agent.run("List recent watsonx Discovery transactions")
print(result.output)

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 Pydantic AI

Pydantic ensures the data coming *out* of watsonx Discovery is correct. When your agent uses tools like `query_discovery_content`, it validates that the response structure matches your Python models, preventing runtime errors.

Yes. The `list_discovery_collections` tool provides a validated list of every collection in the project. You'll always get predictable results, which is what you want.

It does. The `list_available_enrichments` tool lets your agent see applied NLP models like Sentiment and Entities. This information is validated, so you know exactly what kind of analysis the results contain.

You run queries using `query_discovery_content`. The core benefit here is that even when querying complex documents, the final output structure you receive from the MCP Server is reliable.

It handles system settings and document metadata. The `get_document_details` tool retrieves this information, and Pydantic guarantees that the data types—like status and date fields—are correct.

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