How to Use the IBM watsonx MCP in Pydantic AI

Q: Can I use IBM watsonx with Pydantic AI for semantic search?

You can use generateembeddings to get vectors. You then define a Pydantic model to store and validate the resulting array structure before using it in your agent.

Q: How do I set up the IBM watsonx connection in Pydantic AI?

Install the MCP-compatible package and point the MCPToolset to your Vinkius server URL. Pydantic AI handles the transport and tool registration automatically.

Use IBM watsonx with Pydantic AI for type-safe model interactions and verified tool responses.

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 Pydantic AI

Create your Vinkius account to connect IBM watsonx 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 IBM watsonx with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe tool execution in Pydantic AI

Every response from `list_models` or `get_model_details` is validated against your Pydantic schemas. If the API structure shifts, your agent throws a validation error rather than crashing or hallucinating fields. This ensures your agent's state remains consistent. You define the expected structure, and the MCP server provides the data that matches your requirements.

Reliable text and chat generation

Call `generate_text` and `generate_chat` within your agent’s toolset. Pydantic AI enforces strict types on the input and output, making your interaction with watsonx models predictable. This is critical for production pipelines. You get clean, typed objects back from the foundation model, allowing for immediate integration into your business logic.

Prompt tuning and lifecycle control

Manage your tuning jobs with `start_model_tuning` and `get_tuning_status`. Because these are handled through the MCP server, you can wrap them in your own Pydantic models to track status updates precisely. This keeps your deployment workflow clean. You know exactly when a model is ready for use because the status check is integrated directly into your agent's typed response loop.

Setup guide

Set up IBM watsonx 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": {
        "ibm-watsonx-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent IBM watsonx 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 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 Pydantic AI

Pydantic AI checks every response against your defined models. If the data from `list_models` or other tools doesn't match, the agent triggers an error, preventing silent failures.

You can use `generate_embeddings` to get vectors. You then define a Pydantic model to store and validate the resulting array structure before using it in your agent.

Install the MCP-compatible package and point the `MCPToolset` to your Vinkius server URL. Pydantic AI handles the transport and tool registration automatically.

It is designed for reliable execution. By combining it with Pydantic AI, you get a robust layer of validation on top of the watsonx API responses.

Vinkius uses an ephemeral, zero-trust architecture. When your agent sends data like text for `generate_text` or `generate_embeddings`, it is processed through an isolated memory space.

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