How to Use the DealHub CPQ MCP in Pydantic AI

Q: How do I connect Pydantic AI to the DealHub CPQ server?

You'll use the MCPToolset class, passing it the Vinkius server URL. Then you add this toolset to your Agent's toolsets list. Pydantic AI handles the rest, making the DealHub CPQ tools available to your chosen LLM.

Add type-safe DealHub CPQ tools to any agent with Pydantic AI. Get validated, structured data for every quote and opportunity.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DealHub CPQ MCP to Pydantic AI

Create your Vinkius account to connect DealHub CPQ 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 DealHub CPQ with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Quote and Opportunity Creation

When your agent creates a deal, you need the data to be right. Pydantic AI validates every response from the DealHub server against your Pydantic models. When your agent calls `create_opportunity` or `create_quote`, you're getting a validated object, not just a JSON blob. If the server ever returns an unexpected field or the wrong data type, your code will raise a `ValidationError` immediately. This prevents silent data corruption from making its way into your system. It's about trusting the data structures your agent is working with.

Validated Data from Your MCP Server

Reading data needs to be just as reliable as writing it. When your agent uses `get_opportunity`, `list_quotes`, or `list_users`, Pydantic AI ensures the response fits the exact schema you've defined. No more defensive coding or checking for missing keys. This means you can build more robust workflows. Your agent can confidently chain commands, like using the output from `list_opportunities` to feed into `update_opportunity`, knowing the data at each step is clean and correct. It removes a whole class of runtime errors.

Use Any LLM for DealHub Tasks

Pydantic AI doesn't lock you into a specific model provider. You can use OpenAI, Gemini, Anthropic, or even a local model to power your agent. The framework handles the interaction with the DealHub MCP Server, so you can swap out the underlying LLM without rewriting your tool logic. This lets you choose the best model for the job. You might use a fast model for simple tasks like `get_quote_status` and a more powerful model for complex operations that might precede a call to `update_opportunity`. The tool definitions stay the same.

Setup guide

Set up DealHub CPQ 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": {
        "dealhub-cpq-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent DealHub CPQ 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 DealHub. 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 DealHub CPQ 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 DealHub CPQ MCP in Pydantic AI

Pydantic AI validates the JSON response for every tool call against a corresponding Pydantic model. If data from a tool like `get_opportunity` doesn't match the expected structure and types, it raises a `ValidationError` instead of letting your agent proceed with bad data.

You'll use the `MCPToolset` class, passing it the Vinkius server URL. Then you add this toolset to your `Agent`'s `toolsets` list. Pydantic AI handles the rest, making the DealHub CPQ tools available to your chosen LLM.

Yes, Pydantic AI and the MCP toolset are built for modern Python and fully support async operations. This is perfect for building responsive applications that can manage DealHub CPQ tasks without blocking your main thread.

Absolutely. Pydantic AI is model-agnostic. As long as you have a compatible LLM interface, you can use it to drive the DealHub CPQ tools. The framework separates the tool logic from the language model.

Your data's security is handled at the transport layer. Pydantic AI connects to the Vinkius MCP server over a secure, authenticated channel. The server itself is sandboxed, meaning your sensitive CPQ data (quotes, opportunities, user info) is processed in an isolated V8 Isolate for each request.

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