How to Use the Denim MCP in Pydantic AI

Q: How do I initialize the Denim MCP toolset in Pydantic AI?

You import MCPToolset from the library and pass your Vinkius HTTP URL. Then, add this toolset directly to your Agent constructor using the toolsets argument.

Build type-safe marketing agents with Denim 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 Denim MCP to Pydantic AI

Create your Vinkius account to connect Denim 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 Denim with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Denim data validation in Pydantic AI

The `list_audience_segments` tool returns your configured targeting groups as strictly typed Python models. Pydantic AI validates this payload at runtime, ensuring your agent never processes corrupt segment lists. If the API response format ever changes, your code fails loudly and immediately. This prevents silent failures that could lead to sending campaigns to the wrong audience.

Safely import new leads with zero silent errors

The `add_new_contact` tool registers new leads into your Denim CRM with strict field validation. The framework guarantees that phone numbers, emails, and custom attributes match your schemas before hitting the database. This setup blocks malformed contact details from reaching your database. It saves your marketing team from manual cleanups of broken email addresses.

Load and validate email templates programmatically

The `list_email_templates` tool pulls your marketing layouts into Pydantic AI for structural validation. Your agent can inspect the HTML and text placeholders to verify that required merge tags are present. This ensures your automated emails never go out with missing customer names or broken links. Our MCP server handles the heavy lifting of fetching the templates safely.

Setup guide

Set up Denim 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": {
        "denim-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You import `MCPToolset` from the library and pass your Vinkius HTTP URL. Then, add this toolset directly to your `Agent` constructor using the `toolsets` argument.

Yes, every response from Denim is validated against Pydantic models. If an endpoint returns unexpected fields, the framework raises a validation error immediately rather than letting your agent hallucinate.

Absolutely, Pydantic AI is model-agnostic. You can run Denim tools using Anthropic, Gemini, or even local models like Ollama without changing your tool configuration.

No, Vinkius hosts the server externally. You only need to provide the secure HTTP endpoint URL to your `MCPToolset` instance, which avoids managing local runtimes.

All CRM data, email templates, and audience segment structures are isolated in single-use V8 sandboxes. Vinkius secures the transport with end-to-end TLS encryption and never stores your marketing keys or contact lists.

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