How to Use the Duda MCP in Pydantic AI

Q: How do I register the Duda MCP Server in Pydantic AI?

Instantiate an MCPToolset pointing to the Duda server URL in your Python code. Pydantic AI then registers all Duda tools like listsitetemplates automatically.

Q: Does Pydantic AI validate Duda template details?

Yes, when the agent calls gettemplatedetails, Pydantic AI validates the Duda JSON response. Any missing Duda template fields trigger an immediate Python error.

Q: Can Pydantic AI filter published Duda websites safely?

Yes, the agent runs listpublishedwebsites to fetch active Duda domains. Pydantic AI validates the status fields to ensure only published Duda sites are processed.

Q: How do I search for a specific Duda site using Pydantic AI?

Your agent executes the searchsitesbydomain tool to locate specific Duda properties. Pydantic AI ensures the returned Duda site object matches your schema.

Build type-safe Python agents with Pydantic AI that validate Duda site structures at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duda MCP to Pydantic AI

Create your Vinkius account to connect Duda 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 Duda with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Duda site discovery with Pydantic AI

Your agent uses `list_duda_sites` to parse Duda site registries into strict Pydantic AI models. This guarantees every Duda site identifier matches your Python type hints. If the Duda API returns unexpected fields, Pydantic AI halts the execution immediately. This prevents malformed Duda data from corrupting your Python application.

Validate Duda client profiles with zero silent errors

Query Duda permissions using `get_client_account_profile` and enforce clean Pydantic AI validation at runtime. The framework ensures all Duda user roles conform to your schemas. If a Duda user profile is corrupt, Pydantic AI raises a clear validation error. This keeps your Duda integration completely type-safe and reliable.

Strict MCP Server audits for dynamic Duda collections

Inspect dynamic Duda layouts by calling `list_site_collections` with strict MCP validation. This maps raw Duda schemas directly to validated Python objects. You can also run `quick_site_health_audit` to check Duda publishing rates. The toolset validates all Duda health metrics before Pydantic AI processes them.

Setup guide

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

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

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

Instantiate an `MCPToolset` pointing to the Duda server URL in your Python code. Pydantic AI then registers all Duda tools like `list_site_templates` automatically.

Yes, when the agent calls `get_template_details`, Pydantic AI validates the Duda JSON response. Any missing Duda template fields trigger an immediate Python error.

Yes, the agent runs `list_published_websites` to fetch active Duda domains. Pydantic AI validates the status fields to ensure only published Duda sites are processed.

Your agent executes the `search_sites_by_domain` tool to locate specific Duda properties. Pydantic AI ensures the returned Duda site object matches your schema.

All Duda domain names and health audit metrics are parsed in memory using an ephemeral V8 sandbox. No Duda database records are ever stored or cached by Vinkius.

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