How to Use the Middesk MCP in Pydantic AI

Q: Can Middesk help my Pydantic AI agent with business prefilling?

Yes. Use prefillbusiness to get initial data and let your agent validate it against your internal records. It's a fast way to start a new verification.

Q: Does Pydantic AI require a specific transport for Middesk?

Use the MCPToolset with an HTTP or SSE transport. It's the standard way to connect and ensures your agent is running with the latest tool definitions.

Type-safe KYB verification for Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Middesk MCP to Pydantic AI

Create your Vinkius account to connect Middesk 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 Middesk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-validated business identity for Pydantic AI

Every response from `autocomplete_identity` is validated against your Pydantic models at runtime. If the registry returns malformed data, your agent triggers a clean validation error instead of hallucinating values. This is the only way to build a reliable compliance agent. You get the speed of API-driven verification with the safety of strict Python typing.

Strictly typed tax registration checks

Use `list_tax_registrations` to pull filing data that your agent can trust. Since Pydantic AI validates the schema immediately, you know the data matches your expected format before it hits your risk logic. This prevents silent bugs in your onboarding pipeline. Your agent handles the business logic, and the server ensures the data integrity remains high.

Verified document handling for Pydantic AI

Call `get_document` to pull specific files with full type safety. Your agent receives verified, structured objects, making it easy to build automated review loops without worrying about data corruption. It works for `list_businesses` too. You get a consistent, typed way to manage your entire merchant portfolio through your agent's interface.

Setup guide

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

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

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

The server provides structured data that fits your models perfectly. Simply define your Pydantic schemas, and the agent will enforce them every time a tool is called.

Yes. Use `prefill_business` to get initial data and let your agent validate it against your internal records. It's a fast way to start a new verification.

Use the `MCPToolset` with an HTTP or SSE transport. It's the standard way to connect and ensures your agent is running with the latest tool definitions.

Your agent will fail with a clear validation error. This prevents your agent from making a decision based on junk data or undefined fields.

Your identity and tax documents are never persisted. We use an ephemeral sandbox where data exists only for the duration of the tool execution, ensuring your sensitive business records stay off our servers.

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