How to Use the Moxie MCP in Pydantic AI

Q: How does Pydantic AI ensure my agent creates a valid Moxie invoice?

When your agent calls createinvoice, the JSON response from the Moxie MCP server is parsed and validated against a Pydantic model. If any field is missing or has the wrong type, Pydantic AI raises an exception. Your code won't proceed with bad data.

Q: What happens if the Moxie MCP Server API changes unexpectedly when using Pydantic AI?

Your agent will fail loudly with a ValidationError. This is a core benefit—you'll know immediately that the contract between your agent and the API is broken, instead of discovering it through corrupted data downstream.

Q: Is the setup complicated?

No, it's straightforward. After pip install, you instantiate the MCPToolset with your Vinkius server URL and pass it to your agent. Pydantic AI handles the tool discovery and model generation for you.

Build agency automation that never fails silently. Connect to Moxie with Pydantic AI and get type-safe, validated results every time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moxie MCP to Pydantic AI

Create your Vinkius account to connect Moxie 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 Moxie with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Structurally Sound Client Management

This toolset lets your agent manage your client roster with guaranteed data structures. When your agent calls `create_client`, the response is automatically validated against a Pydantic model. If the API returns anything unexpected, your code raises a `ValidationError` immediately. The same principle applies to projects. You can `create_project` and `create_task` knowing that the IDs and statuses you get back are exactly what your application expects. No more defensive coding against malformed API responses.

Type-Safe Financial Operations with Pydantic AI

Stop worrying about silent data corruption in your billing system. Pydantic AI validates every field when your agent uses the `create_invoice` or `create_time_entry` tools. If a currency is wrong or a date is malformed, it stops cold. This makes your financial automation incredibly reliable. You can build an agent that runs `search_invoices` to check for overdue payments and trust that the data—dates, amounts, statuses—is 100% correct before you act on it. This MCP Server makes your agent accountable.

Reliable Internal Workflows

Use the `list_users` tool to get a properly structured list of your team members for task assignment. Your agent can then use `create_task`, and Pydantic AI ensures the assignee ID is a valid format before your code even sees it. This is perfect for building internal support bots. An agent can `create_ticket` and you'll know for sure that the response contains a valid ticket number and status. It removes an entire class of runtime errors from your code.

Setup guide

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

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

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

When your agent calls `create_invoice`, the JSON response from the Moxie MCP server is parsed and validated against a Pydantic model. If any field is missing or has the wrong type, Pydantic AI raises an exception. Your code won't proceed with bad data.

Yes. Pydantic AI is model-agnostic. You can use it with local models via Ollama, or with major providers like OpenAI and Anthropic, and it will handle the tool-calling and validation with Moxie consistently.

Your agent will fail loudly with a `ValidationError`. This is a core benefit—you'll know immediately that the contract between your agent and the API is broken, instead of discovering it through corrupted data downstream.

No, it's straightforward. After `pip install`, you instantiate the `MCPToolset` with your Vinkius server URL and pass it to your agent. Pydantic AI handles the tool discovery and model generation for you.

The server processes business operations data, including client and project records, financial details for invoices and expenses, and time entries. Security is handled by Vinkius; your connection uses a single, revocable token, and the server itself is stateless and isolated.

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