How to Use the LawPay MCP in Pydantic AI

Q: Does LawPay work with Pydantic AI for refunds?

Yes. You can use the createrefund tool safely by enforcing strict models for transaction IDs and amounts in your agent's logic.

Get type-safe legal billing with Pydantic AI and LawPay, ensuring every invoice and refund matches your firm's strict financial schema.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LawPay MCP to Pydantic AI

Create your Vinkius account to connect LawPay 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 LawPay with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Runtime schema validation for Pydantic AI

Every response from `get_transaction` or `list_invoices` is checked against your Pydantic models. If the server returns a malformed record, the agent stops immediately. This prevents silent errors in your billing workflow. You get guaranteed data structures every time you call a tool, keeping your firm's financial records consistent and accurate.

Safe IOLTA transaction execution in Pydantic AI

The server provides `create_refund` and `create_invoice` tools that your agent uses to manage client funds. Because you define the Pydantic models, you can enforce strict constraints on refund amounts. Your agent checks the account type via `get_account_info` before committing any transaction. This double-check ensures you never accidentally pull from a trust account.

Efficient account monitoring with Pydantic AI

The agent uses `list_accounts` and `get_account_stats` to maintain a real-time view of your firm's ledgers. It maps the data to your models for easy visualization. This allows for proactive financial management. You can identify pending settlements or low-balance accounts by checking the output from `list_settlements` against your defined expectations.

Setup guide

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

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

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

It provides type-safe validation for every tool call. You define the structure for `create_invoice`, and the agent fails if the server output deviates.

Yes. You can use the `create_refund` tool safely by enforcing strict models for transaction IDs and amounts in your agent's logic.

You create a custom Pydantic model for account checks. The agent verifies that the account returned by `get_account` is an operating account before proceeding.

Your agent will raise a validation error. This prevents the agent from hallucinating or using data that doesn't match your firm's internal schema.

The server returns only the specific fields needed for your models. Sensitive financial identifiers are processed through typed interfaces, preventing direct exposure in your agent's state.

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