How to Use the PreciseFP MCP in Pydantic AI

Q: Can I use Pydantic AI to create a new client in PreciseFP and immediately send them a form?

Absolutely. Your agent would call createperson first. Then, using the returned person ID, it would call createformengagement. Pydantic AI ensures the ID passed between these two steps is handled correctly.

Q: What happens if the PreciseFP API changes and my Pydantic AI agent isn't updated?

Your agent will fail loudly with a ValidationError. This is a feature, not a bug. It prevents your application from running with mismatched data, alerting you that the API contract has changed.

Q: Is the setup for PreciseFP and Pydantic AI complicated?

It's quite direct. You install pydantic-ai-slimmcp, then create an MCPToolset instance with the server URL. This toolset is then passed to your agent, which handles the rest.

Q: How does Pydantic AI handle the privacy of sensitive person data from PreciseFP?

The person data itself is only in memory during the agent's operation. Vinkius provides an ephemeral, sandboxed environment for each API call, and the connection is secured end-to-end. Pydantic AI's role is to ensure that data, while in use, conforms to your expected structure.

Onboard financial clients with type-safe certainty. Pydantic AI validates every PreciseFP response so your agent never works with bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PreciseFP MCP to Pydantic AI

Create your Vinkius account to connect PreciseFP to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PreciseFP with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build Error-Proof Intake Workflows

Your Pydantic AI agent can reliably manage client intake. It can fetch form templates with `list_form_templates`, create a new client record with `create_person`, and then initiate the paperwork with `create_form_engagement`. Here's the key difference: if the PreciseFP API ever returns data that doesn't match the expected Pydantic model, your agent will raise a `ValidationError` instantly. No silent failures or corrupted data.

Query Client Data with Confidence

Use your agent to pull client records without worrying about data integrity. It can fetch a specific client's details with `get_person` or see their entire history with `get_account_activity`. Pydantic AI automatically parses the JSON response from the MCP server into a Pydantic model. This means you get autocompletion and type hints in your code, and you're protected against unexpected API changes.

A Type-Safe PreciseFP MCP Server

This server gives your agent access to all the core functions of PreciseFP for wealth management. Your agent can list accounts, check on form statuses, and even pull PDF templates with `list_pdf_templates`. Because Pydantic AI is model-agnostic, you can use this toolset with OpenAI, Anthropic, or a local model. The framework's focus is on correctness, ensuring the data your agent acts on is exactly what you expect it to be.

Setup guide

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

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

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

It validates the API response against a Pydantic model. If the JSON from the `get_account` call is missing a required field or has the wrong data type, Pydantic AI will throw an exception instead of letting your agent use the bad data.

Absolutely. Your agent would call `create_person` first. Then, using the returned person ID, it would call `create_form_engagement`. Pydantic AI ensures the ID passed between these two steps is handled correctly.

Your agent will fail loudly with a `ValidationError`. This is a feature, not a bug. It prevents your application from running with mismatched data, alerting you that the API contract has changed.

It's quite direct. You install `pydantic-ai-slim[mcp]`, then create an `MCPToolset` instance with the server URL. This toolset is then passed to your agent, which handles the rest.

The `person` data itself is only in memory during the agent's operation. Vinkius provides an ephemeral, sandboxed environment for each API call, and the connection is secured end-to-end. Pydantic AI's role is to ensure that data, while in use, conforms to your expected structure.

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