How to Use the Griffin MCP in Pydantic AI

Strictly validate fintech data with Griffin and Pydantic AI. No hallucinated fields, just type-safe banking operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Griffin MCP to Pydantic AI

Create your Vinkius account to connect Griffin 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 Griffin with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce type-safety for Griffin operations

Every response from `get_transaction` or `list_accounts` is validated against your Pydantic models. If the API returns a field you didn't expect, the agent stops immediately. This prevents silent corruption in your ledger. You gain the confidence that your agent's logic is based on verified, structured data every time it runs.

Execute internal transfers with verified models

Define the parameters for `create_internal_transfer` using Pydantic models. The framework checks these constraints at runtime before the request hits the Griffin API. If the data doesn't match your schema, the agent throws a validation error. You catch these issues during development rather than discovering them in production.

Query verification status with total precision

Use `list_verifications` to pull compliance data into your type-safe pipeline. Pydantic AI maps the response, ensuring every KYC document status is correctly typed. Your agent logic depends on this accuracy. By forcing strict validation, you ensure that your compliance monitoring remains consistent, regardless of which model you use.

Setup guide

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

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

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

You get runtime validation for every Griffin API response. It forces your agent to adhere to your strict data models, eliminating hallucinated fields.

The framework raises a validation error instantly. This prevents the agent from processing bad data, ensuring your internal ledger stays accurate.

You can. The framework is model-agnostic, so you can point it at local LLMs while keeping the same type-safe MCP connection to the Griffin server.

You use the MCPToolset class with your Vinkius endpoint URL. It bridges the server to your agent, providing typed access to all twelve tools.

Your transaction history is accessed through an encrypted, ephemeral connection. The server does not persist your sensitive bank data, and the agent only uses it within the current validation context.

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