Can my agent list all bank accounts for a specific organization in Griffin?

Yes. Use the 'list_accounts' tool with the 'organizationId' parameter. The agent will fetch all bank accounts associated with that organization flawlessly.

How do I check the status of a KYC/KYB verification via chat?

You can use the 'get_verification' tool. Provide the Verification ID, and the agent will return the full details, including the current status and decision of the verification natively.

Can I trigger an internal money transfer between accounts through the agent?

Absolutely. Use the 'create_internal_transfer' tool. By passing the amount and account IDs, your agent will programmatically trigger the transfer within Griffin's secure infrastructure flawlessly.

Griffin MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Griffin
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Griffin through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Griffin "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Griffin?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Griffin MCP Server

Connect your Griffin Banking-as-a-Service account to any AI agent and take full control of your embedded finance operations through natural conversation.

Pydantic AI validates every Griffin tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Index Orchestration — Discover all available API resources and navigate your organization's banking infrastructure natively
Account Oversight — List and inspect all bank accounts, including available balances and account numbers flawlessy
Live Transaction Monitoring — Retrieve detailed transaction histories and resolve specific payment details including status and amounts flawlessly
Verification Workflow — Manage KYC and KYB verifications by listing and inspecting individual verification records natively
Financial Transfers — Trigger internal transfers between accounts to manage liquidity across your organization synchronously
Payee Management — List and verify saved payees to ensure secure and accurate payment orchestration natively

The Griffin MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Griffin to Pydantic AI via MCP

Follow these steps to integrate the Griffin MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Griffin with type-safe schemas

Why Use Pydantic AI with the Griffin MCP Server

Pydantic AI provides unique advantages when paired with Griffin through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Griffin integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Griffin connection logic from agent behavior for testable, maintainable code

Griffin + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Griffin MCP Server delivers measurable value.

Type-safe data pipelines: query Griffin with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Griffin tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Griffin and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Griffin responses and write comprehensive agent tests

Griffin MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Griffin to Pydantic AI via MCP:

create_internal_transfer

Transfer money between internal accounts

get_account

Get details for a specific bank account

get_index

Get the root index of resources from the Griffin API

get_me

Get details of the current authenticated user

get_organization

Get details for a specific organization

get_transaction

Get details for a specific transaction

get_verification

Get details for a specific verification

list_accounts

List bank accounts for an organization

list_organizations

List all accessible organizations

list_payees

List saved payees for an organization

list_transactions

Retrieve transaction history for a bank account

list_verifications

List KYC/KYB verifications for an organization

Example Prompts for Griffin in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Griffin immediately.

"List my organizations in Griffin"

"Show the recent transactions for account ID acc_93021"

"Check the KYC verification status for ID ver_88392"

Troubleshooting Griffin MCP Server with Pydantic AI

Common issues when connecting Griffin to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Griffin + Pydantic AI FAQ

Common questions about integrating Griffin MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Griffin MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.