How to Use the Column MCP in Pydantic AI

Build type-safe banking agents with Pydantic AI and the Column MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Column MCP to Pydantic AI

Create your Vinkius account to connect Column 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 Column with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Column bank tools in Pydantic AI

Ensure every banking response matches your expected schema. The `column_get_balance` and `column_get_bank_account` tools return structured data that Pydantic AI verifies at runtime. This prevents the agent from processing malformed financial data. If the server returns bad input, your agent catches the validation error immediately.

Trigger transfers with Pydantic AI

Issue ACH payments while maintaining strict type safety. You call `column_create_ach_transfer` within your agent, knowing the model handles the arguments correctly. This approach removes guesswork from financial actions. The agent relies on your defined models to construct the transfer request accurately.

Monitor webhook activity in Pydantic AI

Keep your agent informed of incoming events. Use `column_list_webhooks` to view the status of your current listeners. Your agent inspects these streams to trigger downstream logic. It maintains a clear view of all active notification channels connected to your bank charter.

Setup guide

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

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

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

It validates the server output against your Pydantic models. If the data structure deviates from your requirements, the agent rejects the result to prevent errors.

You define the expected schema for each tool. As long as the server output matches, the agent processes the banking data without interruption.

You install the slim package, define the MCPToolset, and point it to your server URL. The agent then registers the tools for use in your workflow.

Every tool listed in the server is available. You just need to define the corresponding Pydantic models to ensure the agent understands the tool output.

Your entity data is validated locally before transmission. The Column server uses a zero-trust architecture, ensuring that your business registration details are never exposed to unauthorized processes.

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