Can I access data from multiple accounting platforms like QuickBooks and Xero simultaneously?

Yes! Railz normalizes data across all supported providers. Use the `list_businesses` and `list_connections` tools to identify the target entity, then query reports which will return in a consistent format regardless of the underlying source.

How do I retrieve a Balance Sheet for a specific company connection?

First, find the relevant `connection_id` for the business using `list_connections`. Then, use the `get_balance_sheet` tool with that ID to fetch the snapshot of assets and liabilities.

Does this integration allow creating new invoices or only reading them?

The current toolset focuses on read-only operations for auditing and analysis, such as `list_invoices`, `list_bills`, and `list_accounts`. This ensures safe exploration of financial data without accidental modifications.

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

Name: Railz
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 Railz 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 Railz "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Railz?"
    )
    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 Railz MCP Server

Empower your AI agent to access normalized financial data from various accounting, banking, and commerce platforms with Railz. By connecting Railz to your agent, you transform complex financial auditing into a natural conversation. Your agent can instantly list businesses, audit invoices, and retrieve deep financial reports like Balance Sheets and P&L statements without you ever touching a dashboard. Whether you are managing multiple client accounts or a single corporate entity, your agent acts as a real-time financial analyst, ensuring your data is always accessible and structured.

Pydantic AI validates every Railz 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

Business Directory — List all registered businesses in your Railz account and inspect their specific metadata.
Connection Auditing — Monitor active service provider connections (QuickBooks, Xero, Shopify, etc.) for any business entity.
Financial Reporting — Fetch real-time, normalized reports including Balance Sheets, Profit & Loss, and Cash Flow statements.
Invoice & Bill Management — Query and analyze accounts receivable (invoices) and accounts payable (bills) across multiple providers.
Commerce Insights — Access sales orders and transaction data from connected commerce platforms to track revenue trends.

The Railz 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 Railz to Pydantic AI via MCP

Follow these steps to integrate the Railz 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 Railz with type-safe schemas

Why Use Pydantic AI with the Railz MCP Server

Pydantic AI provides unique advantages when paired with Railz 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 Railz integration code

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

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

Railz + Pydantic AI Use Cases

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

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

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

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

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

Railz MCP Tools for Pydantic AI (12)

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

get_balance_sheet

Get balance sheet report

get_business

Get details for a specific business

get_cash_flow

Get cash flow statement

get_profit_and_loss

Get profit and loss report

list_accounts

List chart of accounts

list_bank_transactions

List bank transactions

list_bills

List bills for a business

list_businesses

List all businesses in Railz

list_commerce_orders

g., Shopify, BigCommerce). List commerce orders

list_connections

g., QuickBooks, Xero) for a given business. List connections for a business

list_invoices

List invoices for a business

list_journal_entries

List journal entries

Example Prompts for Railz in Pydantic AI

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

"List all businesses registered in my Railz account."

"Show active connections for business 'biz_123'."

"Get the Profit and Loss report for connection 'conn_456'."

Troubleshooting Railz MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Railz + Pydantic AI FAQ

Common questions about integrating Railz 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 Railz MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.