How to Use the Working Capital Calculator MCP in Pydantic AI

Calculate cash conversion cycles and working capital needs with type-safe validation using the Working Capital Calculator in Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Working Capital Calculator MCP to Pydantic AI

Create your Vinkius account to connect Working Capital Calculator 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 Working Capital Calculator with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Compute cash conversion cycle duration via MCP

The `calculate_cash_conversion_cycle` tool returns the exact days your cash is trapped in operations. You feed it inventory, receivables, and payables days. It subtracts payables from the sum of the other two. Pydantic AI validates every single response against your models at runtime. If the MCP returns a string instead of an integer for the cycle days, your agent fails loudly. You never get silent data corruption.

Convert cycle days to monetary values

The `calculate_monetary_working_capital` tool takes the cycle duration and multiplies it by your daily cost of goods sold. Right. Let's look at the cash. A timeframe means nothing without a dollar amount. It outputs the exact cash buffer you need. This strict validation is critical for financial systems. If the turnover data is missing or malformed, the Pydantic model rejects it immediately. Your agent stops and throws an error instead of guessing the missing field.

Fetch full financial cycle profiles

The `get_financial_cycle_summary` tool returns every constituent period and final value when you need the full breakdown. Your agent parses the JSON and maps it directly to your Pydantic response model. This works with any underlying model you choose. You can swap between local models or cloud APIs without changing your tool logic. The type safety remains absolute across every provider.

Setup guide

Set up Working Capital Calculator 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": {
        "working-capital-calculator-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Working Capital Calculator 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 Working Capital Calculator. 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 Working Capital Calculator 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 Working Capital Calculator MCP in Pydantic AI

Install the slim MCP package and initialize an MCPToolset with your HTTP URL. Pass that toolset into the toolsets list when you create your Agent. The tools are automatically discovered and typed.

Your agent will crash with a validation error. Pydantic AI checks every response against your defined models at runtime. It refuses to process unexpected fields or wrong data types.

Yes. The MCPToolset natively supports Streamable HTTP and SSE transports. Just pass the correct URL when you initialize the toolset. The connection handles the streaming automatically.

Yes. The framework is completely model-agnostic. You can point your agent to a local LLM or a cloud API, and the MCP tool validation works exactly the same way.

No. The MCP only processes the numbers you send in the request and returns the result. It does not persist your daily cost of goods sold or cycle durations. Your data stays in your own environment.

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