How to Use the MarketMan MCP in Pydantic AI

Q: How do I install the MarketMan integration for Pydantic AI?

Run pip install "pydantic-ai-slimmcp" in your environment. Then import MCPToolset and point it to your Vinkius server URL to expose the MCP tools.

Q: Can I use Pydantic AI to verify inventory categories in MarketMan?

Yes. The agent executes listcategories to get item counts. Pydantic AI ensures the returned counts are parsed as valid integers before passing them to your decision-making loops.

Q: How is the privacy of my MarketMan count sheets protected in Pydantic AI?

Your physical count sheets retrieved via getcountsheets are processed directly within your local Python runtime memory. The transport layer uses end-to-end encryption to pull the data from the secure Vinkius gateway.

Bring type-safe runtime validation to your Pydantic AI agents querying MarketMan inventory and waste data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MarketMan MCP to Pydantic AI

Create your Vinkius account to connect MarketMan 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 MarketMan with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe inventory auditing with Pydantic AI

Stop worrying about silent API failures or corrupted data structures. This MCP Server integrates with Pydantic AI to validate every inventory record returned by `list_inventory` against strict Python type models at runtime. If the restaurant database returns an unexpected null value or a malformed string, your agent fails loudly immediately. This prevents your menu calculations from using corrupt data and keeps your financial reporting clean.

Validate waste events before running calculations

When tracking kitchen waste, data integrity is everything. Your agent can call `get_waste_events` to pull logged waste records, and Pydantic AI will instantly verify that the quantities and timestamps match your expected schema. This strict validation ensures that your automated cost-of-goods-sold reports are built on solid numbers. You can write custom Pydantic models to parse the tool output and flag anomalies before they reach your accounting database.

Run model-agnostic recipe and vendor audits

This setup is completely model-agnostic, meaning you can swap your underlying LLM while keeping your type safety intact. Your agent can call `list_recipes` and `list_vendors` to audit your food costs regardless of whether you use OpenAI, Anthropic, or local models. To get started, initialize the `MCPToolset` with your Vinkius HTTP endpoint and pass it to your agent. This unified approach replaces deprecated transport classes and keeps your codebase clean.

Setup guide

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

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

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

Run `pip install "pydantic-ai-slim[mcp]"` in your environment. Then import `MCPToolset` and point it to your Vinkius server URL to expose the MCP tools.

The framework will raise a validation error immediately. Instead of processing bad data from `list_purchase_orders`, the agent catches the schema mismatch and halts execution.

Yes. The agent executes `list_categories` to get item counts. Pydantic AI ensures the returned counts are parsed as valid integers before passing them to your decision-making loops.

Yes. The MCP toolset connects to the externally hosted Vinkius server over a secure HTTP or SSE transport, meaning you do not have to manage the server process locally.

Your physical count sheets retrieved via `get_count_sheets` are processed directly within your local Python runtime memory. The transport layer uses end-to-end encryption to pull the data from the secure Vinkius gateway.

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