How to Use the Envi Healthcare Supply Chain MCP in Pydantic AI

Q: How do I add the Envi Healthcare Supply Chain MCP Server to Pydantic AI?

Install the pydantic-ai-slimmcp package. Initialize an MCPToolset with your endpoint URL and pass it in the toolsets array to your Agent. Use the unified HTTP approach, as MCPServerHTTP is deprecated.

Q: How does Pydantic AI handle schema errors from Envi Healthcare Supply Chain?

It fails loudly. If your agent calls listmedicalinventorylevels and the returned JSON doesn't match your Pydantic model, the framework throws a validation error rather than passing bad data to your application.

Type-safe healthcare supply chain management for Pydantic AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Envi Healthcare Supply Chain MCP to Pydantic AI

Create your Vinkius account to connect Envi Healthcare Supply Chain 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 Envi Healthcare Supply Chain with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Envi MCP Server data at runtime

`get_envi_account_metadata` retrieves your account limits and configurations. Pydantic AI validates every field in that response against your predefined models. If the API returns a string instead of an integer for a limit, the agent throws a loud validation error immediately. This strict typing applies to `quick_healthcare_supply_audit` as well. You get a high-level summary of POs and inventory, and you know the data structure is exactly what your downstream code expects. No silent failures. No hallucinated metrics.

Parse purchase orders without silent errors

`list_healthcare_pos` pulls all purchase orders from your account. Your model-agnostic agent processes this list, ensuring every PO ID matches your expected format before proceeding to the next step. When the agent needs specifics, it calls `get_po_technical_details`. It extracts the line items and settings for a single order. Because Pydantic AI enforces correctness, you never have to worry about the agent making up a delivery date or a line item cost.

Monitor stock alerts with exact precision

`list_critical_stock_alerts` identifies supplies sitting below safety thresholds. The agent receives this list and guarantees that every item has a valid SKU and threshold value attached to it. The agent then uses `get_supply_stock_level` to verify the exact real-time stock for those critical items. It matches the inventory data with facility information from `list_healthcare_facilities`, ensuring every restock request routes to a valid clinic ID.

Setup guide

Set up Envi Healthcare Supply Chain 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": {
        "envi-healthcare-supply-chain-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Envi Healthcare Supply Chain 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 Envi Healthcare Supply Chain. 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 Envi Healthcare Supply Chain 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 Envi Healthcare Supply Chain MCP in Pydantic AI

Install the pydantic-ai-slim[mcp] package. Initialize an MCPToolset with your endpoint URL and pass it in the toolsets array to your Agent. Use the unified HTTP approach, as MCPServerHTTP is deprecated.

It fails loudly. If your agent calls `list_medical_inventory_levels` and the returned JSON doesn't match your Pydantic model, the framework throws a validation error rather than passing bad data to your application.

Yes. The framework is completely model-agnostic. You can route `list_latest_supply_requisitions` data through Anthropic, OpenAI, or a local Llama model without changing your MCP Server toolset code.

Yes. The toolset supports both Streamable HTTP and SSE transports. You just need to ensure your external server is running and accessible via the provided URL.

Vinkius manages the authentication layer entirely. When your agent requests data via `list_latest_supply_requisitions`, the payload travels over an encrypted, ephemeral connection that requires a single, short-lived endpoint token to access.

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