How to Use the Metrc MCP in Pydantic AI

Q: How do I initialize the Metrc MCP Server in Pydantic AI?

Use the unified MCPToolset pointing to your Vinkius HTTP endpoint. Pass this toolset to your Agent constructor to give your model immediate access to tools like listfacilities.

Validate your cannabis compliance data at runtime using Pydantic AI and Metrc.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metrc MCP to Pydantic AI

Create your Vinkius account to connect Metrc 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 Metrc with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate active packages with strict Pydantic AI schemas

The `list_active_packages` tool fetches live inventory records and validates them against strict Python type definitions at runtime. Pydantic AI ensures that every package ID, weight, and item category matches your expected schema before your agent can act on it. If the state API returns unexpected null values, the framework fails loudly instead of letting corrupted data slip into your local database. You can safely inspect individual items using `get_package_details` knowing your agent is working with clean, verified types.

Parse strain and item lists on this MCP Server

The `list_active_strains` tool retrieves your facility's registered plant profiles directly into your type-safe agent. Running this MCP Server tool ensures your local inventory system never maps a package to a non-existent strain. To keep your catalog accurate, `list_active_items` checks active product configurations against state-approved categories. Pydantic AI parses these nested structures instantly, throwing clear validation errors if a product configuration violates regulatory definitions.

Track plants and harvests with type-safe models

The `list_tracked_plants` tool exposes active plant counts and growth phases directly to your validation pipelines. Your agent uses these typed models to verify that physical plant tags align with state-mandated track-and-trace rules. When plants move to processing, `list_active_harvests` provides the exact harvest weights and drying records. Because Pydantic AI is model-agnostic, you can run these strict validation checks using OpenAI, Gemini, or local models.

Setup guide

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

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

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

Use the unified `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset to your `Agent` constructor to give your model immediate access to tools like `list_facilities`.

The framework raises a validation error immediately, stopping execution before bad data pollutes your database. This prevents silent failures when calling tools like `list_active_sales` or `list_incoming_transfers`.

Yes, you can define custom Pydantic models to wrap tool outputs like `get_unit_of_measures`. This lets you enforce strict local compliance rules on top of the state-level track-and-trace requirements.

Yes, the framework supports both streamable HTTP and SSE transports for external servers. This keeps your connection stable when fetching large datasets from tools like `list_tracked_plants`.

Absolutely, your license keys, package histories, and harvest weights are processed locally within your application memory. Vinkius secures the transport layer with ephemeral, zero-trust sandboxes, meaning your compliance data is never stored or cached.

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