How to Use the Metrc MCP in OpenAI Agents SDK

Q: How do I authenticate the Metrc MCP Server within the OpenAI Agents SDK?

You pass your Vinkius HTTP endpoint token to the MCPServerStreamableHttp constructor. The SDK automatically handles the handshake, letting your agents discover and call tools like listfacilities without manual header setup.

Q: How does the OpenAI Agents SDK handle rate limits when querying Metrc?

Setting cacheToolsList=True ensures your agent doesn't waste precious API quota repeatedly fetching tool definitions. For high-volume endpoints like listtrackedplants, you should implement standard Python backoff decorators around your agent execution loops.

Run safe, production-grade cannabis compliance workflows in the OpenAI Agents SDK with strict guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Metrc to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track facilities and packages with OpenAI Agents SDK

The `list_facilities` tool pulls active state-licensed cannabis locations directly into your agent's context. Your OpenAI agent uses this live registry to verify license numbers before triggering any secondary actions or compliance checks. When you need deep-dive audits, `get_package_details` fetches the exact unit counts and item categories for any inventory ID. The SDK runs these queries through your configured safety guardrails, preventing the agent from initiating transfers or altering states without explicit human-in-the-loop approval.

Validate active harvests and plant counts safely

Your agent calls `list_tracked_plants` to pull the exact growth phase and location of every plant in the facility. This live feed prevents your system from mismatching physical inventory with state records during high-throughput operations. To keep the ledger clean, `list_active_harvests` exposes wet weights and drying statuses to your Python runtime. The OpenAI Agents SDK manages these multi-step data collections by passing tasks between specialized agents, keeping your compliance logs clean and traceable in the developer dashboard.

Match sales receipts to the live Metrc MCP Server

The `list_active_sales` tool exposes raw point-of-sale records directly to your custom compliance agents. This MCP Server integration allows your agent to cross-reference retail transaction logs against active state limits in real time. If a discrepancy pops up, the agent calls `get_unit_of_measures` to align physical weights with state-mandated reporting metrics. By caching the tools list on setup, your OpenAI agent handles these validation checks without adding extra API latency to checkout lines.

Setup guide

Set up Metrc MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Metrc tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Metrc tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Metrc tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Metrc Agent",
            instructions="You have access to Metrc tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You pass your Vinkius HTTP endpoint token to the `MCPServerStreamableHttp` constructor. The SDK automatically handles the handshake, letting your agents discover and call tools like `list_facilities` without manual header setup.

Yes, you control tool exposure by defining specific agent schemas or using the SDK's built-in guardrails. This prevents an agent from invoking read-heavy operations like `list_active_packages` unless specifically authorized by the active run context.

Setting `cacheToolsList=True` ensures your agent doesn't waste precious API quota repeatedly fetching tool definitions. For high-volume endpoints like `list_tracked_plants`, you should implement standard Python backoff decorators around your agent execution loops.

Absolutely, you can spin up specialized agents for each license ID and let the SDK coordinate the handoffs. One agent runs `list_incoming_transfers` while another checks `list_active_items` to verify incoming inventory against warehouse capacity.

Your license IDs, package details, and plant counts flow through Vinkius's zero-trust V8 sandbox directly to your private OpenAI runtime. We never store or log the payloads of tools like `list_active_sales` on our host servers.

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