How to Use the Metrc MCP in AutoGen

Q: How do AutoGen agents collaborate to solve Metrc compliance issues?

One agent can call listincomingtransfers to find pending shipments, while another agent checks listfacilities to verify receiving license statuses. They share this data in their group chat to confirm the transfer is legal before executing it.

Q: How does this MCP Server protect sensitive cannabis sales data?

Your sales receipts and harvest records queried via listactivesales are protected by end-to-end encryption. The Vinkius runtime executes all tool calls inside isolated, single-use V8 containers that leave zero trace of your compliance data on disk.

Deploy AutoGen agents to debate and reconcile physical inventory counts against your live Metrc compliance registry.

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 AutoGen

Create your Vinkius account to connect Metrc to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reconcile sales discrepancies using AutoGen agents

`list_active_sales` serves as the ground truth for your sales reconciliation agent loop, pulling every receipt logged in the state system. When a discrepancy occurs, an AutoGen auditor agent pulls these receipts and compares them against local POS logs to find missing transactions. A separate compliance agent reviews the outputs, flagging any sales that violate daily purchase limits. The agents debate the source of the error before proposing a corrective action plan to the human operator.

Verify harvest weights via multi-agent consensus

`list_active_harvests` provides the wet and dry weight records that your cultivation and compliance agents must reconcile. The cultivation agent pulls harvest yields while the compliance agent verifies that the weights match the limits registered in `list_facilities`. If the weights diverge, the agents run a negotiation loop to determine if moisture loss accounts for the difference. They call `get_unit_of_measures` to ensure all calculations use matching units before finalizing the audit log.

Audit plant lifecycles using this MCP Server

`list_tracked_plants` allows your AutoGen agents to monitor vegetative and flowering plants across multiple physical rooms. A tracking agent monitors plant counts, while a security agent cross-references the active room locations against state regulations. The agents use `list_active_items` to verify that every plant batch is correctly associated with an approved strain. If an unapproved strain name is detected, the security agent halts the workflow and alerts the compliance officer.

Setup guide

Set up Metrc MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Metrc tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Metrc_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Metrc data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Metrc_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Metrc data")
    print(result.messages[-1].content)

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 AutoGen

One agent can call `list_incoming_transfers` to find pending shipments, while another agent checks `list_facilities` to verify receiving license statuses. They share this data in their group chat to confirm the transfer is legal before executing it.

Yes, you configure the MCP tool adapter to handle rate limiting gracefully. This ensures that even if multiple agents repeatedly call `list_active_packages` during a debate, the requests are queued to avoid triggering state API bans.

The AutoGen MCP extension automatically converts the JSON schemas of tools like `get_package_details` into the format required by your agents. You do not need to write manual schema wrappers or parser functions.

Yes, this server supports both transport methods. You can connect your AutoGen agents to the hosted Vinkius endpoint via HTTP for cloud deployments, or run it locally using stdio during development.

Your sales receipts and harvest records queried via `list_active_sales` are protected by end-to-end encryption. The Vinkius runtime executes all tool calls inside isolated, single-use V8 containers that leave zero trace of your compliance data on disk.

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