How to Use the Metrc MCP in LangChain

Q: Can I trace Metrc tool calls using LangChain and LangSmith?

Yes, every call to tools like listactivesales or listactiveharvests shows up in your LangSmith trace. You see the exact payload sent to the state registry and the exact JSON returned, making it simple to debug failed compliance uploads.

Q: How do I pass facility licenses dynamically in a LangChain agent?

You configure your agent to call listfacilities first, which retrieves all active licenses. The agent then extracts the correct license number from the output and injects it as the required parameter for downstream tools like listtrackedplants.

Feed real-time Metrc compliance data directly into your LangChain reasoning loops to catch inventory discrepancies before state audits do.

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 LangChain

Create your Vinkius account to connect Metrc to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Metrc compliance checks in LangChain

`list_facilities` is the entry point for your compliance chains, letting your agent identify active state licenses before executing deeper inventory queries. Your agent runs this tool first to resolve the physical location context, then pipes the resulting facility ID directly into subsequent analytical chain steps. This multi-step execution pattern allows LangChain chains to fetch active inventory using `list_active_packages` and immediately compare those counts against local databases. By using LangSmith, you can trace every single tool execution to verify exactly which state license was queried and how long the Metrc API took to respond.

Verify transfer manifests with multi-step agents

`list_incoming_transfers` pulls pending manifest data so your agent can verify incoming shipments against current facility capacity. The agent acts on real-time data, checking the incoming strain names against `list_active_strains` to flag unauthorized genetics before they arrive at your loading dock. Because LangChain handles stateful tool sequencing, your agent can automatically run `get_unit_of_measures` to convert weight values on the fly. This prevents manual unit entry errors and ensures your local database matches the state system of record down to the milligram.

Trace plant lifecycle history through the MCP Server

`list_tracked_plants` exposes the growth phase of every plant in your facility directly to your LangChain agent. When a plant transitions, the agent pulls the batch history and feeds it to `list_active_harvests` to log wet weights and harvest dates without manual data entry. You configure this pipeline as a ReAct agent that evaluates harvest yields against active items from `list_active_items`. If yields fall outside historical averages, the agent flags the specific harvest batch and logs the anomaly in your LangSmith dashboard.

Setup guide

Set up Metrc MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Metrc tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "metrc-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Metrc transactions"
    })
    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 LangChain

Your LangChain runnables should use built-in retry logic with exponential backoff when calling tools like `list_active_packages`. Since this MCP Server translates API responses directly, you can handle 429 status codes within your chain's error-handling steps to prevent compliance gaps.

Yes, every call to tools like `list_active_sales` or `list_active_harvests` shows up in your LangSmith trace. You see the exact payload sent to the state registry and the exact JSON returned, making it simple to debug failed compliance uploads.

You configure your agent to call `list_facilities` first, which retrieves all active licenses. The agent then extracts the correct license number from the output and injects it as the required parameter for downstream tools like `list_tracked_plants`.

Yes, you can combine this server with other database or messaging servers using the LangChain multi-server adapter. This lets your agent pull cannabis data via `get_package_details` and instantly post a summary to Slack or update a local database in a single run.

Your state license keys, active harvest weights, and package IDs remain isolated within a sandboxed V8 execution environment. No compliance data or API keys are stored on Vinkius servers, as the platform acts strictly as an ephemeral proxy between your LangChain agent and the state registry.

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