How to Use the Metrc MCP in LlamaIndex

Q: How does LlamaIndex index live data from Metrc?

You use the MCP tool spec to pull data from tools like listactiveharvests and convert the JSON payloads into LlamaIndex Document objects. These documents are then embedded and stored in your vector database for semantic search.

Q: Can LlamaIndex query historical Metrc transfer manifests?

Yes, by calling listincomingtransfers, LlamaIndex can pull manifest records and index them. Your agent can then answer questions about past shipments, origin facilities, and transit dates using natural language.

Q: How do I prevent LlamaIndex from hallucinating compliance data?

By forcing the query engine to retrieve fresh data from getpackagedetails before answering. This guarantees that your agent bases its responses on the actual state registry instead of outdated training data.

Index live Metrc inventory data directly into LlamaIndex to query your state compliance records using natural language.

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 LlamaIndex

Create your Vinkius account to connect Metrc to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable index of Metrc inventory

`list_active_packages` acts as the primary data ingestion tool, pulling real-time package statuses into your LlamaIndex vector store. Instead of writing custom database pipelines, your RAG system queries this tool to index package IDs, quantities, and item categories into searchable document nodes. Once indexed, users can ask questions about inventory levels without knowing the underlying schema. The agent uses the index to resolve queries like which packages are nearing expiration or which batches require immediate physical audits.

Ground compliance QA in live state registry data

`list_active_strains` provides the exact botanical genetic records registered with the state, which LlamaIndex uses to ground its responses. When users ask about strain genetics or active grows, the engine cross-references the prompt against real-time data to prevent hallucinations. By combining this tool with `list_active_items`, your LlamaIndex query engine can resolve complex product questions. The agent verifies that the product names match the state-registered strains, ensuring your physical labeling is always compliant.

Query transfer history using LlamaIndex RAG

`list_incoming_transfers` pulls shipping manifests and transfer logs directly into your document indexing pipeline. LlamaIndex parses these manifests, turning complex transport data into queryable nodes that track chain of custody from cultivator to dispensary. This setup lets compliance officers query transfer histories using plain English. The agent calls `get_package_details` behind the scenes to verify the contents of any flagged transfer, providing an immediate audit trail for state inspectors.

Setup guide

Set up Metrc MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Metrc MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Metrc tools.",
)
response = await agent.run("List recent Metrc data")

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 LlamaIndex

You use the MCP tool spec to pull data from tools like `list_active_harvests` and convert the JSON payloads into LlamaIndex Document objects. These documents are then embedded and stored in your vector database for semantic search.

Yes, by calling `list_incoming_transfers`, LlamaIndex can pull manifest records and index them. Your agent can then answer questions about past shipments, origin facilities, and transit dates using natural language.

By forcing the query engine to retrieve fresh data from `get_package_details` before answering. This guarantees that your agent bases its responses on the actual state registry instead of outdated training data.

Yes, you can pass an allowed tools list to the MCP tool spec during initialization. For example, you can restrict the indexer to only use `list_active_items` and `get_unit_of_measures` while blocking access to sales or plant data.

Your state credentials and inventory records are never saved or cached on the Vinkius platform. All data retrieved via `list_facilities` is processed in a zero-trust, ephemeral V8 sandbox that destroys all session state immediately after the request finishes.

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