How to Use the OpenTHC MCP in LlamaIndex

Q: How do I load OpenTHC MCP tools into LlamaIndex?

Install the package and initialize BasicMCPClient with your Vinkius URI. Wrap it in McpToolSpec and call totoollistasync() to get the tools. Pass this list to your FunctionAgent to start querying compliance data.

Q: Can LlamaIndex index OpenTHC data for offline RAG?

Yes, you can load outputs from listproducts and listvarieties directly into a vector index. This allows your agent to perform semantic searches over your strain genetics and product catalog. You get instant answers without hitting the live API for every query.

Q: Can I filter which OpenTHC MCP Server tools LlamaIndex can access?

Yes, you can use the allowedtools parameter in the client configuration to restrict access. For example, you might only expose listlabresults to a customer-facing budtender agent. This keeps your financial and B2B transaction tools secure.

Index live OpenTHC compliance data into LlamaIndex to query your cannabis inventory and lab results with zero hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect OpenTHC MCP to LlamaIndex

Create your Vinkius account to connect OpenTHC to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup OpenTHC with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build a searchable OpenTHC knowledge base

`list_inventory` pulls your entire catalog of cannabis lots, weights, and storage locations directly into your LlamaIndex vector store. This lets you run semantic queries over your physical stock instead of writing custom database scripts. Your agent answers complex inventory questions instantly by searching this live index. By indexing these records, you bridge the gap between physical reality and digital records. The framework updates this knowledge base continuously, keeping your compliance data fresh.

Query lab analysis data using this MCP Server

`list_lab_results` retrieves official Certificates of Analysis and cannabinoid potencies for every product batch in your facility. LlamaIndex stores these results as nodes in your document index, enabling rapid search over terpene profiles and safety metrics. Budtenders query this index to find specific strain characteristics for customers. This system eliminates manual certificate lookup. Your agent matches physical packages to their chemical profiles by querying the indexed lab data directly.

Track retail sales history in LlamaIndex

`list_b2c_transactions` extracts daily dispensary sales records and tax breakdowns to feed your financial index. LlamaIndex synthesizes this raw transaction data to highlight buying patterns and tax liabilities. You get real-time compliance reporting without exporting massive spreadsheets. The agent monitors these transactions to flag potential purchase limit violations. This protects your dispensary license from accidental compliance breaches.

Setup guide

Set up OpenTHC 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 OpenTHC 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 OpenTHC tools.",
)
response = await agent.run("List recent OpenTHC 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 OpenTHC. 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 OpenTHC 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 OpenTHC MCP in LlamaIndex

Install the package and initialize `BasicMCPClient` with your Vinkius URI. Wrap it in `McpToolSpec` and call `to_tool_list_async()` to get the tools. Pass this list to your `FunctionAgent` to start querying compliance data.

Yes, you can load outputs from `list_products` and `list_varieties` directly into a vector index. This allows your agent to perform semantic searches over your strain genetics and product catalog. You get instant answers without hitting the live API for every query.

The MCP Server provides direct access to live endpoints like `list_inventory` which you can poll on a schedule. LlamaIndex upserts these records into your vector store to prevent data drift. This ensures your agent always reasons on current stock levels.

Yes, you can use the `allowed_tools` parameter in the client configuration to restrict access. For example, you might only expose `list_lab_results` to a customer-facing budtender agent. This keeps your financial and B2B transaction tools secure.

Vinkius manages the connection using an isolated V8 sandbox, ensuring your sensitive plant tags and retail sales data never leak. Your API credentials are never stored in plain text. Everything stays encrypted, and context is wiped between agent sessions.

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