How to Use the Dutchie Plus MCP in LlamaIndex

Q: Can I use LlamaIndex to search Dutchie Plus menus semantically?

Yes. You configure the MCP Server to pull menus via listonlinemenus, then use LlamaIndex's vector index to store and query the product descriptions, prices, and THC content.

Q: Can I filter which Dutchie Plus tools are accessible?

Yes, you can use LlamaIndex's allowedtools filter during setup. This lets you restrict your agent to read-only tools like getdutchieplusmetadata while blocking order modification tools.

Q: How does this MCP Server handle dispensary PII security?

All sensitive dispensary order records processed by listenterpriseorders are sandboxed inside Vinkius's zero-trust infrastructure. Your LlamaIndex instance only pulls the specific data nodes needed for indexing, keeping enterprise retail logs private.

Index live Dutchie Plus dispensary menus and order histories directly into LlamaIndex vector stores for zero-hallucination RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dutchie Plus MCP to LlamaIndex

Create your Vinkius account to connect Dutchie Plus 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 Dutchie Plus with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your LlamaIndex RAG applications in live menu data

Stop letting your agent guess what cannabis products are actually in stock. This MCP Server lets LlamaIndex query `list_online_menus` and index the live menu listings directly into your local vector database for semantic search. When a customer asks for a specific strain profile, the LlamaIndex agent queries the vector index instead of hallucinating. It uses `get_location_details` to verify the store's operating hours before recommending the product.

Semantic search across your synced brands

Index your entire brand catalog by pulling data directly into LlamaIndex via this MCP integration. The agent calls `list_synced_brands` to fetch all synchronized enterprise brands, converting the raw API response into searchable nodes. This setup eliminates guesswork when customers ask complex questions about brand availability. Your agent searches the indexed data and uses `quick_enterprise_volume_audit` to see which brands are moving fastest.

Audit Dutchie Plus transactions with LlamaIndex

Convert raw transactional data into a searchable knowledge base. Your LlamaIndex agent calls `list_enterprise_orders` to retrieve recent sales, then indexes the payloads so you can query sales patterns using natural language. Instead of writing complex SQL queries, you ask the agent which products are pending fulfillment. It uses `list_pending_fulfillment_orders` to pull the latest queue, indexing it instantly to keep your search results accurate.

Setup guide

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

Yes. You configure the MCP Server to pull menus via `list_online_menus`, then use LlamaIndex's vector index to store and query the product descriptions, prices, and THC content.

It forces the agent to ground its answers in the live JSON returned by `get_order_details` and `list_dispensary_locations`. If a product or order isn't in the indexed API response, the agent admits it doesn't know.

Install llama-index-tools-mcp, initialize the BasicMCPClient, and convert it using McpToolSpec. Pass the resulting tool list to your FunctionAgent to expose all 10 dispensary management endpoints.

Yes, you can use LlamaIndex's allowed_tools filter during setup. This lets you restrict your agent to read-only tools like `get_dutchie_plus_metadata` while blocking order modification tools.

All sensitive dispensary order records processed by `list_enterprise_orders` are sandboxed inside Vinkius's zero-trust infrastructure. Your LlamaIndex instance only pulls the specific data nodes needed for indexing, keeping enterprise retail logs private.

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