How to Use the GoTab MCP in LlamaIndex

Q: How do I connect GoTab to my LlamaIndex vector store?

You initialize the BasicMCPClient with your GoTab endpoint and convert the tools using McpToolSpec. This lets your index query tools like getitem to build its knowledge base.

Q: Can LlamaIndex update menu items on GoTab?

Yes, the agent can invoke updateitemstatus when it detects a change in your indexed inventory documents. This allows automated menu updates based on your physical stock levels.

Q: How does LlamaIndex prevent hallucinating GoTab menu items?

The agent queries live data using getmenu and listitems before answering. By grounding its responses in actual API data, it avoids suggesting dishes that are currently unavailable.

Index restaurant menus and live orders into LlamaIndex to query your operations using grounded semantic search via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GoTab MCP to LlamaIndex

Create your Vinkius account to connect GoTab 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 GoTab with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing live restaurant menus into LlamaIndex

`get_menu` retrieves the complete structure of a specific restaurant menu, including all categories and items. The LlamaIndex framework reads this structured data and indexes it directly into your vector store. This lets your agent answer customer questions about ingredients or pricing using real-time restaurant data. By combining `list_categories` and `get_item`, the agent builds a searchable knowledge base of your entire catalog. Customers get answers grounded in your actual menu, preventing the agent from hallucinating dishes that do not exist.

Semantic search over orders using LlamaIndex MCP Server

`list_orders` pulls the recent transaction history for a specific restaurant location. LlamaIndex indexes these order details, allowing managers to query sales trends using natural language. You can ask which items are selling fastest without writing complex SQL queries. The framework treats the tool outputs as live document resources. When you query the index, it pulls fresh data using `get_order` to ensure your financial insights are based on actual, up-to-the-minute restaurant transactions.

Real-time availability updates for indexed catalogs

`update_item_status` changes whether a dish is available for order on your digital menu. When LlamaIndex detects a discrepancy between your physical stock records and your vector index, it triggers this tool to update the live menu. This keeps your physical kitchen and digital storefront in sync. Your agent uses `list_items` to check stock levels, updates the vector index, and immediately executes the status change. Preventing customers from ordering out-of-stock items becomes automatic with this closed-loop system.

Setup guide

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

You initialize the `BasicMCPClient` with your GoTab endpoint and convert the tools using `McpToolSpec`. This lets your index query tools like `get_item` to build its knowledge base.

Yes, the agent can invoke `update_item_status` when it detects a change in your indexed inventory documents. This allows automated menu updates based on your physical stock levels.

The agent queries live data using `get_menu` and `list_items` before answering. By grounding its responses in actual API data, it avoids suggesting dishes that are currently unavailable.

Yes, you can use the MCP server to pull active customer sessions by querying `list_tabs` and `get_tab` to index current customer sessions. This allows you to run semantic queries on active guest spending patterns in real time.

This integration accesses menu pricing, item descriptions, and category structures. All data transfers occur over encrypted HTTPS connections, and the Vinkius platform processes these requests in ephemeral sandboxes that destroy session data immediately after execution.

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