How to Use the GoFood MCP in LangChain

Q: How do I handle GoFood order cancellations in LangChain?

You use the cancelorder tool within a conditional LangChain run. The agent evaluates the cancellation reason and immediately fires the tool to update the platform, ensuring your store metrics remain clean.

Q: Can I update GoFood menus based on database triggers using LangChain?

Yes, you can pipe database outputs directly into the updatecatalog tool. Your LangChain agent checks the database changes and updates your GoFood digital menu layout instantly.

Q: How does LangSmith trace GoFood MCP tool failures inside LangChain?

LangSmith traces the exact payloads sent to tools like acceptorder or updatemenustocks. If an API call fails, you see the exact error message and input parameters directly in your LangSmith dashboard.

Q: How do I manage multiple restaurant connections?

Use linkoutlet to register each storefront with this MCP integration. You can then run listlinkedoutlets to verify which locations are active before sending updates.

Manage GoFood orders and menu updates by piping live kitchen data directly through your LangChain multi-step reasoning chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GoFood MCP to LangChain

Create your Vinkius account to connect GoFood 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 GoFood with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain GoFood order states dynamically

`accept_order` kicks off the sequence when a customer buys a meal. Your LangChain agent receives the order payload, checks the details, and passes the output to `mark_order_prepared` once the kitchen finishes cooking. This sequential MCP flow runs inside a single run trace. LangSmith logs every transition from receipt to preparation, giving you a clear audit trail of your kitchen's actual performance metrics.

Control GoFood menu stocks using this MCP Server

`update_menu_stocks` syncs your physical inventory levels with your digital storefront. A low-stock alert from your database immediately triggers this tool inside your LangChain chain to prevent customers from ordering sold-out dishes. You avoid order cancellations by keeping your digital menu accurate in real-time. The agent evaluates the inventory delta and executes the update without requiring manual merchant intervention.

Run multi-step GoFood promo campaigns

`create_promo` lets your agent launch targeted discounts across your outlets. The LangChain chain first pulls active campaigns using `list_promos`, analyzes their performance, and spins up new offers to drive peak-hour sales. Decisions happen programmatically based on real-time store performance. Your agent coordinates these actions across multiple locations by reading the current setup through `get_outlet_info` before pushing the promo live.

Setup guide

Set up GoFood 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 GoFood 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({
    "gofood-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 GoFood 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 GoFood / GoBiz. 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 GoFood 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 GoFood MCP in LangChain

You use the `cancel_order` tool within a conditional LangChain run. The agent evaluates the cancellation reason and immediately fires the tool to update the platform, ensuring your store metrics remain clean.

Yes, you can pipe database outputs directly into the `update_catalog` tool. Your LangChain agent checks the database changes and updates your GoFood digital menu layout instantly.

LangSmith traces the exact payloads sent to tools like `accept_order` or `update_menu_stocks`. If an API call fails, you see the exact error message and input parameters directly in your LangSmith dashboard.

Use `link_outlet` to register each storefront with this MCP integration. You can then run `list_linked_outlets` to verify which locations are active before sending updates.

Your merchant credentials, order details, and menu pricing run inside an ephemeral, zero-trust V8 Isolate Sandbox. Vinkius never persists your catalog or transaction data, destroying the execution environment immediately after your LangChain agent finishes its tool call.

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