How to Use the Foodpanda MCP in Google ADK

Q: How do I initialize the Foodpanda MCP Server with Google ADK?

Install google-adk and create an McpToolset using StreamableHttpServerParameters. Pass that toolset to your LlmAgent initialization. The agent will read the tools over the HTTP transport automatically.

Q: Can Google ADK restrict which Foodpanda tools the agent uses?

Yes. You provide a list of specific tool names to the McpToolset constructor. If you only want the agent reading data, you just expose getorderhistory and hide the write commands.

Q: Can Google ADK link Foodpanda order history to BigQuery?

You can. Your agent pulls recent transactions via getorderdetails and formats them for BigQuery insertion. This bridges your live delivery operations with your enterprise analytics warehouse.

Q: Is customer delivery data safe when processed by the MCP Server and Google ADK?

The getorderhistory tool exposes delivery addresses and order totals through a zero-trust architecture. Vinkius authenticates the single endpoint token and destroys the connection state immediately after the payload transfers.

Connect your BigQuery data to the Foodpanda MCP Server using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Foodpanda MCP to Google ADK

Create your Vinkius account to connect Foodpanda to Google ADK 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 Foodpanda with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync menus with BigQuery analytics

The `export_catalog` and `get_vendor_catalog` tools pull your entire restaurant menu structure into your Gemini agent's context. You can map this live data against historical sales trends sitting in BigQuery. Once Gemini identifies underperforming items, it uses `get_vendor_categories` to suggest menu restructuring. The 1M+ token window means the agent digests thousands of SKUs in a single prompt without losing the thread.

Trigger campaigns via Google ADK

The `upsert_promotion` tool lets your agent deploy targeted discounts across your delivery network. You feed weather data or local event schedules from Google Cloud into the agent to dictate pricing logic. The agent verifies the campaign rollout by checking `get_promotion_job`. You restrict which tools the agent can touch by passing a `tool_names` filter to the `McpToolset` during setup.

Manage kitchen load with MCP Server

The `update_vendor_status` tool gives Vertex AI agents the ability to throttle incoming delivery requests. If your backend detects a spike in dine-in orders, the agent flips the Foodpanda store to busy. The agent monitors recovery by polling `get_vendor_status`. It waits for the kitchen backlog to clear before reopening the digital storefront. This keeps your delivery metrics green.

Setup guide

Set up Foodpanda MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Foodpanda tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Foodpanda_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Foodpanda tools via MCP.",
    tools=mcp_tools,
)

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 Foodpanda. 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 Foodpanda 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 Foodpanda MCP in Google ADK

Install `google-adk` and create an `McpToolset` using `StreamableHttpServerParameters`. Pass that toolset to your `LlmAgent` initialization. The agent will read the tools over the HTTP transport automatically.

Yes. You provide a list of specific tool names to the `McpToolset` constructor. If you only want the agent reading data, you just expose `get_order_history` and hide the write commands.

Gemini's massive context window easily absorbs the JSON output from `export_catalog`. The agent reads the entire catalog structure at once instead of relying on fragmented vector search retrievals.

You can. Your agent pulls recent transactions via `get_order_details` and formats them for BigQuery insertion. This bridges your live delivery operations with your enterprise analytics warehouse.

The `get_order_history` tool exposes delivery addresses and order totals through a zero-trust architecture. Vinkius authenticates the single endpoint token and destroys the connection state immediately after the payload transfers.

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