How to Use the Deliveroo MCP in LlamaIndex

Q: How do I query Deliveroo orders with LlamaIndex?

Initialize a BasicMCPClient with your Vinkius URL and wrap it in McpToolSpec. Call totoollistasync() to pass the functions to your agent.

Q: Can LlamaIndex agents update Deliveroo prep stages?

Yes, your agent can trigger createprepstage based on semantic search results. The system reads your kitchen logs and maps them to platform updates.

Q: How do I restrict which Deliveroo tools my LlamaIndex agent uses?

Use the allowedtools filter when configuring your McpToolSpec. This prevents the agent from calling disruptive endpoints like order rejection by mistake.

Index live Deliveroo orders into LlamaIndex vector stores for semantic search and grounded updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deliveroo MCP to LlamaIndex

Create your Vinkius account to connect Deliveroo 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 Deliveroo with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Deliveroo orders for LlamaIndex semantic search

`get_orders` and `get_order` pull raw restaurant delivery data directly into your LlamaIndex workflow. Your application reads these active tickets and converts them into document nodes. The framework indexes these details into a searchable vector store alongside your internal kitchen manuals. When staff ask about a specific dietary requirement, the agent queries the combined knowledge base to provide an accurate answer.

Ground order acceptance in real API data

The `update_order_status` tool gives your RAG applications write access to the delivery platform. Agents ground their acceptance decisions in actual API data rather than hallucinated rules. You configure a `FunctionAgent` to evaluate current kitchen capacity before confirming new requests. If the indexed data shows a backlog, the system rejects the ticket within the mandatory ten-minute window.

Map POS logs to Deliveroo MCP Server updates

`create_prep_stage` and `create_sync_status` push progress updates from your local POS back to the platform. This Deliveroo MCP Server turns static RAG pipelines into active operational assistants. Passing `include_resources=True` to the client allows your agent to read POS logs directly. The system then maps those log events to specific preparation stages without manual data entry.

Setup guide

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

Initialize a `BasicMCPClient` with your Vinkius URL and wrap it in `McpToolSpec`. Call `to_tool_list_async()` to pass the functions to your agent.

Yes, your agent can trigger `create_prep_stage` based on semantic search results. The system reads your kitchen logs and maps them to platform updates.

Use the `allowed_tools` filter when configuring your `McpToolSpec`. This prevents the agent from calling disruptive endpoints like order rejection by mistake.

Yes, all tools support asynchronous execution. This prevents blocking your main thread while waiting for POS injection statuses to resolve.

The MCP Server processes customer delivery addresses and preparation times. Vinkius routes all traffic through zero-trust ephemeral endpoints, meaning no persistent data remains on the intermediary layer.

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