Meituan Waimai MCP Server for Mastra AI 10 tools — connect in under 2 minutes
Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect Meituan Waimai through the Vinkius and Mastra agents discover all tools automatically — type-safe, streaming-ready, and deployable anywhere Node.js runs.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";
async function main() {
// Your Vinkius token — get it at cloud.vinkius.com
const mcpClient = await createMCPClient({
servers: {
"meituan-waimai": {
url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
},
},
});
const tools = await mcpClient.getTools();
const agent = new Agent({
name: "Meituan Waimai Agent",
instructions:
"You help users interact with Meituan Waimai " +
"using 10 tools.",
model: openai("gpt-4o"),
tools,
});
const result = await agent.generate(
"What can I do with Meituan Waimai?"
);
console.log(result.text);
}
main();
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Meituan Waimai MCP Server
Connect your Meituan Waimai (美团外卖) restaurant operations to any AI agent and transform your delivery management through natural conversation. Meituan Waimai is China's largest food delivery platform, handling millions of daily orders across hundreds of thousands of restaurants.
Mastra's agent abstraction provides a clean separation between LLM logic and Meituan Waimai tool infrastructure. Connect 10 tools through the Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution — deployable to any Node.js host in one command.
What you can do
- Order Management — Retrieve detailed order information, list orders by status (pending, confirmed, delivering, completed, cancelled)
- Order Lifecycle Control — Confirm new orders, mark orders as delivering, complete deliveries, or cancel with explanations
- Refund Processing — Approve or reject customer refund requests with detailed reasoning and order verification
- Restaurant Information — Query restaurant details including ratings, addresses, business hours, and delivery coverage
- Menu Management — List full restaurant catalogs, filter by category, view prices, descriptions, and stock levels
- Stock Control — Update item availability in real-time, mark items as sold out, or replenish inventory
- Delivery Tracking — Mark orders as out for delivery with rider information for customer transparency
The Meituan Waimai MCP Server exposes 10 tools through the Vinkius. Connect it to Mastra AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Meituan Waimai to Mastra AI via MCP
Follow these steps to integrate the Meituan Waimai MCP Server with Mastra AI.
Install dependencies
Run npm install @mastra/core @mastra/mcp @ai-sdk/openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.ts and run with npx tsx agent.ts
Explore tools
Mastra discovers 10 tools from Meituan Waimai via MCP
Why Use Mastra AI with the Meituan Waimai MCP Server
Mastra AI provides unique advantages when paired with Meituan Waimai through the Model Context Protocol.
Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure — add Meituan Waimai without touching business code
Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation
TypeScript-native: full type inference for every Meituan Waimai tool response with IDE autocomplete and compile-time checks
One-command deployment to any Node.js host — Vercel, Railway, Fly.io, or your own infrastructure
Meituan Waimai + Mastra AI Use Cases
Practical scenarios where Mastra AI combined with the Meituan Waimai MCP Server delivers measurable value.
Automated workflows: build multi-step agents that query Meituan Waimai, process results, and trigger downstream actions in a typed pipeline
SaaS integrations: embed Meituan Waimai as a first-class tool in your product's AI features with Mastra's clean agent API
Background jobs: schedule Mastra agents to query Meituan Waimai on a cron and store results in your database automatically
Multi-agent systems: create specialist agents that collaborate using Meituan Waimai tools alongside other MCP servers
Meituan Waimai MCP Tools for Mastra AI (10)
These 10 tools become available when you connect Meituan Waimai to Mastra AI via MCP:
cancel_order
Requires a cancellation reason explaining why the order is being cancelled (e.g., "restaurant closed", "item out of stock", "unable to prepare"). The order must be in a cancellable state (not already completed or delivered). Use carefully as cancellations impact merchant ratings and customer experience. Cancel a Meituan delivery order with a reason
complete_order
This is the final state in the order lifecycle and indicates the customer has received their food. Should only be called after the delivery rider has confirmed drop-off or the customer has picked up the order. Triggers payment settlement to the merchant. Mark a Meituan delivery order as completed
confirm_order
This transitions the order to confirmed status and begins the preparation workflow. Required step before marking the order as delivering. Use the order ID from the order list and the restaurant POI ID. Essential for acknowledging new orders and starting the fulfillment process. Confirm a pending Meituan delivery order
get_order_detail
Use the order ID obtained from the order list to track specific orders, verify order contents, check delivery addresses, or investigate customer complaints. Essential for order management and customer service operations. Get detailed information about a specific Meituan delivery order
get_order_list
Filter by order status: 1=待确认 (pending confirmation), 3=已确认 (confirmed), 5=配送中 (delivering), 7=已完成 (completed), 8=已取消 (cancelled). Pagination uses page number and limit parameters. Critical for monitoring incoming orders, tracking order volume, and managing the order pipeline. List orders for a Meituan restaurant with optional status filter
get_restaurant_info
Use the POI ID (Point of Interest identifier) to get restaurant details before managing orders, verifying delivery coverage, or checking business hours. Essential for multi-restaurant operators managing multiple POIs. Get detailed information about a Meituan restaurant/POI
handle_refund
When rejecting, provide a reason explaining the refusal. Refund requests typically come with customer explanations and evidence. Use order details to verify the claim before making a decision. Approved refunds are processed back to the customer's original payment method. Approve or reject a refund request for a Meituan order
list_menus
Optionally filter by category ID to get items from a specific menu section (e.g., appetizers, mains, drinks). Critical for inventory management, price updates, and menu optimization. Returns stock quantities to help identify low-stock items. List menu items for a Meituan restaurant
mark_delivering
Optionally includes delivery rider name and phone number for customer tracking. Use this for self-delivery orders where the restaurant manages their own riders. For Meituan-managed delivery, the platform handles this automatically. Mark a Meituan order as being delivered (out for delivery)
update_stock
Use this to mark items as sold out (stock=0) when ingredients run out, or replenish stock when new inventory arrives. Stock changes immediately reflect on the customer-facing menu. Essential for preventing orders for unavailable items and maintaining accurate inventory. Food ID is obtained from the list_menus tool. Update stock quantity for a menu item in Meituan
Example Prompts for Meituan Waimai in Mastra AI
Ready-to-use prompts you can give your Mastra AI agent to start working with Meituan Waimai immediately.
"Show me all pending orders for my restaurant POI123."
"Mark food ID 4567 as sold out for POI123 — we ran out of chicken."
"Handle refund request for order ORD-789 — customer says food never arrived. Approve it."
Troubleshooting Meituan Waimai MCP Server with Mastra AI
Common issues when connecting Meituan Waimai to Mastra AI through the Vinkius, and how to resolve them.
createMCPClient not exported
npm install @mastra/mcpMeituan Waimai + Mastra AI FAQ
Common questions about integrating Meituan Waimai MCP Server with Mastra AI.
How does Mastra AI connect to MCP servers?
MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.Can Mastra agents use tools from multiple servers?
Does Mastra support workflow orchestration?
Connect Meituan Waimai with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Meituan Waimai to Mastra AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.