Content
# Canuckeats MCP — AI-Powered Canadian Food Delivery
**Order UberEats and DoorDash in Canada through AI agents.** Canuckeats is a Model Context Protocol (MCP) service that lets AI agents browse menus and place real food delivery orders across 89 Canadian cities — no human in the loop required.
> **Endpoint:** `https://mcp.canuckeats.com/mcp`
> **Registration:** `POST https://mcp.canuckeats.com/register` — free, instant, no email confirmation
> **Protocol:** [MCP 2024-11-05](https://modelcontextprotocol.io/specification/2025-11-05) — Streamable HTTP
> **Coverage:** 17,000+ restaurants · 89 cities · Canada only · UberEats + DoorDash
---
## Why Canuckeats for Agents?
Canadian residents who want AI assistants to handle their food delivery face a gap: UberEats and DoorDash don't offer agent-accessible APIs. Canuckeats bridges that gap. An agent given a task like *"order me sushi for dinner"* can:
1. Find open restaurants near the user's address in their city
2. Browse full menus with prices and modifier options
3. Get a precise cost breakdown before charging anything
4. Place the order and confirm payment in a single tool call
5. Track delivery status and report the ETA back to the user
Every order dispatches through real UberEats or DoorDash accounts — the same food, same drivers, same cities.
---
## Get an API Key — Instant Self-Signup
No waiting, no approval queue. Register your agent and start making calls in under 30 seconds:
```http
POST https://mcp.canuckeats.com/register
Content-Type: application/json
{
"agent_name": "MyFoodAgent",
"email": "you@yourproject.com",
"description": "AI assistant that orders lunch for remote teams"
}
```
**Response:**
```json
{
"api_key": "your-api-key-shown-once",
"key_id": "uuid",
"scopes": ["catalog:read", "orders:write"],
"medusa_customer_id": "cus_...",
"mcp_endpoint": "https://mcp.canuckeats.com/mcp",
"docs": "https://github.com/canuckeats/MCP",
"message": "Registration successful. Keep your API key secure — it is shown only once and cannot be retrieved again."
}
```
**The key is shown once.** Save it immediately. If you lose it, register again with the same email — duplicate email is rejected, so use a unique email per key.
**Registration limits:** Up to 5 registrations per IP per 24 hours. One key per email address. Disposable email addresses are not accepted.
---
## What Cities Are Covered?
All major Canadian cities: **Calgary, Edmonton, Vancouver, Toronto, Ottawa, Montreal, Winnipeg, Hamilton, London, Halifax, Saskatoon, Regina, Kelowna, Victoria, Abbotsford, Barrie, Brampton, Burlington, Burnaby, Coquitlam** and 69 more across **Alberta, British Columbia, Ontario, Manitoba, Saskatchewan, Nova Scotia, New Brunswick** and other provinces.
Use `list_cities` to get the current full list with restaurant counts.
---
## 8 Tools — Full Order Lifecycle
| Tool | Auth | Description |
|------|------|-------------|
| `list_cities` | API key | List all 89 cities with restaurant counts |
| `search_restaurants` | API key | Search by city, cuisine, name, or price range |
| `get_restaurant` | API key | Full restaurant details |
| `get_menu` | API key | Complete menu with sections, prices, and modifier options |
| `validate_order` | API key | Preview exact total — no charge, no order created |
| `create_order` | API key | Create order + Stripe PaymentIntent (no charge yet) |
| `confirm_payment` | API key | Charge card and dispatch order to platform |
| `get_order_status` | API key | Live status, tracking URL, and ETA |
---
## Quickstart: Connect in 60 Seconds
### Python (using `mcp` SDK)
```python
import asyncio, json
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
async def main():
async with streamablehttp_client(
"https://mcp.canuckeats.com/mcp",
headers={"Authorization": "Bearer YOUR_API_KEY"}
) as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
# Find restaurants
result = await session.call_tool("search_restaurants", {
"city_slug": "vancouver-bc",
"query": "sushi",
"limit": 5
})
restaurants = json.loads(result.content[0].text)
print(f"Found {restaurants['total']} sushi spots in Vancouver")
asyncio.run(main())
```
### TypeScript / Node.js
```typescript
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
const client = new Client({ name: "my-agent", version: "1.0" }, { capabilities: {} })
await client.connect(new StreamableHTTPClientTransport(
new URL("https://mcp.canuckeats.com/mcp"),
{ requestInit: { headers: { Authorization: "Bearer YOUR_API_KEY" } } }
))
const result = await client.callTool({ name: "list_cities", arguments: {} })
const cities = JSON.parse(result.content[0].text)
console.log(`${cities.length} cities available`)
```
### Claude Desktop Integration
Add to your Claude Desktop MCP config (`claude_desktop_config.json`):
```json
{
"mcpServers": {
"canuckeats": {
"type": "streamable-http",
"url": "https://mcp.canuckeats.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
```
Then ask Claude: *"Order me a pepperoni pizza from anywhere in Calgary to 400 4 Ave SW, Calgary AB T2P 0J4."*
---
## Complete Order Flow
```
list_cities → get city slug (e.g. "calgary-ab")
↓
search_restaurants → get restaurant id
↓
get_menu → get menu_item_id + modifier options
↓
validate_order → confirm total (no charge)
↓
create_order → get order_id + stripe_payment_intent_id
↓
confirm_payment → charge pm_... and dispatch
↓
get_order_status (poll) → track until delivered
```
See [docs/examples/order-flow.md](docs/examples/order-flow.md) for a narrated walkthrough with real request/response examples.
---
## Rate Limits
| Endpoint | Limit |
|----------|-------|
| `/register` | 5 registrations per IP per 24 hours |
| All tools (general) | 60 requests / minute per key |
| `create_order`, `confirm_payment` | 10 requests / minute per key |
Response headers `X-RateLimit-Limit` and `X-RateLimit-Remaining` are included on every MCP response.
---
## Key Facts for Agents
- **Canadian addresses only.** Province must be a two-letter code: `AB`, `BC`, `ON`, `QC`, `MB`, `SK`, `NS`, `NB`, `NL`, `PE`, `NT`, `YT`, `NU`.
- **Payment method:** `confirm_payment` accepts a Stripe `pm_*` payment method ID. The agent's operator must provide a valid Stripe payment method that has already been set up with Stripe.
- **Order dispatch is automatic.** After `confirm_payment` succeeds, orders are forwarded to UberEats or DoorDash within 2–5 minutes. Use `get_order_status` to track.
- **Delivery platform is chosen automatically** based on which platform has that restaurant in its catalog.
- **`source_id` on menu items** is used internally — you do not need to reference it directly. Just use `menu_item_id` (the integer `id` field) when calling `create_order`.
- **Modifiers are optional.** If a menu item has required modifiers (e.g. drink size), omitting them may cause the order to fail at the platform level. Check `modifier_groups[].min_selections` to know which are required.
- **Scheduled delivery** is supported via the `scheduled_for` ISO 8601 field on `create_order`. Use ASAP delivery by omitting this field.
---
## Supported Delivery Platforms
| Platform | Coverage |
|----------|----------|
| **UberEats** | All 89 cities |
| **DoorDash** | All 89 cities |
Orders are placed on whichever platform has the requested restaurant. The `source` field on each restaurant (`"ubereats"` or `"doordash"`) tells you which platform will be used.
---
## Canadian Cities — Full List
Alberta · British Columbia · Manitoba · New Brunswick · Newfoundland · Nova Scotia · Ontario · Prince Edward Island · Quebec · Saskatchewan
Use `list_cities` for the live list. Notable cities include:
**Alberta:** Calgary, Edmonton, Red Deer, Lethbridge, Airdrie, Medicine Hat, Grande Prairie, Fort McMurray
**BC:** Vancouver, Surrey, Burnaby, Richmond, Kelowna, Abbotsford, Victoria, Coquitlam, Langley
**Ontario:** Toronto, Ottawa, Hamilton, London, Brampton, Mississauga, Barrie, Windsor, Kitchener, Ajax, Aurora
**Quebec:** Montreal (selected areas)
**Prairie & Atlantic:** Saskatoon, Regina, Winnipeg, Halifax, Moncton, Fredericton
---
## API Reference
- [Full tool schemas with TypeScript types](docs/tools.md)
- [Quick start guide with code samples](docs/quickstart.md)
- [End-to-end order walkthrough](docs/examples/order-flow.md)
- [Machine-readable tools manifest](tools.json)
---
## Support
- **Issues / questions:** Open a GitHub issue in this repo
- **API key lost:** Re-register with a different email, or email hello@canuckeats.com
- **Order issues:** Email hello@canuckeats.com with your `order_id`
- **Website:** [canuckeats.com](https://canuckeats.com)
MCP Config
Below is the configuration for this MCP Server. You can copy it directly to Cursor or other MCP clients.
mcp.json
Connection Info
You Might Also Like
AP2
AP2 provides code samples and demos for the Agent Payments Protocol.
google-meta-ads-ga4-mcp
MCP server for Google Ads, Meta Ads & GA4 — works with ChatGPT, Claude,...
nuwax
Nuwax AI enables easy building and deployment of private Agentic AI solutions.
Train-in-Silence
The first Task-Aware MCP server and automated VRAM calculator for LLM...
stacklit
108,000 lines of code. 4,000 tokens of index. One command makes any repo...
AppClaw
AI-powered mobile automation agent — describe what you want in plain...