npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

foodpanda-mcp

v1.2.1

Published

MCP server for ordering food from foodpanda.ph via AI assistants

Readme

foodpanda-mcp

An MCP server that lets AI assistants order food from foodpanda.ph on your behalf.

Tell your AI assistant what you want to eat, and it handles the rest — searching restaurants, browsing menus, building a cart, and placing orders through your foodpanda account.

Features

  • Search restaurants by name or cuisine near your delivery address
  • Browse full menus with prices, descriptions, and customization options
  • Build a cart with real-time price validation from foodpanda
  • Two-step checkout with order preview and explicit confirmation
  • Checkout with Cash on Delivery (credit card and GCash require browser-based payment flows and are not supported)
  • Automatic token refresh via browser login (no more copying tokens from DevTools)

Quick Start

1. Get your delivery coordinates

Get the latitude and longitude of your delivery address (right-click on Google Maps → copy coordinates).

Note: You no longer need to manually copy a session token. The refresh_token tool handles authentication by opening a browser window for you to log in.

2. Configure your MCP client

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "foodpanda": {
      "command": "npx",
      "args": ["-y", "foodpanda-mcp"],
      "env": {
        "FOODPANDA_LATITUDE": "14.5623",
        "FOODPANDA_LONGITUDE": "121.0137"
      }
    }
  }
}

Other MCP Clients

Any MCP-compatible client that supports stdio transport will work. Set the two coordinate environment variables and run npx foodpanda-mcp. On first use, the AI will open a browser for you to log in to foodpanda.

3. Try it out

Ask your AI assistant:

"Search for Jollibee near me and show me their menu"

"Add 1 Chickenjoy to my cart"

"Preview my order and let me confirm before placing it"

Available Tools

| Tool | Description | |------|-------------| | search_restaurants | Search for restaurants by name or cuisine | | get_restaurant_details | Get restaurant info (hours, delivery fee, minimum order) | | get_menu | Browse a restaurant's menu organized by category | | get_item_details | Get full item details including topping/customization options | | add_to_cart | Add items to your cart (validates prices with foodpanda) | | get_cart | View current cart contents and totals | | remove_from_cart | Remove items from cart | | preview_order | Preview order summary with delivery address and payment methods | | place_order | Place the order after user confirmation | | refresh_token | Open a browser to log in and refresh the session token |

Environment Variables

| Variable | Required | Description | |----------|----------|-------------| | FOODPANDA_SESSION_TOKEN | No | JWT bearer token (optional — use refresh_token tool instead) | | FOODPANDA_LATITUDE | Yes | Latitude of your delivery address | | FOODPANDA_LONGITUDE | Yes | Longitude of your delivery address |

Order Safety

The checkout flow is designed with a human-in-the-loop pattern:

  1. preview_order shows the full order summary (items, totals, delivery address, payment methods)
  2. The AI is instructed to always show this to you and ask for confirmation
  3. place_order only executes after you explicitly approve

This prevents accidental orders — the AI cannot skip the confirmation step.

How It Works

  • Search uses foodpanda's GraphQL API with Apollo persisted queries
  • Restaurant details and menus use the REST API at /api/v5/vendors/{code}
  • Cart is stateless on foodpanda's side — this server maintains cart state in memory and sends the full cart to /api/v5/cart/calculate for price validation on every change
  • Checkout fetches your saved addresses and payment methods, then submits to /api/v5/cart/checkout
  • Prices are in PHP (Philippine Peso)

Building from Source

git clone https://github.com/johnwhoyou/foodpanda-mcp.git
cd foodpanda-mcp
npm install    # also installs Google Chrome via postinstall
npm run build

Then use the local build in your MCP client config:

{
  "mcpServers": {
    "foodpanda": {
      "command": "node",
      "args": ["/absolute/path/to/foodpanda-mcp/build/index.js"],
      "env": {
        "FOODPANDA_LATITUDE": "14.5623",
        "FOODPANDA_LONGITUDE": "121.0137"
      }
    }
  }
}

Limitations

  • Session tokens expire. The refresh_token tool handles this automatically — the AI opens a browser for you to log in when needed.
  • No official API. This server reverse-engineers foodpanda's internal web API. It may break if foodpanda changes their API.
  • Philippines only. Targets foodpanda.ph specifically. Other regions use different API endpoints and may not work.
  • Payment methods. Only Cash on Delivery is supported. Credit card and GCash require browser-based payment flows (Adyen SDK / app redirect) that cannot be completed through API calls. See #2.
  • Single delivery address. Uses the saved address closest to your configured coordinates.

License

MIT