Ubereats

io.github.markswendsen-codePublished by GitHub account markswendsen-codev0.1.0Updated Oct 24, 2026

MCP server for Uber Eats - let AI agents order food delivery

VerifiedSTDIODesktop onlyLocation & LifestyleBrowser Automation

Overview

AI-generated overview

Unofficial Uber Eats connector that lets an AI assistant search restaurants, browse menus, build a cart, place food orders and track delivery.

What you can do
  • Search restaurants by name, cuisine or food type and open a restaurant's full menu with item details and prices
  • Set the delivery address and manage the login session (check status, get a login URL, log out)
  • Add items with quantity and special instructions, view the cart, or clear it
  • Preview a checkout and place the order only with an explicit confirmation flag
  • Track an active order's status, progress and ETA
When to use it
Useful when you want an assistant to handle food-delivery browsing and ordering end to end in a region where Uber Eats operates, including reordering and checking on an order in progress. Not needed if you only want restaurant information without ordering.
Requirements
Runs locally via npm or npx, so Node.js 18+ is required. Playwright installs a Chromium browser on first run. An active Uber Eats account with a saved payment method is needed; login happens through a browser URL returned by the status tool, and session cookies are kept at a local path. Uber Eats must be available in your region.
Before you install
The server can place real orders that charge your saved payment method, so review the preview step before confirming. It drives Uber Eats through browser automation with stealth fingerprinting, which may conflict with the site's terms. Session cookies are stored unencrypted in a local file, so protect that file. Menu customizations and dynamic pricing may not match what is actually ordered.

Installation

In SourceWeft

  1. Open Ubereats in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@striderlabs/mcp-ubereats

[npm] [MCP Registry] [License: MIT]

MCP server for Uber Eats — let AI agents search restaurants, browse menus, place orders, and track deliveries.

Built by Strider Labs.

Features

  • Search restaurants by name, cuisine, or food type
  • Browse full menus with item details and prices
  • Add items to cart with quantity and special instructions
  • Clear cart and start fresh
  • Place orders with a mandatory confirmation step
  • Track active order status and delivery progress
  • Persistent sessions — stay logged in across restarts

Installation

bash
npm install -g @striderlabs/mcp-ubereats

Or run directly with npx:

bash
npx @striderlabs/mcp-ubereats

Configuration

Add to your MCP client configuration (e.g., Claude Desktop ~/Library/Application Support/Claude/claude_desktop_config.json):

json
{  "mcpServers": {    "ubereats": {      "command": "npx",      "args": ["-y", "@striderlabs/mcp-ubereats"]    }  }}

Authentication

This connector uses Playwright browser automation. On first use:

  1. Call ubereats_status — it will return a login URL
  2. Open the URL in your browser and log in to Uber Eats
  3. Run ubereats_status again to verify the session was saved
  4. Session cookies are stored at ~/.strider/ubereats/cookies.json
  5. Sessions persist automatically across restarts

To log out or reset your session:

ubereats_logout

Available Tools

Session Management

ToolDescription
ubereats_statusCheck login status; returns login URL if not authenticated
ubereats_loginGet the login URL to open in a browser
ubereats_logoutClear stored session cookies (log out)

Delivery

ToolDescription
ubereats_set_addressSet delivery address before searching

Restaurants & Menus

ToolDescription
ubereats_searchSearch restaurants by name, food type, or cuisine
ubereats_get_restaurantGet restaurant details and full menu

Cart & Ordering

ToolDescription
ubereats_add_to_cartAdd an item to cart with quantity and special instructions
ubereats_view_cartView current cart contents and totals
ubereats_clear_cartRemove all items from cart
ubereats_checkoutPreview or place the order (confirm=true to place)
ubereats_track_orderTrack an active order's status and ETA

Example Usage

Check login status

json
{  "tool": "ubereats_status"}

Set delivery address

json
{  "tool": "ubereats_set_address",  "arguments": {    "address": "123 Main St, San Francisco, CA 94102"  }}

Search for restaurants

json
{  "tool": "ubereats_search",  "arguments": {    "query": "sushi",    "cuisine": "japanese"  }}

Get restaurant menu

json
{  "tool": "ubereats_get_restaurant",  "arguments": {    "restaurantId": "nobu-restaurant-sf"  }}

Add to cart

json
{  "tool": "ubereats_add_to_cart",  "arguments": {    "restaurantId": "nobu-restaurant-sf",    "itemName": "Spicy Tuna Roll",    "quantity": 2,    "specialInstructions": "No wasabi please"  }}

Preview order before placing

json
{  "tool": "ubereats_checkout",  "arguments": {    "confirm": false  }}

Place the order

json
{  "tool": "ubereats_checkout",  "arguments": {    "confirm": true  }}

Track order

json
{  "tool": "ubereats_track_order",  "arguments": {    "orderId": "abc123"  }}

Typical Workflow

1. ubereats_status          — check if logged in2. ubereats_set_address     — set where to deliver3. ubereats_search          — find restaurants4. ubereats_get_restaurant  — browse the menu5. ubereats_add_to_cart     — add items6. ubereats_view_cart       — review cart7. ubereats_checkout        — preview (confirm=false), then place (confirm=true)8. ubereats_track_order     — track delivery

Requirements

  • Node.js 18+
  • Playwright (Chromium browser auto-installed on first run)
  • An active Uber Eats account with a saved payment method

How It Works

  1. Headless Chrome — Playwright runs a real browser in the background
  2. Stealth mode — Browser fingerprint mimics a real user to avoid detection
  3. Cookie persistence — Login sessions are saved and reloaded automatically
  4. Structured responses — All tool outputs are JSON for easy parsing

Security

  • Session cookies stored locally at ~/.strider/ubereats/cookies.json
  • No credentials are stored — authentication uses the browser-based Uber login flow
  • Cookies never leave your machine

Limitations

  • Uber Eats must be available in your region
  • Menu customizations (modifiers, options) may require additional interaction
  • Order placement requires a valid payment method on your Uber Eats account
  • Dynamic pricing and availability may differ from what is displayed

Development

bash
git clone https://github.com/markswendsen-code/mcp-ubereats.gitcd mcp-ubereatsnpm installnpm run buildnpm start

License

MIT © Strider Labs

Related

Source: README.md at commit b517a8c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.