Log inSubmit server
Ubereats logo

Ubereats

Search Uber Eats, manage carts, place confirmed orders, and track deliveries through MCP tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Ubereats

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "ubereats": {
      "command": "npx",
      "args": [
        "-y",
        "@striderlabs/mcp-ubereats"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @striderlabs/mcp-ubereats

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 19d ago.

Overview

The ubereats MCP server connects AI agents to Uber Eats through Playwright browser automation for restaurant search, menu browsing, ordering, and delivery tracking. It uses persistent local cookies for authentication and exposes structured JSON tools for addresses, restaurants, carts, checkout, and active orders. Reach for it when an agent needs to prepare or place Uber Eats orders using an account with a saved payment method.

Use cases

  • Search restaurants by cuisine or food type
  • Browse menus and compare available items
  • Build and review a delivery cart
  • Preview and confirm Uber Eats orders
  • Track an active delivery

Key features

  • Browser-based Uber Eats authentication
  • Persistent local login sessions
  • Restaurant and menu search
  • Cart management with item instructions
  • Confirmation-based checkout
  • Order status and ETA tracking

Tools11

What Ubereats lets your agent do. Expand a tool for its parameters.

Self-reported~166 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

8/8 checks healthy over the last 47d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · @striderlabs/mcp-ubereats (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
npm downloads177Package downloads in the last 30 days.
Last commit7mo agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed11Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Ubereats works

What ubereats MCP server does

The ubereats MCP server gives an MCP-compatible agent a workflow for ordering food through Uber Eats. It covers the process from selecting a delivery location to monitoring an active order. Agents can check whether a session is authenticated, obtain a browser login URL, set an address, search for restaurants, inspect menus, and build a cart.

Cart operations include adding items with quantities and special instructions, reviewing current contents and totals, and clearing the cart. Checkout supports two stages: a preview with confirmation disabled, followed by order placement with confirmation enabled. After an order is placed, the tracking tool can report its status and estimated arrival information.

How it works

The server uses Playwright to run a Chromium browser in the background and interact with Uber Eats. On the first authentication attempt, ubereats_status returns a URL that the user opens in a browser to log in. Calling the status tool again verifies whether the session was saved.

Cookies are stored locally at ~/.strider/ubereats/cookies.json and reloaded on later runs. Tool results are returned as JSON, making them suitable for agent workflows that need to inspect search results, menus, carts, or order state.

A typical sequence is to authenticate, set the delivery address, search for a restaurant, retrieve its menu, add items, inspect the cart, preview checkout, place the order, and then track it.

Setup and configuration

Install the package globally with npm install -g @striderlabs/mcp-ubereats, or run it without a global installation through npx @striderlabs/mcp-ubereats. An MCP client can start it with the npx command and the package name as its argument. The README gives Claude Desktop as a configuration example.

Node.js 18 or newer is required. Playwright installs the Chromium browser automatically on the first run. The account used with the ubereats MCP server must have an active Uber Eats account and a saved payment method if the workflow will place orders.

To reset authentication, call ubereats_logout; this clears the stored session cookies. The initial login flow requires opening the returned URL manually in a browser.

Tools and capabilities

  • ubereats_status checks authentication and returns a login URL when needed.
  • ubereats_login provides the login URL directly.
  • ubereats_logout removes the saved session.
  • ubereats_set_address establishes the delivery location.
  • ubereats_search searches by restaurant name, food type, or cuisine.
  • ubereats_get_restaurant returns restaurant information and its menu.
  • ubereats_add_to_cart adds an item with quantity and special instructions.
  • ubereats_view_cart returns cart contents and totals.
  • ubereats_clear_cart empties the cart.
  • ubereats_checkout previews or places an order based on the confirm value.
  • ubereats_track_order reports an active order's status and ETA.

Limitations and notes

The ubereats MCP server depends on Uber Eats availability in the user's region. Order placement requires a valid payment method already saved to the Uber Eats account. Menu customizations such as modifiers and options may need additional interaction, and displayed pricing or availability can change dynamically.

Because checkout can place a real order when confirm=true, an agent workflow should review the cart and use the preview mode before confirming. Authentication is browser-based rather than credential-based, and session state depends on the locally stored cookie file.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Ubereats

ubereats is an MCP server that connects an AI agent to Uber Eats through Playwright browser automation. Its main tools check authentication, set a delivery address, search restaurants, read menus, manage a cart, preview or place orders, and track delivery status. It keeps session cookies locally so logins can persist across restarts.

Install it with npm or run it through npx. Use `npm install -g @striderlabs/mcp-ubereats` for a global installation, or start it with `npx @striderlabs/mcp-ubereats` from an MCP client configuration.

It handles login through a browser URL rather than storing account credentials. Call `ubereats_status` or `ubereats_login`, open the returned URL, sign in to Uber Eats, and call `ubereats_status` again to verify the saved session.

Yes, it can place an order when `ubereats_checkout` is called with `confirm=true`. Use `confirm=false` first to preview the cart, and make sure the Uber Eats account has a valid saved payment method.

It requires Node.js 18 or newer, Playwright with its Chromium browser, an active Uber Eats account, and a saved payment method for ordering. Uber Eats must also be available in the user's region.

Related MCP servers

All in Delivery All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewUbereats AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/ubereats?style=directory)](https://allmcps.com/mcp/ubereats)
HTML Embed
<a href="https://allmcps.com/mcp/ubereats"><img src="https://allmcps.com/api/badge/ubereats?style=directory" alt="Ubereats on AllMCPs" /></a>