markswendsen-code avatar

Doordash

markswendsen-code/mcp-doordash

A browser automation connector that lets AI agents order food through DoorDash without an official API. Exposes search_restaurants, get_restaurant_menu, place_order, and track_order operations using Playwright to drive the DoorDash website. Handles session persistence, automatic MFA, and encrypted credential storage per user. Built by Strider Labs as part of their action execution toolkit. Useful when you want Claude to actually place delivery orders autonomously rather than just suggesting restaurants. The 85% completion rate and UI change detection suggest they're maintaining it as DoorDash updates their interface. Runs via npx for Claude Desktop or self-hosted. MIT licensed, so you can audit the browser automation yourself.

GitHub stars
4
tools
4
auth
Secret needed
transport
STDIO
env vars
3
last updated
Apr 17, 2026

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

search_restaurantsSearch for restaurants by location, cuisine, and maximum delivery time.

Search for restaurants by location, cuisine, and maximum delivery time.

No parameter schema in public metadata yet.

get_restaurant_menuBrowse a restaurant's menu, optionally filtered by search term.

Browse a restaurant's menu, optionally filtered by search term.

No parameter schema in public metadata yet.

place_orderPlace a food delivery order with items, delivery address, and special instructions.

Place a food delivery order with items, delivery address, and special instructions.

No parameter schema in public metadata yet.

track_orderTrack the status of an existing order by order ID.

Track the status of an existing order by order ID.

No parameter schema in public metadata yet.

Sponsors

Configuration

DOORDASH_EMAIL*

DoorDash email/phone for authentication

DOORDASH_PASSWORD*secret

DoorDash account password

DOORDASH_ADDRESS

Delivery address zip code or full address

Readme

@striderlabs/mcp-doordash

Order food delivery via DoorDash using AI agents

npm MCP Registry Claude Desktop License: MIT

Part of Strider Labs — action execution for personal AI agents.

Get Started in 2 Minutes

For Claude Desktop Users

  1. Add this to ~/.openclaw/config.json or your Claude Desktop config:
{
  "mcpServers": {
    "doordash": {
      "command": "npx",
      "args": ["-y", "@striderlabs/mcp-doordash"]
    }
  }
}
  1. Restart Claude.
  2. Tell Claude: "Order Thai food from nearby for delivery today"

Your agent can now place orders. That's it.


Installation (NPM)

npm install @striderlabs/mcp-doordash

Or with npx directly:

npx @striderlabs/mcp-doordash

View the full README on GitHub

Details

Repository
github.com/markswendsen-code/mcp-doordash
Categories
Web & Browser Automation, Finance & Commerce
Package
@striderlabs/mcp-doordash
Transport
STDIO
Auth
Required
Registry
MCP registry, active

More from markswendsen-code

Related Web & Browser Automation MCP servers

View all
1mikusnuz avatarCwsmikusnuz/cws-mcpMCP server for Chrome Web Store — extension upload, publish, status, and rollout4stars
2felixgeelhaar avatarScoutfelixgeelhaar/scoutBrowser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.3stars
3hayodev avatarSafari DevTools MCPhayodev/safari-devtools-mcpMCP server for Safari DevTools — browser debugging and automation for AI coding agents2stars
4arcededev avatarAIR SDKarcededev/air-sdkCollective intelligence for browser automation agents. Site capabilities, selectors, and extraction.1stars
5bgaze avatarSnapstack Serverbgaze/snapstack-serverLocal always-on server for SnapStack: browser capture intake + MCP over 127.0.0.1.1stars
6scrapeer avatarScrapeerscrapeer/scrapeer-mcp-serverRun Scrapeer visual web-scraping flows from AI agents.1stars