Doordash

io.github.markswendsen-code由 GitHub 账号 markswendsen-code 发布v0.4.1更新于 Oct 24, 2026

MCP server for DoorDash - let AI agents order food delivery autonomously with browser-based ordering

已验证STDIO仅桌面位置与生活浏览器自动化

概览

AI 生成的概览

一个本地 MCP 服务器，让 AI 助手搜索 DoorDash 餐厅、浏览菜单、加入购物车、下单外卖并跟踪配送状态。

可以做什么
按名称、菜系或食物类型搜索餐厅，并浏览含商品详情和价格的菜单。将商品按数量和特殊要求加入购物车。经确认步骤提交外卖订单并跟踪订单状态。跨重启保持按用户隔离的持久登录会话，并自动处理多因素认证。
适用场景
适合希望助手端到端处理日常 DoorDash 点餐的场景，例如查找附近餐厅、比较菜单并提交外卖订单，而不只是查询信息。最适合已有 DoorDash 账户、并愿意让代理代为操作的用户。
运行要求
以 Node.js 本地进程运行（需 Node.js 18 或更高版本），通过 npm 包安装，通常在 Claude Desktop 配置中用 npx 启动。需要 DoorDash 账户，通过 DOORDASH_EMAIL 和 DOORDASH_PASSWORD 环境变量提供，并用 DOORDASH_ADDRESS 指定配送地址。仅支持桌面端，需要网络访问和浏览器自动化运行环境。
安装前请注意
该服务器通过 DOORDASH_PASSWORD 保存你的 DoorDash 账户密码并代为登录，请谨慎保管该密钥，优先使用本地 env 文件。它可以提交真实订单并产生费用，让代理无人值守下单前请确认确认步骤。它通过浏览器自动化和拟真浏览器配置操作 DoorDash，而非官方 API，可能与 DoorDash 条款冲突，且网站改版时可能失效。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Doordash，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

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:
json
{  "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)

bash
npm install @striderlabs/mcp-doordash

Or with npx directly:

bash
npx @striderlabs/mcp-doordash

Features

  • 🔍 Search restaurants by name, cuisine, or food type
  • 📜 Browse menus with full item details and prices
  • 🛒 Add to cart with quantity and special instructions
  • 💳 Place orders with confirmation step
  • 📍 Track orders with real-time status updates
  • 🔐 Persistent sessions - stay logged in across restarts
  • 🔄 Automatic MFA - handles multi-factor authentication
  • 📱 Per-user credentials - encrypted session storage

Tested & Compatible

ComponentVersionStatus
MCP SDK^1.0.0✅
Node.js18+✅
Claude DesktopLatest✅
Claude (API)claude-3.5-sonnet+✅
Anthropic SDK^0.20+✅

Metrics

  • Weekly downloads: 395 (Apr 10-17, 2026) — #1 Strider Labs connector (+24% growth)
  • Status: ✅ Live in production
  • Reliability: 85%+ task completion rate
  • Discovery: npm, Claude Plugins, mcpservers.org, ClawHub, PulseMCP

Available Elsewhere

How It Works

For Agents

Your agent can use these capabilities:

javascript
// Search for restaurantsrestaurants = search_restaurants({  location: "San Francisco, CA",  cuisine: "Thai",  max_delivery_time: 30})
// Browse a restaurant's menumenu = get_restaurant_menu({  restaurant_id: "thai-place-downtown",  search: "Pad Thai"})
// Place an orderorder = place_order({  restaurant_id: "thai-place-downtown",  items: [    { item_id: "pad_thai", quantity: 1 },    { item_id: "spring_rolls", quantity: 2 }  ],  delivery_address: "123 Main St, San Francisco, CA",  special_instructions: "Extra lime on the side"})
// Track deliverystatus = track_order({ order_id: order.order_id })

Session Management

  • Each user has encrypted, persistent credentials
  • Automatic OAuth token refresh
  • MFA handling (SMS/email)
  • Sessions survive agent restarts

Reliability

  • 85%+ task completion rate
  • Automated UI change detection (connectors update when DoorDash changes)
  • Fallback paths for failures
  • 24/7 monitoring + alerting

Configuration

Environment Variables

bash
# Optional: Use a specific DoorDash account[email protected]DOORDASH_PASSWORD=your-password  # Highly recommend using .env file

Self-Hosted

bash
# Clone the repogit clone https://github.com/striderlabsdev/mcp-doordashcd mcp-doordash
# Install dependenciesnpm install
# Start the servernpm start
# Your agent can now connect to localhost:3000

Architecture

How We Connect

This connector uses browser automation (Playwright) to interact with DoorDash, because DoorDash doesn't have a public API. Here's why that's safe and reliable:

  • User-controlled: Your agent only accesses your own DoorDash account
  • Session-based: We store your login session securely, not your password
  • Change-aware: We detect DoorDash UI changes and alert immediately
  • Fingerprinting: We use realistic browser profiles to avoid bot detection
  • Rate-limited: We respect DoorDash's infrastructure with appropriate delays

Security

  • Credentials stored encrypted in your local .env or secure vault
  • Sessions isolated per user
  • No data sent to third parties
  • MIT Licensed — audit the code yourself

Support

Contributing

We welcome contributions! Areas of interest:

  • Bug reports and fixes
  • Feature requests (new restaurants, cuisines, etc.)
  • Performance improvements
  • Documentation enhancements

See CONTRIBUTING.md for guidelines.

License

MIT — Free to use, modify, and distribute. See LICENSE for details.

Built by Strider Labs — Making AI agents actually useful.

GitHub | Website | Discord

来源：README.md，提交 9a6fe59

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

1
  1. v0.4.1最新Sep 16, 2026

评分

已满足适用检查项的 40%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。