Instacart MCP Server
Enables AI agents to search for products, manage shopping carts, and place grocery orders on Instacart using browser automation. It includes comprehensive tools for store discovery, product searching, and secure checkout with explicit user confirmation.
README
@striderlabs/mcp-instacart
MCP server that gives AI agents the ability to search products, manage cart, and place grocery orders on Instacart.
Built by Strider Labs — building the action layer for AI agents.
Features
- 🔍 Search Products — Find products across Instacart with prices and availability
- 🛒 Cart Management — Add items, view cart, clear cart
- 📦 Place Orders — Preview and place orders with delivery time selection
- 🔐 Session Persistence — Cookies saved locally for seamless re-authentication
- 🛡️ Order Safety — Requires explicit confirmation before placing orders
Installation
npm install @striderlabs/mcp-instacart
Or install globally:
npm install -g @striderlabs/mcp-instacart
Prerequisites
This package requires Playwright browsers. Install them with:
npx playwright install chromium
MCP Client Configuration
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"instacart": {
"command": "npx",
"args": ["@striderlabs/mcp-instacart"]
}
}
}
Other MCP Clients
npx @striderlabs/mcp-instacart
Available Tools
Authentication
| Tool | Description |
|---|---|
instacart_status |
Check login status and session info |
instacart_login |
Initiate login flow (returns URL for manual login) |
instacart_logout |
Clear saved session and cookies |
Shopping
| Tool | Description |
|---|---|
instacart_search |
Search for products by name |
instacart_stores |
List available stores for delivery location |
instacart_set_address |
Set delivery address or zip code |
Cart
| Tool | Description |
|---|---|
instacart_add_to_cart |
Add a product to cart |
instacart_view_cart |
View cart contents and totals |
instacart_clear_cart |
Remove all items from cart |
Orders
| Tool | Description |
|---|---|
instacart_preview_order |
Preview order before placing |
instacart_place_order |
Place order (requires confirm=true) |
Usage Examples
Check Session Status
User: Am I logged into Instacart?
Agent: [calls instacart_status]
→ Returns login state, email, saved address
Search for Products
User: Find organic bananas on Instacart
Agent: [calls instacart_search with query="organic bananas"]
→ Returns list of products with prices
Build a Shopping List
User: Add milk, eggs, and bread to my Instacart cart
Agent:
[calls instacart_add_to_cart with product="milk"]
[calls instacart_add_to_cart with product="eggs"]
[calls instacart_add_to_cart with product="bread"]
→ Items added to cart
View Cart
User: What's in my Instacart cart?
Agent: [calls instacart_view_cart]
→ Returns items, quantities, subtotal, fees, total
Place Order
User: Place my Instacart order
Agent: [calls instacart_place_order with confirm=false]
→ Returns preview asking for confirmation
User: Yes, place it
Agent: [calls instacart_place_order with confirm=true]
→ Order placed, returns confirmation
Authentication Flow
Instacart requires browser-based login. The flow:
- Call
instacart_login— returns login URL - User opens URL and logs in manually
- Cookies are automatically saved to
~/.strider/instacart/ - Future sessions use saved cookies
Session cookies persist until they expire or instacart_logout is called.
Configuration
Session data is stored in:
~/.strider/instacart/
├── cookies.json # Browser cookies
└── session.json # Session metadata
Order Safety
The instacart_place_order tool has a built-in safety mechanism:
- Without
confirm=true: Returns a preview, does not place order - With
confirm=true: Actually places the order
Agents should ALWAYS show the preview and get explicit user confirmation before calling with confirm=true.
Technical Details
- Uses Playwright for browser automation
- Runs headless by default
- Includes stealth patches to avoid detection
- Supports all Instacart stores available in your area
Limitations
- Requires manual login (no programmatic auth)
- Browser automation may break if Instacart updates their UI
- Some anti-bot measures may require solving CAPTCHAs manually
- Payment methods must be pre-configured in your Instacart account
Troubleshooting
"Not logged in" errors
Run instacart_login and complete the login flow manually.
Timeout errors
Instacart pages may be slow. The server will retry automatically, but you can also:
- Check your internet connection
- Try again after a moment
"Could not find element" errors
Instacart may have updated their UI. Please file an issue with details.
CAPTCHA challenges
Some actions may trigger CAPTCHA. You'll need to:
- Open Instacart in a regular browser
- Complete the CAPTCHA
- Try the MCP action again
Development
# Clone the repo
git clone https://github.com/markswendsen-code/mcp-instacart
cd mcp-instacart
# Install dependencies
npm install
# Install Playwright browsers
npx playwright install chromium
# Build
npm run build
# Run locally
node dist/index.js
License
MIT
Links
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。