Strider Labs Instacart MCP
About
MCP server for Instacart - let AI agents order groceries and household items from local stores
Details
- Author
- markswendsen-code
- Categories
- Other, Automation
Jump to
Setup
Install Strider Labs Instacart MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/markswendsen-code/mcp-instacart
Follow the installation instructions in the repository README, then restart your MCP client.
Order groceries via Instacart using AI agents
Part ofStrider Labs— action execution for personal AI agents.
{ "mcpServers": { "instacart": { "command": "npx", "args": ["-y", "@striderlabs/mcp-instacart"] } } }
- Restart Claude.
- Tell Claude:"Order my usual groceries for delivery tomorrow morning"
Your agent can now place orders. That's it.
- 🛒Search for productsby name or category
- 📦Browse storesand product availability
- 🏪Add to cartwith quantities and special requests
- 💳Place orderswith delivery time selection
- 📍Track orderswith real-time status
- 🔐Persistent sessions- stay logged in across restarts
- 🔄Automatic MFA- handles multi-factor authentication
- 📱Per-user credentials- encrypted session storage
- ⭐Saved items- order your favorites faster
- Weekly downloads:271 (Apr 10-17, 2026) — Top grocery connector (+330% growth)
- Status:✅ Live in production
- Reliability:85%+ task completion rate
- Discovery:npm, mcpservers.org, ClawHub, PulseMCP, Glama, LobeHub
- npm:npmjs.com/@striderlabs/mcp-instacart
- Claude Plugins:Search "Strider Labs" in Claude
- mcpservers.org:Strider Labs Instacart
- Full Strider Labs:github.com/striderlabsdev/striderlabs
// Search for products products = search_products({ query: "organic milk", location: "San Francisco, CA" }) // Browse a store's offerings store_products = get_store_products({ store_id: "whole_foods_sf", category: "Dairy" }) // Add to cart add_to_cart({ product_id: "organic_milk_gallon", quantity: 2, special_instructions: "Cold stock, please" }) // Place an order order = place_order({ delivery_time: "tomorrow morning", delivery_address: "123 Main St, San Francisco, CA", special_instructions: "Ring the doorbell twice" }) // Track delivery status = track_order({ order_id: order.order_id })
- Each user has encrypted, persistent credentials
- Automatic OAuth token refresh
- MFA handling (SMS/email)
- Sessions survive agent restarts
- 85%+ task completion rate
- Automated UI change detection (connectors update when Instacart changes)
- Fallback paths for failures
- 24/7 monitoring + alerting
The MCP server uses apersistent browser profile(~/.strider/instacart/browser-profile) so your login session survives server restarts automatically.
- SetINSTACART_HEADLESS=falsein your MCP server config so the browser window is visible:
{ "mcpServers": { "instacart": { "command": "npx", "args": ["-y", "@striderlabs/mcp-instacart"], "env": { "INSTACART_HEADLESS": "false" } } } }
- Restart Claude / your MCP client.
- Ask Claude to runinstacart_login— a real browser window will open.
- Log in to Instacart inside that window.
- Runinstacart_statusto confirm authentication.
- RemoveINSTACART_HEADLESS(or set it back totrue) and restart — the saved profile keeps you logged in.
Authentication is verified by navigating to/accountand confirming the page resolves without a redirect to/loginor/authentication(positive detection). This is more reliable than checking for the absence of a "Log in" button.
# Show browser window (required for first-time login) INSTACART_HEADLESS=false # default: true (headless)
# Clone the repo git clone https://github.com/striderlabsdev/mcp-instacart cd mcp-instacart # Install dependencies npm install # Start the server npm start # Your agent can now connect to localhost:3000
This connector uses browser automation (Playwright) to interact with Instacart, because Instacart doesn't have a public API. Here's why that's safe and reliable:
- User-controlled:Your agent only accesses your own Instacart account
- Session-based:We store your login session securely, not your password
- Change-aware:We detect Instacart UI changes and alert immediately
- Fingerprinting:We use realistic browser profiles to avoid bot detection
- Rate-limited:We respect Instacart's infrastructure with appropriate delays
- Credentials stored encrypted in your local.envor secure vault
- Sessions isolated per user
- No data sent to third parties
- MIT Licensed — audit the code yourself
- 📖Full Strider Labs Docs
- 🐛Report Issues
- 💬Discussions
- 🌐Website
- 📧Email
We welcome contributions! Areas of interest:
- Bug reports and fixes
- Feature requests (new stores, categories, etc.)
- Performance improvements
- Documentation enhancements
MIT — Free to use, modify, and distribute. SeeLICENSEfor details.
Built by Strider Labs— Making AI agents actually useful.
Unofficial Model Context Protocol server for iFood — browse, search, cart and order food via AI
Pepesto gives your agent the ability to turn any recipe (a URL, plain text, or a photo) into a matched basket of real supermarket products with live prices, across 26 European supermarkets. The MCP covers the recipe → matched cart half of the grocery shopping workflow (parse / search / map ingredients to SKUs / check catalogs)
D2C eCommerce fulfillment platform: manage orders, inventory, shipments, campaigns, and billing via AI agents
MCP server for meal delivery service. Browse menus, manage carts, confirm orders, skip/unskip deliveries, and view order history.
A Dsers MCP with 14 (and expanding) toolset to allow your agent to access and edit your dsers.
Automate AliExpress/Alibaba dropshipping product import to Shopify or Wix via DSers. Bulk import, pricing rules, multi-store push.
Manage your GoodBarber eCommerce, Community, and Membership app via natural language.
Nas.com MCP Server lets AI agents connect to Nas.com so creators can create, launch, and sell with less manual work.
Remote MCP server for Packrift's AI-ready packaging catalog and ecommerce packaging workflows.
An MCP server for interacting with the Rami Levy online grocery store API.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
