blinkit-mcp

blinkit-mcp

Enables Claude to automate grocery shopping on Blinkit, including product search, cart management, location setup, and payment via UPI.

Category
Visit Server

README

<p align="center"> <img src="assets/logo.png" alt="Blinkit MCP Logo" width="120" height="120" style="border-radius:30px;"> </p>

<h1 align="center">Unofficial Blinkit MCP</h1>

<p align="center"> A Model Context Protocol (MCP) server that lets Claude Desktop browse, search, and order from Blinkit in real time. </p>

<p align="center"> <a href="LICENSE"> <img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="MIT License"> </a> <img src="https://img.shields.io/badge/python-3.12+-green.svg" alt="Python 3.12+"> <img src="https://img.shields.io/badge/MCP-Claude%20Desktop-purple.svg" alt="Claude MCP"> </p>


✨ What is Blinkit MCP?

Blinkit MCP is a plug-and-play MCP server that allows Claude Desktop to automate your grocery shopping on Blinkit.

Your AI can:

  • šŸ” Search for products (groceries, electronics, etc.)
  • šŸ›’ Add items to your cart
  • šŸ“ Manage delivery locations
  • šŸ’³ Automate checkout and UPI payments
  • šŸ” Login securely with phone and OTP

No manual clicking required. Just ask Claude to buy milk.


šŸŽ¬ Quick Demo

https://github.com/user-attachments/assets/531f09ad-648a-4ee2-9271-5993ce637093

šŸ’” Ask Claude: "Buy milk from Blinkit"


šŸš€ Quick Start (30 seconds)

  1. Install uv (if you don't have it):

    macOS / Linux

    curl -LsSf https://astral.sh/uv/install.sh | sh
    

    Windows

    powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
    
  2. (Optional) Pre-install Browsers
    If you want to speed up the first run:

    uvx playwright install chromium
    # OR if you have Node.js:
    # npx playwright install chromium
    
  3. Download the MCP bundle
    šŸ‘‰ blinkit-mcp.mcpb

  4. Double-click the .mcpb file — Claude Desktop installs it automatically.

  5. Open Claude Desktop and start shopping.


šŸ”„ Key Features

Feature Description
šŸ”’ Secure Auth Login via Phone Number & OTP (Session persisted locally)
šŸ”Ž Smart Search Find products by name and get pricing/details
šŸ›’ Cart Management Add items, check cart status, and verify availability
šŸ“ Location Detect or manually set delivery location
šŸ’³ Payment Automation New! Select saved UPI IDs or enter new ones automatically
šŸš€ Checkout Flow Handles address selection and ordering flow seamlessly

šŸ“¦ One-Click Installation (Recommended)

Download and install directly in Claude Desktop:

<p align="center"> <a href="https://github.com/hereisSwapnil/blinkit-mcp/releases/download/v1.0.2/blinkit-mcp.mcpb"> <img src="https://img.shields.io/badge/Download-blinkit--mcp.mcpb-orange?style=for-the-badge" alt="Download"> </a> </p>

Supports: macOS • Windows • Linux


šŸ› ļø Manual Installation

If you prefer to run from source:

  1. Clone and Run:

    git clone https://github.com/hereisSwapnil/blinkit-mcp.git
    cd blinkit-mcp
    
    # Install uv (if needed)
    curl -LsSf https://astral.sh/uv/install.sh | sh
    
    # Install Python dependencies
    uv sync
    
    # Install Playwright browsers
    uv run playwright install chromium
    
    # Run the server
    uv run main.py
    
  2. Configure Claude Desktop:

    Add this to your claude_desktop_config.json:

    {
      "mcpServers": {
        "blinkit-mcp": {
          "command": "/usr/local/bin/uv",
          "args": ["run", "main.py"],
          "cwd": "/absolute/path/to/blinkit-mcp",
          "env": {
              "HEADLESS": "false" 
          }
        }
      }
    }
    

    (Set HEADLESS to false to see the browser action, or true for background mode)

🧰 Available MCP Tools

Tool Description
check_login Check if currently logged in
login Login with phone number
enter_otp Verify login with OTP
set_location Manually search and set delivery location
search Search for products
add_to_cart Add product to cart by index
remove_from_cart Remove item from cart
check_cart View cart contents
checkout Proceed to checkout
get_addresses Get list of saved addresses
select_address Select a delivery address
proceed_to_pay Proceed to payment page
get_upi_ids List available UPI payment options
select_upi_id Select a specific UPI ID for payment
pay_now Click the final Pay Now button

šŸ’¬ Example Queries

  • "Buy milk from Blinkit to my home and use my UPI for payment"
  • "Order 2 packets of Maggi and pay via UPI"
  • "Get me some chips, deliver to office, and checkout"

šŸ“ Project Structure

blinkit-mcp/
ā”œā”€ā”€ main.py                # MCP server entry point
ā”œā”€ā”€ src/
│   ā”œā”€ā”€ auth/              # Authentication module
│   │   └── service.py     # Auth service implementation
│   ā”œā”€ā”€ order/             # Order management module
│   │   ā”œā”€ā”€ blinkit_order.py   # Main order controller
│   │   └── services/          # Domain services
│   │       ā”œā”€ā”€ base.py        # Base service class
│   │       ā”œā”€ā”€ search.py      # Search logic
│   │       ā”œā”€ā”€ location.py    # Location logic
│   │       ā”œā”€ā”€ cart.py        # Cart logic
│   │       └── checkout.py    # Checkout & Payment logic
│   └── server.py          # MCP Tool definitions
ā”œā”€ā”€ test/
│   └── cli.py             # CLI for testing independent of Claude
└── README.md

šŸ“„ License

Licensed under the MIT License.


<b>Blinkit MCP turns Claude into your personal grocery assistant.</b> </p>


āš ļø Disclaimer

This project is an experimental proof of concept and is not affiliated, associated, authorized, endorsed by, or in any way officially connected with Blinkit (Grofers India Private Limited), or any of its subsidiaries or its affiliates. The official Blinkit website can be found at blinkit.com.

Star History

Star History Chart


Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured