How to Connect Flipkart Seller to Gemini via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Flipkart Seller, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Flipkart Seller + Gemini

Flipkart Marketplace Seller API v3 for your own seller account: listings with price and stock updates, order shipments (search, details, labels and invoices, ready to dispatch, cancellation, handover and manifest) and returns.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

FLIPKART_APP_ID, FLIPKART_APP_SECRET

Step 1 — Get credentials

Setting up takes about 5 minutes. You need a Flipkart seller account.

1. Sign in to the Flipkart Seller Hub (https://seller.flipkart.com) and open Manage Profile > Developer Access.
2. Click Create New Access, give the application a name and a description and submit. Flipkart shows an Application ID and an Application Secret. A self access application is for your own seller account only; do not share it with a partner.
3. Paste them into FLIPKART_APP_ID and FLIPKART_APP_SECRET.
4. Install the connector and run flipkart_seller_search_listings to check it.

The connector signs in with OAuth2 client credentials: it requests a token with the scope Seller_Api, sending the application id and secret as HTTP Basic, and requests a new one before it expires or after a 401.

Listings: the AI pages through all listings (500 per page) with listing id, product id (FSN) and SKU, or reads them 20 at a time with title, status, vertical, prices and dimensions. For up to 10 SKUs it reads the details: MRP and selling price, tax, status, fulfilment profile, dispatch SLA, packages, stock per location and the orders still to fulfil.

Prices and stock: flipkart_seller_update_price and flipkart_seller_update_inventory change one SKU and need its product id and, for stock, the location id. They change what buyers see at once, so the AI confirms the SKU and the new values with you first. A 200 answer can still carry status: failure for the SKU, and the AI reads the reason.

Orders (shipments): a shipment is what is packed and handed over together. The AI searches shipments before dispatch (APPROVED, PACKING_IN_PROGRESS, PACKED, FORM_FAILED, READY_TO_DISPATCH), after dispatch (SHIPPED, DELIVERED, PICKUP_COMPLETE) or cancelled, 20 per page, and reads order items, prices, dates, the hold flag, addresses, courier and tracking id. Searches reach at most 5,000 shipments, and Flipkart Assured orders are not included.

Processing a new order: for an APPROVED shipment that is not on hold and past its dispatch-after date, the AI generates the label and invoice, downloads them as one PDF and marks the shipment ready to dispatch, which books the courier. Before the pickup it reads the handover counts per courier with the one time code, and downloads the manifest PDF for one courier. These actions answer per shipment with SUCCESS or FAILURE, even when the HTTP status is 200.

Returns: customer returns and courier returns (undelivered shipments) by created or modified date, 25 per page, with status, reason and tracking id, or by return or tracking ids.

Switched off at install: flipkart_seller_cancel_shipments. Cancellations hurt the seller rating and can get the account or a location suspended, so an administrator turns this tool on deliberately, and the AI uses it only when you ask.

Formats: dates are ISO 8601, in IST when no zone is given. Amounts are in INR. Order ids start with OD, listing ids with LST and location ids with LOC; fsn is Flipkart's product id and sku your own. Labels, invoices and the manifest come as PDF files.

Common errors: 401 means an expired or refused token (check the application id and secret), 400 or 422 an invalid request with a code such as INVALID_REQUEST_PAGE_SIZE or INVALID_DATE_FORMAT, 403 an id that belongs to another seller, and 5xx a problem on Flipkart's side such as DEPENDENT_SYSTEM_CALL_FAILED, worth retrying later.

The connector does not create or edit listing content and does not cover self ship dispatch and returns, Flipkart Quick listings, reports or order notifications.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (on Windows %USERPROFILE%\.gemini\settings.json). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart gemini.
3. Run /mcp inside Gemini CLI (or gemini mcp list in your shell): anythingmcp should show as connected.
4. Start prompting: Gemini CLI can now call the Flipkart Seller tools.

Available tools

Example prompts

• "Which shipments are approved and have to be dispatched today?"
• "Generate the labels for all approved shipments that are not on hold and give me the PDF."
• "What are the price and the stock of SKU TSHIRT-BLU-M at each location?"
• "Set the selling price of SKU TSHIRT-BLU-M to 499 INR. Show me the current price first."
• "List the customer returns created this week with their reasons."

FAQ

Where does Gemini CLI look for MCP servers? In ~/.gemini/settings.json for your user, or in .gemini/settings.json inside a project. gemini mcp list shows each server and whether it connects.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Meta Muse
• Connect to Microsoft Copilot