How to Connect Tamara to ChatGPT via MCP

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

Tamara + ChatGPT

Tamara buy now, pay later (Saudi Arabia, UAE, Kuwait, Bahrain, Oman): look up orders by your order number or Tamara id with status, captured, refunded and settled amounts, check payment types and customer eligibility. Capture and refund are included, installed switched off.

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:

TAMARA_API_URL, TAMARA_API_TOKEN

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a Tamara merchant account and its API token.

1. Sign in to the Tamara Partners Portal and open API Token Management, or use the API token Tamara sent with your merchant account. Sandbox and production have different tokens.
2. Paste the token into TAMARA_API_TOKEN, without "Bearer" or spaces. It is sent as Authorization: Bearer <token>. The notification token and the public key are not used here.
3. Set TAMARA_API_URL to https://api.tamara.co for production or https://api-sandbox.tamara.co for the sandbox. It must match the token.
4. Install the connector and run tamara_list_payment_types: it lists the payment types your store offers and confirms the token.

Your order number or Tamara's id: order_reference_id is your own order number sent at checkout, such as the shop order number; order_id is the UUID Tamara issued. Most questions start from your order number, with tamara_get_order_by_reference.

What it reads: an order by your order number or by Tamara order id, with status, payment type and instalments, consumer, addresses, items, total, captured, refunded, canceled and paid amounts, settlement status and date, and its transactions (captures, refunds and cancels); the payment types available in a country (such as PAY_BY_INSTALMENTS or PAY_NOW) with minimum and maximum order amount and the supported numbers of instalments, optionally only those eligible for an amount; before checkout, which payment options a specific customer can use for an amount, and whether Tamara currently treats a customer (by phone number, e-mail or both) as eligible; and a registered webhook with its URL, events and headers.

Order status: new, approved, authorised, then partially_captured or fully_captured, and partially_refunded or fully_refunded; canceled, declined and expired are final. paid_amount is what the customer has paid so far; settlement_status and settlement_date say whether Tamara has paid you out.

Switched off at install: tamara_capture_order (captures an authorised order in full or in part when it ships, so Tamara settles it) and tamara_refund_order (refunds a captured order in full or in part; the money goes back to the customer and cannot be taken back). Both move money, so an administrator turns them on deliberately. Even then the AI shows you the order, the amount and the currency and waits for your yes.

Amounts and times: amounts are objects with amount and currency; SAR and AED have 2 decimals, BHD, KWD and OMR 3. Times are UTC, ISO 8601.

Limits: Tamara has no endpoint to list or search orders, so the AI looks orders up by your order number or by Tamara's id.

Common errors: 401 means a wrong token or a token for the other environment (sandbox or production). 404 on an order means no order with that reference or id in this environment. 400 or 422 on a capture or refund names the field Tamara rejected, for example an amount above what can be captured. 403 means the token works but may not use this API; ask Tamara to enable it for your merchant account.

The connector does not create checkout sessions, authorise or cancel orders, use the claims API or fetch settlement reports.

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 ChatGPT

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.

ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.

1. Go to chatgpt.com/plugins, click Add, then Add custom MCP server.
2. Enter a name, e.g. Name: Tamara.
3. Under Connection, enter the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and keep Authentication on OAuth.
4. Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
5. Install the new plugin from your personal plugins, then type @ in a chat and pick it.

Available tools

Example prompts

• "What is the status of our order 100245 at Tamara, and has Tamara paid it out to us yet?"
• "How much of order 100245 has been captured, refunded and paid by the customer so far?"
• "Which Tamara payment types does our store offer in Saudi Arabia for an order of 1,200 SAR?"
• "Can the customer with the phone number +966501234567 pay 800 SAR with Tamara?"
• "Order 100245 has shipped: capture it in full. Show me the order and the amount first."

FAQ

Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.

Next steps

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