Give Your AI Agent WhatsApp Superpowers with MCP (Official Business API)

Tokolaku, a WhatsApp business platform for Indonesian SMBs built on Meta's official WhatsApp Business Cloud API, has launched a hosted remote Model Context Protocol (MCP) server at api.tokolaku.id/mcp that lets any MCP-capable client connect to a live WhatsApp Business account without SDKs or self-hosted servers. The server exposes tools including list_channels, list_conversations, get_conversation, list_products, list_orders, get_order, and send_message, using OAuth with PKCE, dynamic client registration, and short-lived per-user tokens for read access, plus secret API keys for write access. Write tools route through the same billing, quota, and rate-limit path as the platform's REST API, and the endpoint also serves classic REST and official npm, PyPI, and Packagist SDKs.

What if your AI assistant could check your store's WhatsApp inbox, look up an order, and send the customer a reply — by itself? That's what the Model Context Protocol https://modelcontextprotocol.io MCP makes possible. MCP is now supported across the LLM ecosystem — claude.ai, ChatGPT, Gemini, Cursor, Windsurf, VS Code Copilot, and most agent frameworks speak it — and in this post I'll show you how to wire any MCP-capable client to a live WhatsApp Business platform in under two minutes. No SDKs, no servers to host — it's a remote MCP server. Tokolaku https://tokolaku.id/developers is a WhatsApp business platform for Indonesian SMBs built on Meta's official WhatsApp Business API Cloud API — so no gray-market gateways, no ban roulette . It exposes a hosted MCP server: https://api.tokolaku.id/mcp Any modern MCP client with OAuth discovery claude.ai, ChatGPT, Gemini, LibreChat, and most hosted assistants needs nothing but the URL: https://api.tokolaku.id/mcp list channels , list conversations , get conversation , list products , list orders , get order . Behind the scenes this uses PKCE, dynamic client registration RFC 7591 , and standard discovery metadata RFC 8414/9728 — tokens are minted per user, short-lived, and revocable from the dashboard. Try prompts like: "Any unpaid orders from this week? Summarize who I should follow up with." "Which products got asked about most in yesterday's chats?" For write access actually sending messages , use a secret API key from the developer dashboard. Most coding agents and frameworks Claude Code, Cursor, Windsurf, Cline, VS Code, OpenAI Agents SDK, LangChain, and friends share the same mcpServers config convention: { "mcpServers": { "tokolaku": { "type": "http", "url": "https://api.tokolaku.id/mcp", "headers": { "x-api-key": "tk live sk xxx" } } } } Building your own agent instead? Point any MCP client SDK at the Streamable HTTP URL and pass the key as an x-api-key or Authorization: Bearer header — that's the whole integration. Tools follow your key's scopes tools/list reflects them , and write tools like send message go through the exact same billing, quota, and rate-limit path as the REST API — your agent can't do anything your key can't. A fun one to try in your coding agent of choice: "A customer at +62812xxxx asked about their order this morning. Check the conversation, find the order status, and send them a polite update." Most "AI + WhatsApp" setups either screen-scrape the desktop app fragile, ToS-risky or make you build a bot pipeline first. A remote MCP server flips it: the platform speaks MCP natively, and any agent — today's or next year's — gets structured, permissioned access to real business state: conversations, catalog, orders. The same endpoint also serves classic REST POST /api/v1/messages , webhooks with HMAC signatures and official SDKs on npm https://www.npmjs.com/package/tokolaku-sdk , PyPI https://pypi.org/project/tokolaku/ , and Packagist https://packagist.org/packages/tokolaku/sdk — so the MCP layer is a first-class citizen, not a demo. Questions or weird edge cases? I'd love to hear what your agents do with a WhatsApp inbox. 👇