About Tokolaku
Tokolaku is a remote MCP server for connecting Tokolaku WhatsApp Business accounts to MCP clients, aimed at Indonesian SMBs and their AI agents. It supports conversation, product, and order lookups, plus permission-gated messaging and webhook management.
Key features
- 01Send WhatsApp messages and generate bot replies
- 02Browse channels and inbox conversations
- 03Look up products and order status
- 04Manage inbound-event webhooks
- 05Check subscription plans and quotas
Use cases
- 01Review WhatsApp conversations from an MCP client
- 02Check product details or order payment status
- 03Send session messages through the official channel
- 04Configure and test inbound-event webhooks
MCP support
The server provides a remote Streamable HTTP MCP endpoint, with OAuth 2.1 or API-key access. OAuth tools are read-only; API keys can enable write tools according to their scopes.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.tokolaku.id/mcpclaude mcp add --transport http id-tokolaku https://api.tokolaku.id/mcp{"mcpServers":{"id-tokolaku":{"type":"http","url":"https://api.tokolaku.id/mcp"}}}Open in Cursor{"servers":{"id-tokolaku":{"type":"http","url":"https://api.tokolaku.id/mcp"}}}Open in VS Code{"mcpServers":{"id-tokolaku":{"type":"http","url":"https://api.tokolaku.id/mcp"}}}{"mcpServers":{"id-tokolaku":{"serverUrl":"https://api.tokolaku.id/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMETokolaku MCP Server
Remote MCP (Model Context Protocol) server for Tokolaku — a WhatsApp business platform for Indonesian SMBs built on the official WhatsApp Business API (Meta Cloud API, zero message markup).
Connect Claude, ChatGPT, or any MCP client to your Tokolaku account and let your AI agent send WhatsApp messages, browse conversations, look up products & orders, and manage webhooks.
Endpoint : https://api.tokolaku.id/mcp
Transport: Streamable HTTP (stateless)
Quick start
claude.ai / ChatGPT & other OAuth-capable clients
Just add the URL — no keys needed:
- Add a custom connector / MCP server with URL
https://api.tokolaku.id/mcp - Sign in with your Tokolaku account and approve access
- Done — 6 read-only tools are available (channels, inbox, products, orders)
Claude Code / Claude Desktop / SDKs (API key)
Use a secret API key from your Tokolaku developer dashboard:
{
"mcpServers": {
"tokolaku": {
"type": "http",
"url": "https://api.tokolaku.id/mcp",
"headers": { "x-api-key": "tk_live_sk_xxx" }
}
}
}
Tools
With an API key (scope-gated — tools/list follows your key's scopes):
| Tool | Description |
|---|---|
send_message | Send a session text message via the official channel |
generate_bot_reply | Generate an AI reply using the tenant's bot engine |
list_channels | List connected official channels |
list_conversations / get_conversation | Browse the inbox |
list_products | Browse the product catalog |
list_orders / get_order | Browse orders (incl. payment status) |
get_subscription | Plan & quota info |
list_webhooks / create_webhook / test_webhook | Manage inbound-event webhooks |
Via OAuth (read-only bundle): list_channels, list_conversations, get_conversation, list_products, list_orders, get_order.
Auth
- OAuth 2.1 (PKCE, dynamic client registration, RFC 8414/9728 discovery) — for interactive clients; tokens are per-user and read-only.
- API key (
x-api-keyorAuthorization: Bearer) — secret keys only; write tools respect billing/quota exactly like the REST API.
Links
- Docs & API reference: https://tokolaku.id/api-docs
- Developer overview: https://tokolaku.id/developers
- WhatsApp Business API plan (Rp99k/mo, no message markup): https://tokolaku.id/whatsapp-api
- SDKs: npm
tokolaku-sdk· PyPItokolaku· Packagisttokolaku/sdk
This repository hosts the public metadata (server.json) and documentation for the hosted server; the server itself is a managed service operated by Tokolaku.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.