kirimi-mcp

send_otp

Send a one-time password to any phone number via WhatsApp. Pick an official provider, your own connected device, or a Business API template to control cost and setup.

Instructions

Send a one-time password. Pick the method deliberately: "whatsapp" uses the official Kirimi provider and costs Rp 595 per delivered OTP with no setup; "device" sends through your own connected device and is free; "waba_user" sends through your own WhatsApp Business API template and is free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "phone": "<phone>"
    },
    "name": "send_otp"
  }
}

Input Schema

Name	Required	Description
`phone`	Yes	Phone number in international format without + (e.g. 6281234567890) — the OTP recipient
`method`	No	Delivery channel. Default "whatsapp". Requires device_id when "device", and waba_id + template_name when "waba_user".
`waba_id`	No	Required when method is "waba_user"
`app_name`	No	Brand name shown in the message. Default "Kirimi.id".
`device_id`	No	Required when method is "device"
`template_name`	No	Required when method is "waba_user". Must be an APPROVED AUTHENTICATION category template.
`custom_message`	No	Only for method "device". Must contain the {{otp}} placeholder and be 10-500 characters.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.1.0Sep 20, 2026

TDQS

A4.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden. It reveals cost per delivery, setup requirements, defaults for app_name, template approval constraints, and custom_message length/placeholder rules. It does not mention rate limits or error handling, but for a simple OTP send operation this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is packed with information but every clause earns its place. The primary action is front-loaded, and the method breakdown follows logically. No fluff or redundant restatement of the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters and no output schema, this description covers method selection, costs, prerequisites, defaults, and constraints. An agent can confidently call it without additional lookup. The only omission is return-value behavior, but that is not required in the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, yet the description adds substantial value beyond the schema: it assigns cost to each method, clarifies that waba_user requires an APPROVED template, specifies the custom_message placeholder requirement, and states default values. This is exactly the kind of enrichment that helps an agent pick correct parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Send a one-time password') and immediately enumerates three delivery methods with distinct costs and prerequisites. This clearly distinguishes it from sibling tools like send_message and send_waba_template, which are general messaging tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs the agent to 'Pick the method deliberately' and explains the trade-offs: WhatsApp via Kirimi costs Rp 595, device is free, and waba_user uses an approved template. It also lists required companion parameters for each method, leaving no ambiguity about when to choose which.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.