MyOTP.App

Send OTP

generate_otp

Send a one-time password (OTP) to a phone number via SMS, WhatsApp, or Telegram. MyOTP.App generates the code, formats the message, picks the best carrier route, and delivers it. Returns a message_id (UUID) — keep it; you'll pass it to verify_otp, check_otp_status, or extend_otp later. Each call deducts credits from the account balance; the per-message cost varies by destination country and channel and is returned in the cost field. Use this whenever an app needs to verify someone's phone — signup, login 2FA, password reset, transaction confirmation, etc.

Input Schema

TableJSON Schema

Name	Required	Description
`brand`	No	Sender brand name shown to the recipient (3-16 alphanumeric characters plus dots). Defaults to the brand registered against the API key, or 'MyOTP.App' if none.
`channel`	No	Delivery channel. 'sms' (default) works in 190+ countries. 'whatsapp' is best for India/Brazil/Indonesia/Mexico/Nigeria/Turkey. 'telegram' is best for privacy-focused users. Same API for all three.
`otp_code`	No	Provide your own pre-generated numeric OTP code (3-8 digits, 4-8 for telegram) instead of letting MyOTP generate one. Useful when you already have a code from another system.
`force_send`	No	If true, send a new OTP even if one is already active for this phone number. By default the API returns 409 in that case. Use sparingly — repeated sends to the same number can hit carrier-level spam filters.
`otp_length`	No	Number of digits in the auto-generated OTP. Range 3-8 (4-8 for telegram). Default 6. Requires CUSTOM_OTP_LENGTH entitlement (Business plan or above).
`return_otp`	No	If true, the API response will include the generated OTP code in plain text. Useful for testing or when you want to deliver the OTP via your own channel. Defaults to false. SECURITY: never enable this in production user flows.
`otp_validity`	No	How long the OTP stays valid, in seconds. Range 30-14400 (30-3600 for telegram). Default 300 (5 minutes). Requires CUSTOM_OTP_EXPIRY entitlement (Business plan or above).
`phone_number`	Yes	Destination phone number in international format with NO leading + or 0. Must be 7-15 digits and start with a non-zero digit. Example: '14155550123' for a US number, '447911123456' for a UK number.
`template_order`	No	Pick a specific message template by its order number (1-99). WhatsApp has four: 12 (English, 5-minute code), 13 (English, 10 minutes), 14 (Spanish es_MX, 5 minutes), 15 (Spanish es_MX, 10 minutes). On WhatsApp the template's own expiry overrides otp_validity. Requires the ACCESS_TO_TEMPLATES entitlement (Business plan and up). Not supported on telegram (Telegram generates its own message text).

Output Schema

TableJSON Schema

Name	Required	Description
`otp`	No	The OTP value, present only when return_otp was true.
`cost`	Yes	Credits charged for this send.
`status`	Yes	Always 'accepted' on success; delivery state comes from check_otp_status.
`message`	Yes	Message describing the status of the request.
`date_sent`	Yes	ISO 8601 date-time the OTP was sent.
`expires_at`	Yes	ISO 8601 date-time the OTP expires.
`message_id`	Yes	ID of the message sent. Pass it to verify_otp, check_otp_status and extend_otp.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

changedInput schema / properties / phone_number / description

Previous value: -"Destination phone number in international format with NO leading + or 0. Must be 7-15 digits and start with a non-zero digit. Example: '14155551234' for a US number, '447911123456' for a UK number."New value: +"Destination phone number in international format with NO leading + or 0. Must be 7-15 digits and start with a non-zero digit. Example: '14155550123' for a US number, '447911123456' for a UK number."

Changed1 schema field changedSep 21, 2026

changedInput schema / properties / template_order / description

Previous value: -"Pick a specific message template by its order number (1-99). Requires ACCESS_TO_TEMPLATES entitlement. Not supported on telegram (Telegram generates its own message text)."New value: +"Pick a specific message template by its order number (1-99). WhatsApp has four: 12 (English, 5-minute code), 13 (English, 10 minutes), 14 (Spanish es_MX, 5 minutes), 15 (Spanish es_MX, 10 minutes). On WhatsApp the template's own expiry overrides otp_validity. Requires the ACCESS_TO_TEMPLATES entitlement (Business plan and up). Not supported on telegram (Telegram generates its own message text)."

First observedSep 6, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations declare non-read-only, non-idempotent, open-world behavior, and the description goes well beyond that: it discloses credit deduction per call, country/channel-dependent cost returned in a `cost` field, the default 409 on duplicate active OTP and force_send override, and carrier spam-filter risk. This is exactly the extra behavioral context annotations cannot carry.

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

Conciseness4/5

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

Front-loaded with the core action and channel list, then the reusable message_id and cost/credit implications. Dense but almost every sentence carries actionable information; the final 'use this whenever' sentence is slightly redundant with earlier routing.

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

Completeness4/5

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

An output schema exists, so return-value explanation is not required, yet the description helpfully names message_id and cost as key outputs. For a 9-param mutation tool with rich annotations and full schema coverage, the definition is complete enough to call correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so every one of the 9 parameters is already documented in the schema (including entitlements, ranges, and channel-specific limits). The description adds little parameter-level syntax beyond what the schema states, so the baseline 3 applies.

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 concrete verb+resource (send an OTP to a phone number) plus the delivery channels, and the description explicitly names siblings verify_otp, check_otp_status, and extend_otp as the follow-on tools. An agent can distinguish this from those siblings without opening a schema.

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?

Gives explicit when-to-use guidance ('whenever an app needs to verify someone's phone — signup, login 2FA, password reset, transaction confirmation') and routes the agent to the correct downstream tools once message_id is obtained. Nothing is left to inference.

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

All MyOTP.App tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.