Skip to main content
Glama

Register Webhook

register_webhook
Destructive

Register a webhook so Mobile Text Alerts sends events to a URL you control — for example, to receive replies to messages sent with send_message.

EVENTS

  • message-reply: an inbound reply was received

  • delivery-status: a sent message's delivery status changed

  • message-send: a message was handed off for delivery

  • number-opt-in: a number opted in to a channel

THE SECRET Ask the human user to provide the secret — do not invent one. Tell them to store it outside this conversation (for example in Replit Secrets): the receiving app needs it to verify requests, and it cannot be retrieved from Mobile Text Alerts afterwards.

THE RECEIVING ENDPOINT MUST

  • Be reachable over HTTPS and respond with HTTP 200 (401 if the signature is invalid).

  • Verify the X-Signature header on every request: a lowercase hex HMAC-SHA256 of the RAW request body, keyed with the secret. Compute it over the raw bytes before any JSON parsing (e.g. express.raw() in Express) and compare in constant time. There is no timestamp or nonce, so signatures do not protect against replay.

Payload formats per event: https://developers.mobile-text-alerts.com/tutorials/webhooks

Always call list_webhooks first. Registering the same event and URL again creates a second webhook rather than updating the first, and both will receive every event. If one already exists, reuse it — or, to change the URL or secret, remove it with delete_webhook and register again.

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": {
      "event": "<event>",
      "url": "<url>",
      "secret": "<secret>"
    },
    "name": "register_webhook"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesHTTPS URL of the endpoint that will receive events. It must respond with HTTP 200.
eventYesEvent to subscribe to. Use 'message-reply' to receive replies.
secretYesShared secret used to sign every webhook request. Must be provided by the human user — do not generate one. The user should store it outside this conversation (e.g. Replit Secrets); it cannot be retrieved from Mobile Text Alerts later.
alertEmailNoAddress for failure alerts. Only used when sendAlertEmail is true; defaults to the account's main email.
retryOnErrorNoRetry failed deliveries with exponential backoff (up to 2 retries).
sendAlertEmailNoEmail an alert when deliveries to the URL fail.

Output Schema

NameRequiredDescriptionDefault
dataYesRaw Mobile Text Alerts API response envelope. The webhook is nested one level down, under `data.data` — e.g. `data.data.id`.
errorNo
statusYes
successYes
statusTextYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the single destructiveHint annotation: it discloses that repeat registration creates a second webhook rather than updating, that the secret cannot be retrieved afterwards, that the endpoint must return 200/401 and verify an HMAC-SHA256 X-Signature over raw bytes, and that signatures do not protect against replay. This is exactly the operational context an agent needs before invoking a mutation.

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 purpose, then organized under clear headers (EVENTS, THE SECRET, THE RECEIVING ENDPOINT MUST). Some content duplicates the input schema verbatim, particularly the secret guidance, and the signature-verification detail leans toward implementation tutorial rather than tool selection, but nothing is disorganized.

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?

An output schema exists, so return values need no explanation, and the description covers the remaining risks: duplicate registration, secret provenance and irrecoverability, endpoint requirements, and a link to payload format docs. An agent has everything needed to call this correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description adds genuine meaning by enumerating and defining each event value (e.g. message-send is a handoff, number-opt-in is a channel opt-in) and reinforcing the human-supplied, non-generatable nature of the secret. It says nothing about retryOnError, sendAlertEmail, or alertEmail, but those are fully documented in the schema, so the gap is minor.

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?

The first sentence gives a specific verb and resource ("Register a webhook") plus the effect (Mobile Text Alerts sends events to a URL you control) and a concrete example use case tied to send_message. It is clearly distinguishable from list_webhooks and delete_webhook, which are named later in the text.

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 "Always call list_webhooks first" and explains why (duplicate registration means both webhooks receive every event). It also names the alternative path for changing a URL or secret: remove with delete_webhook and register again. When-to-use, when-not-to, and alternatives are all present.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources