Skip to main content
Glama
thenavidm

Kit MCP Server

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Create a webhook endpoint

create_webhook_endpoint
Destructive

Set up a webhook endpoint to receive Kit event notifications. Requires confirm=true and a secret_name; new signing secrets saved locally.

Instructions

Create a webhook endpoint. May affect delivery, audience membership, published data or irreversible state. Requires confirm=true. Webhook response secrets are redacted; new signing secrets are saved only to a private local file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNo
nameNo
eventsNo
accountNoNamed private account from KIT_ACCOUNTS. Defaults to KIT_DEFAULT_ACCOUNT or the first configured account.
confirmNoSet true only when the user asked for exactly this action.
payloadNoComplete JSON body instead of individual body flags. Supports nullable fields and nested bulk structures. Cannot be combined with body flags or payload_file.
descriptionNo
secret_nameYesNew private filename under KIT_PRIVATE_DIR. Required before creating/rotating a signing secret; never overwritten.
payload_fileNoLocal JSON request body file, at most 5 MB. Contents are validated before the API call and are never logged.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv3.0.0
    • addedInput schema / $defs
      Added value: +{
+  "events": {
+    "description": "Event types this endpoint subscribes to (e.g. `subscriber.created`). On update, the list supplied here replaces the endpoint's full subscription list.",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+}
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true for audience/delivery changes, publishing, destructive operations and signing-secret changes. Use only for an action requested by the user."New value: +"Set true only when the user asked for exactly this action."
    • addedInput schema / properties / events / $ref
      Added value: +"#/$defs/events"
    • removedInput schema / properties / events / description
      Removed value: -"Event types this endpoint subscribes to (e.g. `subscriber.created`). On update, the list supplied here replaces the endpoint's full subscription list."
    • removedInput schema / properties / events / items
      Removed value: -{
-  "type": "string"
-}
    • removedInput schema / properties / events / type
      Removed value: -"array"
    • addedInput schema / properties / payload / properties / events / $ref
      Added value: +"#/$defs/events"
    • removedInput schema / properties / payload / properties / events / description
      Removed value: -"Event types this endpoint subscribes to (e.g. `subscriber.created`). On update, the list supplied here replaces the endpoint's full subscription list."
    • removedInput schema / properties / payload / properties / events / items
      Removed value: -{
-  "type": "string"
-}
    • removedInput schema / properties / payload / properties / events / type
      Removed value: -"array"
  2. First observedv2.0.1

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety bar is lower. The description nonetheless adds genuinely non-obvious behavior: that secrets in webhook responses are redacted and that newly minted signing secrets are written only to a private local file, plus the irreversibility warning. This goes meaningfully beyond the structured fields.

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?

Four short sentences with the action stated first and the risk/secret caveats after; no filler. Slightly terse on parameters given the tool's complexity, but structurally front-loaded and efficient.

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

Completeness3/5

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

For a destructive, non-idempotent mutation with 9 parameters, a nested payload object, and no output schema, the description covers safety and secret-handling well but leaves the request-body construction (payload vs. payload_file exclusivity, events semantics) and the expected result largely unexplained.

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 coverage is 56% across 9 parameters, so roughly half the params are undocumented anywhere. The description adds useful framing for secret_name (where the signing secret lands) and reiterates confirm, but says nothing about url, events, payload vs. payload_file mutually exclusive flags, or name/description, leaving the payload-body parameters thin.

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

Purpose4/5

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

States a specific verb and resource ('Create a webhook endpoint'), which is unambiguous against the many list/get/update webhook siblings. It does not, however, explicitly distinguish itself from update_webhook_endpoint, create_webhook, or rotate_webhook_secret, which sit in the same family.

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

Usage Guidelines3/5

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

The description does state the confirm=true precondition, which is real usage guidance, but it gives no when-not guidance and never names or contrasts the alternative webhook tools (update_webhook_endpoint, create_webhook). The condition for choosing this tool over its siblings 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.

Deploy Server

Other Tools