Linkbreakers MCP

Create Webhook

webhooks_create

Create a webhook that POSTs a signed JSON delivery to an endpoint each time a visitor completes a workflow step (visit.entered, visit.interacted, visit.routed or visit.exited), optionally only for some step kinds or one link.

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": {
      "name": "<name>",
      "endpointUrl": "<endpointUrl>"
    },
    "name": "webhooks_create"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The name of the webhook
`linkId`	No	Filter webhook notifications by a specific link ID. Only events from this link will trigger webhook notifications. If empty, all links in the workspace will trigger notifications.
`source`	No	Source of the webhook - indicates creation method (optional, defaults to LINKBREAKERS for manual dashboard creation)
`delivery`	No	Where, when and what it sends. When set, it takes over from triggers and link_id. Leave it out to use those, or send at every moment on every link.
`triggers`	No	Filter webhook notifications by workflow step kinds. Only workflow steps matching these kinds will trigger webhook notifications: KIND_ENTRY sends visit.entered, KIND_INTERACTION visit.interacted, KIND_CONDITION visit.routed and KIND_EXIT visit.exited. If empty, all workflow step kinds will trigger notifications.
`endpointUrl`	Yes	The URL endpoint that will receive webhook POST requests

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

changedInput schema / properties / source / enum

Previous value: -[
-  "WEBHOOK_SOURCE_LINKBREAKERS",
-  "WEBHOOK_SOURCE_MAKE",
-  "WEBHOOK_SOURCE_ZAPIER"
-]New value: +[
+  "WEBHOOK_SOURCE_LINKBREAKERS",
+  "WEBHOOK_SOURCE_MAKE",
+  "WEBHOOK_SOURCE_ZAPIER",
+  "WEBHOOK_SOURCE_N8N",
+  "WEBHOOK_SOURCE_INTEGRATELY"
+]

Changed1 schema field changedNov 7, 2026

addedInput schema / properties / delivery

Added value: +{
+  "additionalProperties": false,
+  "description": "Where, when and what it sends. When set, it takes over from triggers and link_id. Leave it out to use those, or send at every moment on every link.",
+  "properties": {
+    "directoryIds": {
+      "description": "Where: directories it applies to, with every directory below them.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "linkIds": {
+      "description": "Where: links it applies to. All three lists empty means every link.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "moments": {
+      "description": "When: the moments of a visit it sends at. Ignored when step_ids is set.",
+      "items": {
+        "enum": [
+          "KIND_ENTRY",
+          "KIND_EXIT",
+          "KIND_INTERACTION",
+          "KIND_CONDITION"
+        ],
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "stepIds": {
+      "description": "When: send only when a visit reaches one of these workflow steps.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "tagIds": {
+      "description": "Where: tags it applies to.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "visitorAttributeKeys": {
+      "description": "What: with SELECTED, the attribute keys sent, such as \"$email\" or \"rating\".",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "visitorData": {
+      "description": "What: how much of what is known about the visitor it sends.",
+      "enum": [
+        "INTEGRATION_VISITOR_DATA_NONE",
+        "INTEGRATION_VISITOR_DATA_ALL",
+        "INTEGRATION_VISITOR_DATA_SELECTED"
+      ],
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedNov 3, 2026

changedInput schema / properties / triggers / description

Previous value: -"Filter webhook notifications by workflow step kinds. Only workflow steps matching these kinds will trigger webhook notifications. If empty, all workflow step kinds will trigger notifications."New value: +"Filter webhook notifications by workflow step kinds. Only workflow steps matching these kinds will trigger webhook notifications: KIND_ENTRY sends visit.entered, KIND_INTERACTION visit.interacted, KIND_CONDITION visit.routed and KIND_EXIT visit.exited. If empty, all workflow step kinds will trigger notifications."

AddedOct 30, 2026

TDQS

A3.7/5.0

Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose a meaningful behavioral trait (deliveries are signed JSON POSTs, fired per workflow step completion, with the event-to-kind mapping). It omits operational context an agent would want: required permissions, whether a signing secret is returned on creation, whether the endpoint is verified, and retry/failure behavior.

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?

A single front-loaded sentence with the core behavior first and qualifying details after; no filler and no repetition of the tool name or title.

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 tool with a nested object and an overlap rule, the description is only partially complete: it never mentions that supplying 'delivery' overrides 'triggers' and 'linkId', which is the main way an agent could misconfigure this call. The rich schema compensates for most parameter detail, and absent an output schema the return value need not be explained, but the precedence gap is material.

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 100%, so the schema already documents all six parameters in depth, and the baseline is 3. The description adds the event-name mapping implicitly via the four visit.* events but says nothing about the nested 'delivery' object, which is the most complex and least obvious parameter.

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 ('Create a webhook') and goes further to define the mechanism: a signed JSON POST to an endpoint on workflow step completion, enumerating the four triggering events. An agent can distinguish this from webhooks_update/webhooks_get without opening the schema.

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 implies the creation context and mentions the optional narrowing scope ('only for some step kinds or one link'), but it never states when to choose this over webhooks_update or how it relates to webhooks_list/get. No prerequisites, no exclusions, no explicit alternative routing.

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

All Linkbreakers MCP 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.