Kommo Kiro MCP

Overview Schema Source Related Servers Discussions Admin

create_task

Add a follow-up task to a Kommo lead by specifying text, due date, and optional responsible user. Each call adds a separate task.

Instructions

Create a follow-up task (type 1) attached to a lead. Not idempotent: each call creates a new task. Returns the created task. Use list_tasks to review existing tasks and add_note for non-actionable remarks.

Input Schema

TableJSON Schema

Name	Required	Description
`text`	Yes	Task description shown in Kommo.
`lead_id`	Yes	Kommo lead ID (integer). Obtain it from list_leads or from the create_lead result.
`due_date`	Yes	Deadline as a Unix timestamp in seconds, e.g. 1767225600.
`responsible_user_id`	No	Kommo user ID responsible for the task. Omit for the default.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No	Task ID.
`text`	No	Task description.
`_links`	No	HAL links as returned by Kommo (self, next, ...).
`result`	No	Completion result (object or array), may be empty.
`duration`	No	Duration in seconds.
`group_id`	No	ID of the responsible user's group.
`entity_id`	No	ID of the entity the task is attached to.
`account_id`	No	Kommo account ID.
`created_at`	No	Creation time, Unix seconds.
`created_by`	No	ID of the user who created it.
`updated_at`	No	Last update time, Unix seconds.
`updated_by`	No	ID of the user who last updated it.
`entity_type`	No	Entity type, e.g. leads.
`is_completed`	No	Whether the task is completed.
`task_type_id`	No	Task type ID (1 is follow-up).
`complete_till`	No	Deadline, Unix seconds.
`responsible_user_id`	No	ID of the responsible Kommo user.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.3Oct 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "The created task.",
+  "properties": {
+    "_links": {
+      "additionalProperties": true,
+      "description": "HAL links as returned by Kommo (self, next, ...).",
+      "properties": {},
+      "type": "object"
+    },
+    "account_id": {
+      "description": "Kommo account ID.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "complete_till": {
+      "description": "Deadline, Unix seconds.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "created_at": {
+      "description": "Creation time, Unix seconds.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "created_by": {
+      "description": "ID of the user who created it.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "duration": {
+      "description": "Duration in seconds.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "entity_id": {
+      "description": "ID of the entity the task is attached to.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "entity_type": {
+      "description": "Entity type, e.g. leads.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "group_id": {
+      "description": "ID of the responsible user's group.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "id": {
+      "description": "Task ID.",
+      "type": "integer"
+    },
+    "is_completed": {
+      "description": "Whether the task is completed.",
+      "type": [
+        "boolean",
+        "null"
+      ]
+    },
+    "responsible_user_id": {
+      "description": "ID of the responsible Kommo user.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "result": {
+      "description": "Completion result (object or array), may be empty."
+    },
+    "task_type_id": {
+      "description": "Task type ID (1 is follow-up).",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "text": {
+      "description": "Task description.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "updated_at": {
+      "description": "Last update time, Unix seconds.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "updated_by": {
+      "description": "ID of the user who last updated it.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

Changed4 schema fields changedOct 3, 2026

changedInput schema / properties / due_date / description

Previous value: -"Due date as Unix timestamp"New value: +"Deadline as a Unix timestamp in seconds, e.g. 1767225600."

addedInput schema / properties / lead_id / description

Added value: +"Kommo lead ID (integer). Obtain it from list_leads or from the create_lead result."

addedInput schema / properties / responsible_user_id / description

Added value: +"Kommo user ID responsible for the task. Omit for the default."

changedInput schema / properties / text / description

Previous value: -"Task description"New value: +"Task description shown in Kommo."

First observedv1.0.0Oct 3, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds the concrete consequence of non-idempotency ('each call creates a new task'), which is useful elaboration rather than mere repetition, though it omits permission/auth needs and 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?

Four short sentences, each earning its place, with the core action and non-idempotency caveat front-loaded before the alternative-tool routing. No filler.

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 not be described. Purpose, side-effect behavior, and sibling routing are all present, leaving nothing an agent needs to call this 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 coverage is 100%, so all four parameters are already documented in the schema, making 3 the baseline. The description adds only the 'type 1' constant, which is not mapped to any schema field and is left unexplained, so it adds marginal value.

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 (create) and resource (task), plus scope constraints: it is a follow-up task of type 1 attached to a lead. This distinguishes it from siblings like list_tasks and add_note without opening either 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?

Explicitly routes the agent: use list_tasks to review existing tasks and add_note for non-actionable remarks. This gives both the alternative tools and the conditions that select them, so when-not-to-use is covered.

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