Kommo Kiro MCP

by sam-wilkie

Overview Schema Source Related Servers Discussions Admin

Python

Local

list_custom_fields

Read-onlyIdempotent

List custom field definitions for leads, contacts, or companies to get field IDs for updating records.

Instructions

List custom field definitions for leads, contacts, or companies. Read-only. Returns field objects with id, name, code, type, and enum options. Cached for 1 hour. Use the field IDs in custom_fields_values when calling update_lead or update_contact.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`entity_type`	No	Entity whose fields to list: leads, contacts, or companies. Default "leads".	leads

Output Schema

TableJSON Schema

Name	Required	Description	Default
`items`	Yes	Returned entities.

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": "Custom fields, as {items: [field, ...]}.",
+  "properties": {
+    "items": {
+      "description": "Returned entities.",
+      "items": {
+        "additionalProperties": true,
+        "description": "A custom field definition.",
+        "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"
+            ]
+          },
+          "code": {
+            "description": "System field code, or null.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "entity_type": {
+            "description": "Entity the field belongs to.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "enums": {
+            "description": "Options for select-like fields.",
+            "items": {
+              "additionalProperties": true,
+              "description": "One option.",
+              "properties": {},
+              "type": "object"
+            },
+            "type": [
+              "array",
+              "null"
+            ]
+          },
+          "id": {
+            "description": "Field ID.",
+            "type": "integer"
+          },
+          "is_api_only": {
+            "description": "Whether the field is API only.",
+            "type": [
+              "boolean",
+              "null"
+            ]
+          },
+          "name": {
+            "description": "Field name.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "sort": {
+            "description": "Sort order.",
+            "type": [
+              "integer",
+              "null"
+            ]
+          },
+          "type": {
+            "description": "Field type, e.g. text, select.",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "items"
+  ],
+  "type": "object"
+}

Changed1 schema field changedOct 3, 2026

changedInput schema / properties / entity_type / description

Previous value: -"Entity type: leads, contacts, companies"New value: +"Entity whose fields to list: leads, contacts, or companies. Default \"leads\"."

First observedv1.0.0Oct 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior the annotations cannot convey: results are cached for 1 hour, which affects freshness expectations.

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: what it lists, safety, return shape, caching constraint, and the cross-tool usage tip. Front-loaded with the core purpose.

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 the description need not detail return values, and the annotations cover the safety profile. Combined with the caching note and the ID-reuse guidance, an agent has everything needed to call and consume this tool 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 the entity_type parameter and its enum-ish values are already documented in the schema. The description's mention of leads/contacts/companies is essentially a restatement, 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 specific verb (List) and resource (custom field definitions) scoped to three entity types, and clearly distinguishes itself from get/list siblings that operate on records rather than field metadata.

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

Usage Guidelines4/5

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

Explicitly tells the agent how to use the result: feed the field IDs into custom_fields_values when calling update_lead or update_contact. This is strong downstream routing, though it stops short of stating when NOT to use this tool (e.g., use create_custom_field to add one).

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