Skip to main content
Glama
ghl-mcp-server-v2

ghl-mcp-server-v2

by zackscriven

ghl_object_create_custom_object

Creates a GoHighLevel custom object schema, not a record, so you can define a new object type with labels, key, location, and primary display property.

Instructions

Creates a new custom object SCHEMA (not a record). Renamed from the auto-generated 'ghl_object_create_custom_schema' to match GHL's own terminology ('Create Custom Object') and avoid confusion with ghl_object_update_schema/ghl_object_get_schema_by_key which operate on already-created objects. Create Custom Object Allows you to create a custom object schema. To understand objects and records, please have a look at the documentation here : https://doc.clickup.com/8631005/d/h/87cpx-277156/93bf0c2e23177b0 Endpoint: POST /objects/ (Version header: v3; source: v3/objects-v3.json) Requires an Agency (company-level) token. OAuth scopes: objects/schema.write

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": {
      "body": "<body>"
    },
    "name": "ghl_object_create_custom_object"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body (schema carried verbatim from the official OpenAPI spec).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.1.0
    • changedInput schema / properties / body / properties / labels / allOf
      Previous value: -[
      -  {
      -    "properties": {
      -      "plural": {
      -        "description": "Plural name of the custom object",
      -        "example": "Pets",
      -        "type": "string"
      -      },
      -      "singular": {
      -        "description": "Singular name of the custom object",
      -        "example": "Pet",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "singular",
      -      "plural"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "plural": {
      +        "description": "Plural name of the custom object",
      +        "example": "Pets",
      +        "type": "string"
      +      },
      +      "singular": {
      +        "description": "Singular name of the custom object",
      +        "example": "Pet",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "singular",
      +      "plural"
      +    ],
      +    "title": "CustomObjectLabelDto",
      +    "type": "object"
      +  }
      +]
    • changedInput schema / properties / body / properties / primaryDisplayPropertyDetails / allOf
      Previous value: -[
      -  {
      -    "properties": {
      -      "dataType": {
      -        "description": "Primary property data Type (it can either be TEXT or NUMERICAL type)",
      -        "example": "TEXT",
      -        "type": "string"
      -      },
      -      "key": {
      -        "description": "key that would be used to refer the custom field internally (lowercase + underscore_separated). 'custom_objects.{{objectKey}}' would be added as prefix by default is not passed",
      -        "example": "custom_objects.pet.name",
      -        "type": "string"
      -      },
      -      "name": {
      -        "description": "Name of the Primary property name which will be displayed on the record page",
      -        "example": "Pet name",
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "key",
      -      "name",
      -      "dataType"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "properties": {
      +      "dataType": {
      +        "description": "Primary property data Type (it can either be TEXT or NUMERICAL type)",
      +        "example": "TEXT",
      +        "type": "string"
      +      },
      +      "key": {
      +        "description": "key that would be used to refer the custom field internally (lowercase + underscore_separated). 'custom_objects.{{objectKey}}' would be added as prefix by default is not passed",
      +        "example": "custom_objects.pet.name",
      +        "type": "string"
      +      },
      +      "name": {
      +        "description": "Name of the Primary property name which will be displayed on the record page",
      +        "example": "Pet name",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "key",
      +      "name",
      +      "dataType"
      +    ],
      +    "title": "CustomObjectDisplayPropertyDetails",
      +    "type": "object"
      +  }
      +]
    • addedInput schema / properties / body / title
      Added value: +"CreateCustomObjectSchemaDTO"
  2. First observedv2.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds genuinely new operational context: the v3 endpoint path, the Agency-token requirement, and the objects/schema.write scope. It stops short of describing what happens on a duplicate key or what the response contains, which is the remaining behavioral gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening paragraph is high-value and front-loaded, but the definition then repeats itself ('Create Custom Object' and 'Allows you to create a custom object schema') and includes a rename-history sentence that is meta-commentary rather than decision-relevant. The useful content could be delivered in roughly half the lines.

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

Completeness4/5

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

For a one-parameter creation tool with rich nested schema documentation and full annotations, the description covers purpose, exclusions, endpoint, and auth. It omits any mention of the return value (the created schema object) and failure behavior on key collisions, which matters for a non-idempotent create with no output schema.

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% and the single body parameter is a nested DTO whose fields (key, labels, locationId, primaryDisplayPropertyDetails) are each documented with examples. The description adds no parameter-level guidance beyond the schema, 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 concrete verb+resource ('Creates a new custom object SCHEMA') and immediately disambiguates it from a record, which is the single biggest confusion risk in this family. It also names the sibling tools (ghl_object_update_schema / ghl_object_get_schema_by_key) that operate on already-created objects, so the agent can separate them without opening schemas.

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 says what this is NOT ('not a record') and contrasts with the schema-update/read siblings, so the when-to-use boundary is stated rather than implied. It also gives a hard prerequisite (Agency/company-level token) and the OAuth scope, which determines whether the call is even permitted.

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