create_object_record
Create a new record in a custom or standard object with properties, owner, and followers
This record as markdown: /tools/ghl/create-object-record.md
What create_object_record does on Ghl
AI agents use create_object_record to create or update resources in Ghl, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghl environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
owner | array | — | Array of user IDs who own this record (limited to 1, only for custom objects) |
followers | array | — | Array of user IDs who follow this record (limited to 10) |
schemaKey | string | Yes | Schema key of the object (e.g., "custom_objects.pet", "business") |
locationId | string | — | Location ID (uses default if not provided) |
properties | object | Yes | Record properties as key-value pairs (e.g., {"name": "Buddy", "breed": "Golden Retriever"}) |
Parameters from the server's own tool schema.
Why create_object_record is rated Medium
Creating new records is a reversible Write operation. While it modifies the system state, records can be subsequently deleted or modified. Severity is medium rather than high because the blast radius depends on what object types are created and how they're used downstream, but creation alone is less damaging than deletion or financial operations. High confidence due to clear 'Create' language in the description.
From the tool's definition Tool description states 'Create a new record' which is a data creation operation. The tool adds new data to custom or standard objects without indicating any deletion, overwriting, or financial consequences.
Attacks that exploit this kind of access
The rule that runs create_object_record safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ghl, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_object_record, this is the rule to start with:
create_object_record stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ghl, apply this rule, and every create_object_record call is checked against it from then on.
Questions about create_object_record
Create a new record in a custom or standard object with properties, owner, and followers. It is categorised as a Write tool in the Ghl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_object_record accepts 5 parameters: owner, followers, schemaKey, locationId, properties. Required: schemaKey, properties. The full parameter table on this page comes from the server's own tool schema.
Register the Ghl MCP server in PolicyLayer and add a rule for create_object_record: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ghl. Nothing to install.
create_object_record is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_object_record rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_object_record. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_object_record is provided by the Ghl MCP server (ghl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ghl, and thousands of servers like it.
This server
Across the catalogue