AI agents call hs_get_form to retrieve information from Hubspot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves form configuration data without creating, modifying, deleting, or executing any actions. It has no destructive or financial implications. The blast radius of misuse is minimal—an agent could learn form structure but cannot alter forms, submit data, or affect business operations. Low severity due to the informational nature of the data returned.
From the tool's definition Tool name 'hs_get_form' and description 'Get full form definition' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get full form definition including fields, required properties, and redirect settings. It is categorised as a Read tool in the Hubspot MCP Server, which means it retrieves data without modifying state.
Register the Hubspot MCP server in PolicyLayer and add a rule for hs_get_form: 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 Hubspot. Nothing to install.
hs_get_form is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the hs_get_form 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 hs_get_form. 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.
hs_get_form is provided by the Hubspot MCP server (zleventer/hubspot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →