AI agents call hs_form_submissions 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 queries and retrieves historical form submission records without modifying, deleting, or executing operations. It falls clearly into the Read category. Severity is medium rather than low because form submissions may contain sensitive personal information (PII, email addresses, phone numbers, etc.) that could be exposed if an agent misuses it to exfiltrate customer data or leverage it for reconnaissance.
From the tool's definition Tool retrieves form submission data including field values and timestamps with 'Get recent submissions' — a read-only query operation.
Attacks that exploit this kind of access
Get recent submissions for a form including all field values and submission timestamps. 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_form_submissions: 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_form_submissions 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_form_submissions 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_form_submissions. 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_form_submissions 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 →