AI agents use hs_create_contact to create or update resources in Hubspot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hubspot environment.
This tool creates new data (a contact record) in HubSpot's CRM system, which is a reversible write operation. It does not delete, execute arbitrary code, or move money. Severity is medium because misuse could create spam contacts, pollute the CRM with false data, or enable social engineering via contact injection, but the impact is contained to contact records and can be remediated by deletion.
From the tool's definition Tool name 'hs_create_contact' and description 'Create a new HubSpot contact' indicate data creation. Email is a required field, establishing a persistent new record in the CRM database.
Attacks that exploit this kind of access
Create a new HubSpot contact. Email is required; all other fields are optional. It is categorised as a Write tool in the Hubspot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hubspot MCP server in PolicyLayer and add a rule for hs_create_contact: 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_create_contact 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 hs_create_contact 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_create_contact. 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_create_contact 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 →