AI agents use hubspot_create_contact to create or update resources in Access — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Access environment.
This tool creates new records in HubSpot, which is a reversible write operation (contacts can be deleted). It is not destructive (deletion is not performed by this tool), not financial (no money moves), and not read-only.
From the tool's definition Tool explicitly performs 'Create a new contact in HubSpot CRM' with immediate side effect that 'the contact is immediately created and may trigger workflows.' This is a create operation that modifies persistent data in an external service.
Attacks that exploit this kind of access
Create a new contact in HubSpot CRM. Side effect: the contact is immediately created and may trigger workflows. Email is required; all other fields are optional. It is categorised as a Write tool in the Access MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Access MCP server in PolicyLayer and add a rule for hubspot_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 Access. Nothing to install.
hubspot_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 hubspot_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 hubspot_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.
hubspot_create_contact is provided by the Access MCP server (scottpedia0/access). 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 →