AI agents use hubspot_create_deal 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 data (a deal record) in HubSpot, which is reversible (deals can be deleted or archived by the user). The severity is medium because misuse by an AI agent could create unwanted deal records, pollute the CRM, and cause business confusion, but the impact is limited to CRM data and can be remedied.
From the tool's definition Tool description states 'Create a new deal in HubSpot CRM' and 'the deal is immediately created in the specified pipeline' — this is a create operation that modifies data in an external system (HubSpot).
Attacks that exploit this kind of access
Create a new deal in HubSpot CRM. Side effect: the deal is immediately created in the specified pipeline. Use hubspot_pipelines first to get valid pipeline and stage IDs. 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_deal: 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_deal 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_deal 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_deal. 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_deal 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 →