AI agents call hs_recent_deals 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 returns deal data without creating, modifying, deleting, or executing any operations. It is a straightforward data retrieval function with optional filtering, characteristic of a Read category tool. The severity is low because retrieval of deal metadata poses minimal risk even if misused by an AI agent—it does not modify system state or commit financial transactions.
From the tool's definition Tool description explicitly states it retrieves 'Most recently created deals' with a filter option (openOnly=true). The verb 'retrieves' and lack of any modification, deletion, or execution language indicates a read-only query operation.
Attacks that exploit this kind of access
Most recently created deals. Pass openOnly=true to exclude closed deals. 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_recent_deals: 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_recent_deals 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_recent_deals 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_recent_deals. 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_recent_deals 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 →