AI agents call hs_recent_contacts 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 contact data without altering state. It is a straightforward retrieval operation consistent with other read-category tools like hs_get_contact and hs_crm_search on the same server. The blast radius of misuse is minimal—an agent could retrieve contact records it shouldn't access, but cannot modify or delete them.
From the tool's definition Tool retrieves 'most recently created contacts' with optional filtering. The description uses 'get' language and filtering operations, with no indication of modification, deletion, or side effects.
Attacks that exploit this kind of access
Most recently created contacts, optionally filtered by lifecycle stage (lead, marketingqualifiedlead, opportunity, customer, etc.). 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_contacts: 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_contacts 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_contacts 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_contacts. 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_contacts 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 →