AI agents call hs_search_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 retrieves deal records matching search criteria without altering, creating, or destroying data. It has no side effects beyond data retrieval. The blast radius of misuse is minimal — an attacker could learn about deals in the system but cannot modify, execute actions, or cause financial harm through search alone.
From the tool's definition Tool performs 'Full-text search across deals by name' — a query operation with no modification, deletion, or execution of external processes. The verb 'search' and the absence of any mutation language indicate read-only retrieval.
Attacks that exploit this kind of access
Full-text search across deals by name. 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_search_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_search_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_search_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_search_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_search_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 →