AI agents call products_search to retrieve information from HubSpot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation on products, which is a retrieval action with no side effects or data modification. It fits the Read category profile of querying/searching data. The low severity reflects minimal blast radius—misuse would only expose existing product information, not modify or delete data, and would not execute code or commit financial transactions.
From the tool's definition Tool name 'products_search' with description 'Search products' indicates a query operation that retrieves product data without modifying it. The verb 'search' is explicitly listed in the Read category examples (search, list, get, fetch).
Documented attack patterns abuse exactly the kind of access products_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HubSpot MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for products_search:
{
"version": "1",
"default": "deny",
"tools": {
"products_search": {}
}
}products_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search products. It is categorised as a Read tool in the HubSpot MCP MCP Server, which means it retrieves data without modifying state.
Register the HubSpot MCP server in PolicyLayer and add a rule for products_search: 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 MCP. Nothing to install.
products_search 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 products_search 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 products_search. 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.
products_search is provided by the HubSpot MCP server (shinzo-labs/hubspot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 112 HubSpot MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
112 HubSpot MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.