AI agents call crm_search_objects 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.
The tool retrieves and filters CRM data without creating, modifying, or deleting any records. Search operations are inherently read-only with no side effects. Even if an AI agent misuses filters, it can only discover existing data, not alter it. Severity is low because the blast radius is limited to information disclosure of data the agent may already have access to.
From the tool's definition Tool name is 'crm_search_objects' and description states 'Search CRM objects using filters' — this is a query/search operation with no modification or deletion capability.
Documented attack patterns abuse exactly the kind of access crm_search_objects 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 crm_search_objects:
{
"version": "1",
"default": "deny",
"tools": {
"crm_search_objects": {}
}
}crm_search_objects 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 CRM objects using filters. 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 crm_search_objects: 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.
crm_search_objects 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 crm_search_objects 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 crm_search_objects. 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.
crm_search_objects 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.