Search tasks with specific filters
AI agents call tasks_search to retrieve information from HubSpot MCP Server 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/query operation on task data in HubSpot's CRM. Search operations are inherently non-destructive reads that retrieve information based on filters. There is no indication of create, update, delete, or execution capabilities. The blast radius of misuse is minimal—an agent could retrieve unintended task data but cannot modify systems or cause irreversible harm.
From the tool's definition Tool name 'tasks_search' and description 'Search tasks with specific filters' indicate a query operation that retrieves task data without modifying or deleting it.
Attacks that exploit this kind of access
Search tasks with specific filters. It is categorised as a Read tool in the HubSpot MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HubSpot MCP Server MCP server in PolicyLayer and add a rule for tasks_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 Server. Nothing to install.
tasks_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 tasks_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 tasks_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.
tasks_search is provided by the HubSpot MCP Server MCP server (kozo93/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 →