AI agents call query_task_history to retrieve information from Tick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical information about tasks that have already been completed, abandoned, or deleted. It performs no modifications, deletions, or side effects—it only queries and filters existing data. This is a classic Read category tool with minimal risk; the worst case is exposure of task history metadata, which poses low severity.
From the tool's definition The tool 'query_task_history' is described as a query operation that retrieves historical task data (completed, abandoned, or deleted tasks).
Attacks that exploit this kind of access
Query completed, abandoned, or deleted task history with the same fine filters. It is categorised as a Read tool in the Tick MCP Server, which means it retrieves data without modifying state.
Register the Tick MCP server in PolicyLayer and add a rule for query_task_history: 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 Tick. Nothing to install.
query_task_history 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 query_task_history 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 query_task_history. 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.
query_task_history is provided by the Tick MCP server (kpihx/tick-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 →