AI agents call patrol_tasks to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes task status information to identify problematic patterns, but does not create, modify, delete, or execute operations. It is a diagnostic/monitoring tool that fits the 'Read' category as it queries task state without causing changes.
From the tool's definition 'Scan for task issues' indicates the tool performs analysis and monitoring without modifying data. It checks for conditions like stuck tasks, low-confidence completions, orphaned tasks, zombie-blocked tasks, and pending reviews—all observational queries with…
Attacks that exploit this kind of access
Scan for task issues: stuck tasks, low-confidence completions, orphaned tasks, zombie-blocked tasks, and pending reviews. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for patrol_tasks: 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 Todos. Nothing to install.
patrol_tasks 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 patrol_tasks 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 patrol_tasks. 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.
patrol_tasks is provided by the Todos MCP server (@hasna/todos). 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 →