AI agents call check_task_lock 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 the current state of a task lock lease without modifying any data, triggering external operations, or causing side effects. It is a pure information query consistent with Read category semantics. The low severity reflects minimal blast radius—an AI agent misusing this tool would only obtain lock status information, not gain ability to execute tasks, modify data, or cause destructive actions.
From the tool's definition Tool name 'check_task_lock' combined with description 'Check local task lock lease status' indicates a query/inspection operation. The verb 'check' and the focus on status inspection (not modification or execution) confirm this is a read-only operation.
Attacks that exploit this kind of access
Check local task lock lease status. 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 check_task_lock: 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.
check_task_lock 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 check_task_lock 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 check_task_lock. 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.
check_task_lock 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 →