AI agents use update_task_progress to create or update resources in ATMcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ATMcp environment.
This tool modifies task metadata (progress status and lease renewal) reversibly within a distributed task management system. It does not delete data (not Destructive), does not move money (not Financial), does not execute arbitrary code (not Execute), and creates/modifies coordination state rather than just reading (not Read).
From the tool's definition Tool name 'update_task_progress' and description 'Report progress and renew your lease' indicates modification of task state. The status parameter accepts 'in_progress' or 'blocked', which are state transitions.
Attacks that exploit this kind of access
Report progress and renew your lease. status may be 'in_progress' or 'blocked'. It is categorised as a Write tool in the ATMcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AT MCP server in PolicyLayer and add a rule for update_task_progress: 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 ATMcp. Nothing to install.
update_task_progress is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_task_progress 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 update_task_progress. 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.
update_task_progress is provided by the AT MCP server (midcheck/atmcp). 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 →