Return a paused task to the queued state so a worker can claim it.
AI agents use resume_task to create or update resources in State Trace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your State Trace environment.
resume_task modifies task state from paused to queued, making it a Write operation (reversible state modification). Severity is medium because misuse could disrupt task workflow—an agent could maliciously resume critical tasks out of order or resume tasks intended to remain paused—but the effect is not destructive (tasks remain intact) or irreversible.
From the tool's definition Tool description states it returns 'a paused task to the queued state', which modifies the state of a task object. This is a reversible state change operation.
Attacks that exploit this kind of access
Return a paused task to the queued state so a worker can claim it. It is categorised as a Write tool in the State Trace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the State Trace MCP server in PolicyLayer and add a rule for resume_task: 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 State Trace. Nothing to install.
resume_task 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 resume_task 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 resume_task. 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.
resume_task is provided by the State Trace MCP server (agent-pattern-labs/state-trace). 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 →