AI agents use pause_kwork to create or update resources in Kwork — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kwork environment.
This tool pauses a service listing, making it invisible to buyers. It modifies the state of a kwork (sets it to paused/inactive) but is reversible — the kwork can presumably be unpaused/resumed. No data is deleted, no money is moved, and no code is executed. The blast radius is medium: misuse could cause loss of business visibility and potential revenue, but the action can be undone.
From the tool's definition Приостановить кворк. Кворк перестанет отображаться покупателям. (Pause a kwork/gig — it will stop being visible to buyers)
Attacks that exploit this kind of access
Приостановить кворк. Кворк перестанет отображаться покупателям. It is categorised as a Write tool in the Kwork MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kwork MCP server in PolicyLayer and add a rule for pause_kwork: 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 Kwork. Nothing to install.
pause_kwork 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 pause_kwork 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 pause_kwork. 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.
pause_kwork is provided by the Kwork MCP server (simonether/kwork-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 →