AI agents invoke pause_loop to trigger actions in Scrumdo. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool controls active system processes by pausing loop execution, which is an external operation that affects running state. While not destructive (reversible via resume), it is an Execute action because it manipulates ongoing operations whose effects depend on system state. The medium severity reflects that pausing loops could disrupt workflows but is generally reversible and non-destructive.
From the tool's definition 'Pause a loop — stop dispatching new runs' indicates this tool triggers a state change operation that affects the execution flow of background processes or automated workflows
Attacks that exploit this kind of access
Pause a loop — stop dispatching new runs (an in-flight run finishes;. It is categorised as a Execute tool in the Scrumdo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scrumdo MCP server in PolicyLayer and add a rule for pause_loop: 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 Scrumdo. Nothing to install.
pause_loop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the pause_loop 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_loop. 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_loop is provided by the Scrumdo MCP server (scrumdollc/scrumdo-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 →