Pause a running workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single linear todo list, native TodoWrite is fine.
AI agents invoke workflow_pause to trigger actions in Claude Flow. 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.
Pausing a running workflow is an external operation that changes the state of an actively executing process. It is reversible (workflows can be resumed), so it doesn't qualify as Destructive, but it does trigger a real side effect on an external orchestration system, placing it in the Execute category. Misuse could halt critical enterprise workflows, warranting medium severity.
From the tool's definition 'Pause a running workflow' — triggers an external operational state change on a live workflow execution
Attacks that exploit this kind of access
Pause a running workflow Use when native TodoWrite + sequential Bash is wrong because the work has a real dependency graph that needs persistence, retry policy, pause/resume, and step-output binding across LLM-driven steps. For a single linear todo list, native TodoWrite is fine. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Flow MCP server in PolicyLayer and add a rule for workflow_pause: 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 Claude Flow. Nothing to install.
workflow_pause 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 workflow_pause 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 workflow_pause. 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.
workflow_pause is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.