Execute a 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_execute 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.
The tool executes workflows with dependency graphs and LLM-driven steps, which is a form of code execution. While the tool itself doesn't delete data, it runs external operations that could have side effects depending on what workflow is submitted. This qualifies as Execute rather than Write (which would be for data creation/modification) or Destructive (no mention of irreversible data deletion).
From the tool's definition Tool name 'workflow_execute' and description states 'Execute a workflow' with features like 'step-output binding across LLM-driven steps', 'retry policy', and 'pause/resume'.
Attacks that exploit this kind of access
Execute a 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_execute: 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_execute 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_execute 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_execute. 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_execute 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.