List all workflows 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 call workflow_list to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays workflow metadata without modifying, creating, deleting, or executing anything. It is purely informational. The moderate complexity of the workflow system it introspects does not elevate the risk of a read-only listing operation. Severity is low because misuse (e.g., an agent listing all workflows) causes no direct harm—it may leak workflow names or structure, but no action is taken.
From the tool's definition Tool name 'workflow_list' and description explicitly states 'List all workflows' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all workflows 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 Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for workflow_list: 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_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the workflow_list 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_list. 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_list 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.