Get current V3 implementation progress percentage and metrics Use when native TodoWrite is wrong because you need cross-session goal-completion tracking with witness/audit trail. For in-session checklists, native TodoWrite is simpler.
AI agents call progress_check 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 queries progress data and returns metrics for monitoring purposes. It performs no writes, deletions, code execution, or financial operations. The mention of "witness/audit trail" refers to how the data is tracked, not capabilities of this tool. The appropriate category is Read, with low severity since progress queries pose minimal risk if misused by an AI agent.
From the tool's definition Tool description states "Get current V3 implementation progress percentage and metrics" — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get current V3 implementation progress percentage and metrics Use when native TodoWrite is wrong because you need cross-session goal-completion tracking with witness/audit trail. For in-session checklists, native TodoWrite is simpler. 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 progress_check: 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.
progress_check 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 progress_check 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 progress_check. 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.
progress_check 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.