Get current watch status for progress monitoring 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_watch 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.
The tool retrieves status information for monitoring purposes. The phrase 'Get current watch status' indicates a query/fetch operation. No creation, modification, deletion, or execution of external operations is described. The mention of 'audit trail' reinforces this is a read-only inspection mechanism.
From the tool's definition Tool description states 'Get current watch status' and references 'progress monitoring' and 'goal-completion tracking with witness/audit trail'—these are retrieval and observational operations with no modification or side effects mentioned.
Attacks that exploit this kind of access
Get current watch status for progress monitoring 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_watch: 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_watch 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_watch 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_watch. 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_watch 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.