AI agents call workflow_review to retrieve information from Musubix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and analyzes workflow state information, then presents it for human review. This is fundamentally a read operation with no side effects—it queries current phase status and returns analysis without creating, modifying, or deleting data. The subsequent user approval step is a separate human decision, not an automated action by the tool itself.
From the tool's definition Tool description indicates it performs a 'self-review' (セルフレビューを実行し) of the current phase and 'displays results' (結果を表示します). It requests user approval/modification (ユーザーに承認/修正を求めます) but does not itself modify data or execute external operations.
Attacks that exploit this kind of access
現在のフェーズのセルフレビューを実行し、結果を表示します。 レビュー完了後、ユーザーに承認/修正を求めます。. It is categorised as a Read tool in the Musubix MCP Server, which means it retrieves data without modifying state.
Register the Musubix MCP server in PolicyLayer and add a rule for workflow_review: 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 Musubix. Nothing to install.
workflow_review 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_review 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_review. 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_review is provided by the Musubix MCP server (@nahisaho/musubix-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →