Approve a review request. Only assigned reviewers can approve.
AI agents use approve_review to create or update resources in Rockhopper MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rockhopper MCP Server environment.
The tool approves (accepts/authorizes) a review request, which changes the status or metadata of a review object in the Rockhopper workspace. This is a write operation—it modifies data state reversibly.
From the tool's definition Tool description: "Approve a review request. Only assigned reviewers can approve." This action modifies review state by transitioning a review from pending/open to approved status, which is a reversible state change to workspace data.
Attacks that exploit this kind of access
Approve a review request. Only assigned reviewers can approve. It is categorised as a Write tool in the Rockhopper MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rockhopper MCP Server MCP server in PolicyLayer and add a rule for approve_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 Rockhopper MCP Server. Nothing to install.
approve_review is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the approve_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 approve_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.
approve_review is provided by the Rockhopper MCP Server MCP server (rockhopper-co/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 →