Cheap-gateway code review. Use job_id to review a finished worker diff/checks, or files to review selected sandbox files. Returns structured JSON verdict when parseable.
AI agents call review to retrieve information from MCP Codex Worker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes code review data without creating, modifying, or deleting anything. It is primarily a Read operation. Severity is medium rather than low because code review results could expose sensitive information about code structure, vulnerabilities, or business logic if the tool were misused to review unintended files, and the tool accepts a 'files' parameter giving some control over what gets…
From the tool's definition Tool description states 'review a finished worker diff/checks' and 'review selected sandbox files' with results returned as 'structured JSON verdict'. The action is inspecting/analyzing code and test results, not modifying them.
Attacks that exploit this kind of access
Cheap-gateway code review. Use job_id to review a finished worker diff/checks, or files to review selected sandbox files. Returns structured JSON verdict when parseable. It is categorised as a Read tool in the MCP Codex Worker MCP Server, which means it retrieves data without modifying state.
Register the MCP Codex Worker MCP server in PolicyLayer and add a rule for 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 MCP Codex Worker. Nothing to install.
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 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 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.
review is provided by the MCP Codex Worker MCP server (sorryorc/mcp-codex-worker). 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 →