Request a code review from Codex and Gemini CLIs. Provide code directly as a string. Returns feedback from both reviewers for Claude to consider.
AI agents invoke review_code to trigger actions in Review MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes external CLI programs (Codex and Gemini) as subprocesses to perform analysis. While the intent is read-only code review, it runs external processes whose behavior depends on the input and the CLI tools installed. This qualifies as Execute rather than Read because it triggers external operations beyond simple data retrieval.
From the tool's definition 'Request a code review from Codex and Gemini CLIs' - triggers execution of external CLI processes (Codex and Gemini CLIs) to analyze the provided code
Attacks that exploit this kind of access
Request a code review from Codex and Gemini CLIs. Provide code directly as a string. Returns feedback from both reviewers for Claude to consider. It is categorised as a Execute tool in the Review MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Review MCP Server MCP server in PolicyLayer and add a rule for review_code: 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 Review MCP Server. Nothing to install.
review_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the review_code 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_code. 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_code is provided by the Review MCP Server MCP server (je4550/review-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
review_code is one line of Review MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →