AI agents call code_review to retrieve information from Onion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Code review is an inspection and analysis operation that reads and evaluates code without modifying, executing, or destructing anything. It produces diagnostic output but has no side effects on systems or data. This is a classic Read category tool with low severity since misuse would only result in incorrect analysis feedback, not operational harm.
From the tool's definition Tool name 'code_review' and description indicate it analyzes code to identify bugs, security vulnerabilities, performance issues, and code style problems.
Attacks that exploit this kind of access
审查代码，找出 Bug、安全漏洞、性能问题和代码风格问题。. It is categorised as a Read tool in the Onion MCP Server, which means it retrieves data without modifying state.
Register the Onion MCP server in PolicyLayer and add a rule for code_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 Onion. Nothing to install.
code_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 code_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 code_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.
code_review is provided by the Onion MCP server (onion-ai/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 →