Review code changes and provide feedback
AI agents call review_code to retrieve information from Reviewer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and analyzes code changes to produce feedback. It does not modify files, execute code, or perform destructive actions. However, as an AI-powered review tool, it may internally call LLM APIs or read repository data, making it slightly more than a trivial read. Severity is medium because misuse could expose sensitive code to external AI models, but there is no write or destructive capability described.
From the tool's definition 'Review code changes and provide feedback' — read-only analysis of code with no side effects mentioned
Attacks that exploit this kind of access
Review code changes and provide feedback. It is categorised as a Read tool in the Reviewer MCP MCP Server, which means it retrieves data without modifying state.
Register the Reviewer 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 Reviewer MCP. Nothing to install.
review_code 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_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 Reviewer MCP server (jaggederest/mcp_reviewer). 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 →