Review code for bugs, security issues, performance, or style problems. Simplified zen-inspired tool for systematic code review.
AI agents call review-code to retrieve information from Ultra MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Code review is a read/analysis operation: it inspects provided code and returns findings. No data is written, executed, or deleted. The 'zen-inspired' and 'systematic code review' framing reinforces a passive analysis role. Misuse risk is low since the tool only produces a report.
From the tool's definition 'Review code for bugs, security issues, performance, or style problems' — the tool analyzes and reports on code without modifying it.
Documented attack patterns abuse exactly the kind of access review-code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ultra MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for review-code:
{
"version": "1",
"default": "deny",
"tools": {
"review-code": {}
}
}review-code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Review code for bugs, security issues, performance, or style problems. Simplified zen-inspired tool for systematic code review. It is categorised as a Read tool in the Ultra MCP MCP Server, which means it retrieves data without modifying state.
Register the Ultra 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 Ultra 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 Ultra MCP server (realmikechong/ultra-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 Ultra MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 Ultra MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.