Check cyclomatic complexity with McCabe.
AI agents call analyze_complexity to retrieve information from Code Quality without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and reports complexity metrics from static analysis. McCabe complexity checking is a deterministic, side-effect-free analysis that queries code structure without creating, modifying, deleting, or executing code. It falls squarely in the Read category.
From the tool's definition Tool name is 'analyze_complexity' and description states 'Check cyclomatic complexity with McCabe' — this is a read-only analysis operation that performs static code quality checking without modifying code or executing arbitrary operations.
Attacks that exploit this kind of access
Check cyclomatic complexity with McCabe. It is categorised as a Read tool in the Code Quality MCP Server, which means it retrieves data without modifying state.
Register the Code Quality MCP server in PolicyLayer and add a rule for analyze_complexity: 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 Code Quality. Nothing to install.
analyze_complexity 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 analyze_complexity 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 analyze_complexity. 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.
analyze_complexity is provided by the Code Quality MCP server (javier-morenosa/code-quality-mcp). 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 →