Find unused code with vulture.
AI agents call analyze_dead_code 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.
This tool retrieves and reports analysis results about code quality metrics (specifically unused code detection). It performs no side effects, creates no modifications, executes no code, and makes no destructive changes. It is purely informational, fitting the 'Read' category of data retrieval tools.
From the tool's definition Tool name 'analyze_dead_code' and description 'Find unused code with vulture' indicate a read-only analysis operation. Vulture is a static analysis tool that detects unused code without modifying or executing the codebase.
Attacks that exploit this kind of access
Find unused code with vulture. 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_dead_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 Code Quality. Nothing to install.
analyze_dead_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 analyze_dead_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 analyze_dead_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.
analyze_dead_code 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 →