AI agents call health_report to retrieve information from Codescan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates codebase metadata without side effects. It produces an informational health report graded on existing code characteristics. Even if the AI agent misuses it (e.g., requests frequent scans), the blast radius is minimal — the tool cannot modify code, execute arbitrary commands, or cause data loss.
From the tool's definition The tool 'health_report' generates reports by scanning codebases for static analysis metrics (TODOs, FIXMEs, complexity, file stats, dependencies). The description uses only passive verbs: 'generate', 'scans', 'stats' — all read-only operations.
Attacks that exploit this kind of access
Generate a full codebase health report: stats, TODOs, complexity, dependencies, and a letter grade. It is categorised as a Read tool in the Codescan MCP Server, which means it retrieves data without modifying state.
Register the Codescan MCP server in PolicyLayer and add a rule for health_report: 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 Codescan. Nothing to install.
health_report 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 health_report 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 health_report. 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.
health_report is provided by the Codescan MCP server (yifanyifan897645/codescan-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 →