Check a file for code quality issues — bugs, code smells, security vulnerabilities, and complexity problems. Like having SonarLint in your IDE. Use after writing or modifying code to catch issues early. Returns issues with exact line numbers, severity, and available quick fixes. For multiple file...
AI agents call check_quality to retrieve information from Sonarlint without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though check_quality only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Check a file for code quality issues — bugs, code smells, security vulnerabilities, and complexity problems. Like having SonarLint in your IDE. Use after writing or modifying code to catch issues early. Returns issues with exact line numbers, severity, and available quick fixes. For multiple files use check_files. It is categorised as a Read tool in the Sonarlint MCP Server, which means it retrieves data without modifying state.
Register the Sonarlint MCP server in PolicyLayer and add a rule for check_quality: 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 Sonarlint. Nothing to install.
check_quality 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 check_quality 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 check_quality. 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.
check_quality is provided by the Sonarlint MCP server (@nielspeter/sonarlint-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.