AI agents call validate_code_rules to retrieve information from Sonarqube without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries SonarQube to retrieve code rule violations—a read-only operation that returns data about code quality issues. It does not execute code, modify data, delete anything, or commit financial transactions. The sibling tools (get_project_issues, get_quality_profile, get_sonar_rules) are also read operations, consistent with SonarQube's primary function as a static analysis platform.
From the tool's definition Tool name 'validate_code_rules' and description 'Get rule violations for code validation' indicate querying/retrieving rule violation data.
Attacks that exploit this kind of access
Get rule violations for code validation. It is categorised as a Read tool in the Sonarqube MCP Server, which means it retrieves data without modifying state.
Register the Sonarqube MCP server in PolicyLayer and add a rule for validate_code_rules: 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 Sonarqube. Nothing to install.
validate_code_rules 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 validate_code_rules 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 validate_code_rules. 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.
validate_code_rules is provided by the Sonarqube MCP server (@miocid152/sonarqube-mcp-server). 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 →