AI agents call sq_search_rules to retrieve information from Sonarcube without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against SonarQube's rule catalogue. It retrieves metadata about analysis rules based on filter criteria (language, type, severity, tags) but does not create, modify, delete, or execute any code or rules. The blast radius of misuse is minimal — an attacker could only enumerate or learn about available rules, which does not impact systems or data integrity.
From the tool's definition Tool name is 'sq_search_rules' and description states 'Search analysis rules by language, type, severity, or tags' — this is a query operation that retrieves rule definitions from SonarQube without modifying or executing anything.
Attacks that exploit this kind of access
Search analysis rules by language, type, severity, or tags. It is categorised as a Read tool in the Sonarcube MCP Server, which means it retrieves data without modifying state.
Register the Sonarcube MCP server in PolicyLayer and add a rule for sq_search_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 Sonarcube. Nothing to install.
sq_search_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 sq_search_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 sq_search_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.
sq_search_rules is provided by the Sonarcube MCP server (sonarcube-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 →