AI agents call sq_search_issues 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 retrieves and filters existing code quality issue data from SonarQube without modifying, executing, or deleting anything. It is a standard data query operation with no side effects, fitting the Read category. The filtering parameters (severity, type, file, rule) are all selection criteria for the search, not actions that alter state.
From the tool's definition Tool is named 'sq_search_issues' and described as 'Search for issues' with filtering capabilities. The verb 'search' and lack of any mutation language (create, update, delete, execute) indicates a read-only operation that queries and retrieves data from…
Attacks that exploit this kind of access
Search for issues (bugs, vulnerabilities, code smells) with filtering by severity, type, file, rule, etc. 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_issues: 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_issues 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_issues 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_issues. 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_issues 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 →