Find SonarQube project keys by project name or key.
AI agents call search_sonar_projects to retrieve information from Sonarqube Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves project metadata (keys) from SonarQube without modifying, executing, or deleting anything. It is a standard read operation with minimal blast radius if misused by an agent—worst case being exposure of project identifiers that are typically non-sensitive metadata.
From the tool's definition Tool name 'search_sonar_projects' and description 'Find SonarQube project keys by project name or key' indicate a search/query operation. Server is explicitly described as 'Read-only MCP server' with no side effects.
Attacks that exploit this kind of access
Find SonarQube project keys by project name or key. It is categorised as a Read tool in the Sonarqube Api MCP Server, which means it retrieves data without modifying state.
Register the Sonarqube Api MCP server in PolicyLayer and add a rule for search_sonar_projects: 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 Api. Nothing to install.
search_sonar_projects 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 search_sonar_projects 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 search_sonar_projects. 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.
search_sonar_projects is provided by the Sonarqube Api MCP server (yozzone/sonarqube-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 →