search_hotspots
AI agents call search_hotspots to retrieve information from Mcp Sonarcloud without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search/query security hotspots in SonarCloud, which is a retrieval operation with no side effects. While the description is empty, the name and surrounding read-only tools (search_my_sonarqube_projects, list_issue_tags, get_project_quality_gate_status) establish a clear pattern of Read operations. Confidence is slightly reduced due to missing description, but the categorical evidence is strong.
From the tool's definition Tool name 'search_hotspots' combined with sibling tools that are predominantly read-only (list_*, get_*, search_*) and the server context of querying SonarCloud projects and security hotspots.
Attacks that exploit this kind of access
search_hotspots. It is categorised as a Read tool in the Mcp Sonarcloud MCP Server, which means it retrieves data without modifying state.
Register the Mcp Sonarcloud MCP server in PolicyLayer and add a rule for search_hotspots: 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 Mcp Sonarcloud. Nothing to install.
search_hotspots 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_hotspots 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_hotspots. 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_hotspots is provided by the Mcp Sonarcloud MCP server (lukleh/mcp-sonarcloud). 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 →