Stop and start Tomcat
AI agents invoke restart_tomcat to trigger actions in Gradle Tomcat MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
restart_tomcat executes a complex operation with external side effects: it halts a running application server and restarts it. While not destructive (data is not deleted) or financial, it is Execute-category because it runs a system-level operation whose effects depend on the current state.
From the tool's definition Tool description states 'Stop and start Tomcat' — this directly triggers external process control operations (stopping and starting a service). The sibling tools include start_tomcat and stop_tomcat, confirming this is an operational control action.
Attacks that exploit this kind of access
Stop and start Tomcat. It is categorised as a Execute tool in the Gradle Tomcat MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gradle Tomcat MCP Server MCP server in PolicyLayer and add a rule for restart_tomcat: 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 Gradle Tomcat MCP Server. Nothing to install.
restart_tomcat is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the restart_tomcat 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 restart_tomcat. 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.
restart_tomcat is provided by the Gradle Tomcat MCP Server MCP server (lkb2k/mcp-gradle). 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 →