Stop JDT.LS server(s) and clear runtime state.
AI agents invoke restart_server to trigger actions in Jons Mcp Java. 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.
This tool executes a server control operation (restart and state clearing), which qualifies as Execute rather than Write or Destructive. While it clears state, the primary action is triggering an external process. It's not Destructive in the classical sense because it does not permanently delete user data or make irreversible changes to version-controlled artifacts.
From the tool's definition Tool description states 'Stop JDT.LS server(s) and clear runtime state' — directly triggers an external operation (server restart and state clearing) with effects that cannot be precisely predicted without knowing the full system context.
Attacks that exploit this kind of access
Stop JDT.LS server(s) and clear runtime state. It is categorised as a Execute tool in the Jons Mcp Java MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Jons Mcp Java MCP server in PolicyLayer and add a rule for restart_server: 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 Jons Mcp Java. Nothing to install.
restart_server 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_server 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_server. 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_server is provided by the Jons Mcp Java MCP server (jonmmease/jons-mcp-java). 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 →