lsp_stop_server · Lsp MCP: Risk & Policy

WHAT IT DOES

What lsp_stop_server does on Lsp

AI agents invoke lsp_stop_server to trigger actions in Lsp. 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.

WHY IT NEEDS A POLICY

Why lsp_stop_server needs a policy

Stopping a language server is a state-changing operation that terminates an external process. While not destructive (the server can be restarted) and not a read operation, it executes a command/action with external side effects. This qualifies as Execute. Severity is medium because stopping a language server could interrupt development workflows but is reversible and doesn't destroy data or move money.

From the tool's definition Tool name 'lsp_stop_server' and description 'Stop a running language server' indicates it triggers an external operation (terminating a server process) whose effects depend on which server argument is provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lsp_stop_server Rate-limited

lsp_stop_server stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "lsp_stop_server": {
      "limits": [
        {
          "counter": "lsp_stop_server_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Lsp, so you can run agents against it safely.

FAQ

Questions about lsp_stop_server

What does the lsp_stop_server tool do? +

Stop a running language server to free resources. Servers auto-stop after idle timeout, so manual stop is rarely needed. It is categorised as a Execute tool in the Lsp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on lsp_stop_server? +

Register the Lsp MCP server in PolicyLayer and add a rule for lsp_stop_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 Lsp. Nothing to install.

What risk level is lsp_stop_server? +

lsp_stop_server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit lsp_stop_server? +

Yes. Add a rate_limit block to the lsp_stop_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.

How do I block lsp_stop_server completely? +

Set action: deny in the PolicyLayer policy for lsp_stop_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.

What MCP server provides lsp_stop_server? +

lsp_stop_server is provided by the Lsp MCP server (lsp-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.