lsp_start_server · Lsp MCP: Risk & Policy

WHAT IT DOES

What lsp_start_server does on Lsp

AI agents invoke lsp_start_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_start_server needs a policy

Starting a language server constitutes executing an external operation whose effects depend on which server is started and the workspace configuration. While not destructive in isolation, it is an Execute action (process launch) rather than a passive Read operation.

From the tool's definition Tool description states 'Start a language server manually for a workspace' and provides 'explicit control over server lifecycle.' Starting a language server is an operational action that triggers external process execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lsp_start_server Rate-limited

lsp_start_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_start_server": {
      "limits": [
        {
          "counter": "lsp_start_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_start_server

What does the lsp_start_server tool do? +

Start a language server manually for a workspace. Usually not needed—servers auto-start when you use other LSP tools. Use only when you need explicit control over server lifecycle. 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_start_server? +

Register the Lsp MCP server in PolicyLayer and add a rule for lsp_start_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_start_server? +

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

Can I rate-limit lsp_start_server? +

Yes. Add a rate_limit block to the lsp_start_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_start_server completely? +

Set action: deny in the PolicyLayer policy for lsp_start_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_start_server? +

lsp_start_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.