lsp_code_actions · Lsp MCP: Risk & Policy

WHAT IT DOES

What lsp_code_actions does on Lsp

AI agents invoke lsp_code_actions 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_code_actions needs a policy

Although primarily a read-like operation (fetching suggestions), the tool's core capability is executing code transformations (refactoring actions) when apply=true. This modifies source code files and triggers external LSP operations with side effects that depend on the action selected. This makes it Execute rather than Write because it runs automated transformations whose full impact may not be immediately obvious.

From the tool's definition 'Get quick fixes and refactoring suggestions' and 'Set apply=true to execute an action' — this tool can apply automated code transformations (auto-fix errors, organize imports, extract functions) to source files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lsp_code_actions Rate-limited

lsp_code_actions 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_code_actions": {
      "limits": [
        {
          "counter": "lsp_code_actions_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_code_actions

What does the lsp_code_actions tool do? +

Get quick fixes and refactoring suggestions at a position. Use to auto-fix errors, organize imports, extract functions, or apply other automated transformations. Set apply=true to execute an action. 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_code_actions? +

Register the Lsp MCP server in PolicyLayer and add a rule for lsp_code_actions: 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_code_actions? +

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

Can I rate-limit lsp_code_actions? +

Yes. Add a rate_limit block to the lsp_code_actions 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_code_actions completely? +

Set action: deny in the PolicyLayer policy for lsp_code_actions. 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_code_actions? +

lsp_code_actions 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.