lsp_rename · Lsp MCP: Risk & Policy

WHAT IT DOES

What lsp_rename does on Lsp

AI agents use lsp_rename to create or update resources in Lsp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lsp environment.

WHY IT NEEDS A POLICY

Why lsp_rename needs a policy

This tool creates or modifies code reversibly by renaming symbols (variables, functions, classes, etc.) across a codebase. While the changes are theoretically reversible through version control or undo, the tool itself performs widespread Write operations across multiple files simultaneously. The high severity reflects the blast radius—a malicious rename could break an entire codebase's functionality.

From the tool's definition Tool description explicitly states it 'Rename[s] a symbol across the entire codebase' and has a dry_run parameter that can be disabled, allowing it to apply changes. The phrase 'before applying' confirms actual modification capability.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lsp_rename Rate-limited

lsp_rename stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_rename": {
      "limits": [
        {
          "counter": "lsp_rename_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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_rename

What does the lsp_rename tool do? +

Rename a symbol across the entire codebase safely. Handles all references, imports, and re-exports. Use dry_run=true (default) to preview changes before applying. More reliable than find-and-replace. It is categorised as a Write tool in the Lsp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on lsp_rename? +

Register the Lsp MCP server in PolicyLayer and add a rule for lsp_rename: 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_rename? +

lsp_rename is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit lsp_rename? +

Yes. Add a rate_limit block to the lsp_rename 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_rename completely? +

Set action: deny in the PolicyLayer policy for lsp_rename. 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_rename? +

lsp_rename 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.