apply_refinement_tool · MCP Code Reviewer MCP: Risk & Policy

WHAT IT DOES

What apply_refinement_tool does on MCP Code Reviewer

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

WHY IT NEEDS A POLICY

Why apply_refinement_tool needs a policy

The tool applies code refinements, which means creating or modifying files. While the server mentions 'human-in-the-loop confirmation' and safety measures, the tool itself performs reversible Write operations (with backups). Not Destructive because modifications are reversible via backups; not Execute because it doesn't run arbitrary code or shell commands—it applies pre-generated refinement proposals.

From the tool's definition Tool name 'apply_refinement_tool' indicates application of code modifications. Server description states it 'supports...safe file modifications through automatic backups and path validation,' confirming this tool writes/modifies files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_refinement_tool Rate-limited

apply_refinement_tool 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": {
    "apply_refinement_tool": {
      "limits": [
        {
          "counter": "apply_refinement_tool_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 MCP Code Reviewer, so you can run agents against it safely.

FAQ

Questions about apply_refinement_tool

What does the apply_refinement_tool tool do? +

apply_refinement_tool. It is categorised as a Write tool in the MCP Code Reviewer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_refinement_tool? +

Register the MCP Code Reviewer MCP server in PolicyLayer and add a rule for apply_refinement_tool: 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 MCP Code Reviewer. Nothing to install.

What risk level is apply_refinement_tool? +

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

Can I rate-limit apply_refinement_tool? +

Yes. Add a rate_limit block to the apply_refinement_tool 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 apply_refinement_tool completely? +

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

apply_refinement_tool is provided by the MCP Code Reviewer MCP server (whtan410/mcp_code_review). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.