apply_code_action · MCP-TY MCP: Risk & Policy

WHAT IT DOES

What apply_code_action does on MCP-TY

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

WHY IT NEEDS A POLICY

Why apply_code_action needs a policy

This tool modifies source code based on suggested actions from get_code_actions. While the changes are reversible (can be undone via version control or undo operations), it directly alters code content. The tool does not delete files or execute arbitrary commands, nor does it have financial impact.

From the tool's definition Tool name 'apply_code_action' and description 'Apply a code action by index' indicate modification of code. Code actions typically include refactorings, fixes, and edits that create or modify files reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_code_action Rate-limited

apply_code_action 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_code_action": {
      "limits": [
        {
          "counter": "apply_code_action_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-TY, so you can run agents against it safely.

FAQ

Questions about apply_code_action

What does the apply_code_action tool do? +

Apply a code action by index (from get_code_actions). It is categorised as a Write tool in the MCP-TY 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_code_action? +

Register the MCP-TY MCP server in PolicyLayer and add a rule for apply_code_action: 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-TY. Nothing to install.

What risk level is apply_code_action? +

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

Can I rate-limit apply_code_action? +

Yes. Add a rate_limit block to the apply_code_action 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_code_action completely? +

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

apply_code_action is provided by the MCP-TY MCP server (qinsehm1128/mcp-ty). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.