apply_codemod

Structural (AST-aware) or regex find-and-replace across files. Default engine

SERVERTrace SOURCEnikolai-vysotskyi/trace-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/nikolai-vysotskyi-trace-mcp/apply-codemod.md

WHAT IT DOES

What apply_codemod does on Trace

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

RISK

Why apply_codemod is rated Medium

This tool creates or modifies code files reversibly through find-and-replace operations. While the changes could theoretically be undone (version control), the tool itself performs write operations that alter source files. It is not Destructive because it doesn't irreversibly delete data—replacements preserve file structure and are versionable.

From the tool's definition Tool performs 'find-and-replace across files' which modifies source code content. The description explicitly states it applies structural transformations via AST or regex patterns, making it a code modification operation.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs apply_codemod safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Trace, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For apply_codemod, this is the rule to start with:

apply_codemod Rate-limited

apply_codemod 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_codemod": {
      "limits": [
        {
          "counter": "apply_codemod_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Trace, apply this rule, and every apply_codemod call is checked against it from then on.

FAQ

Questions about apply_codemod

What does the apply_codemod tool do? +

Structural (AST-aware) or regex find-and-replace across files. Default engine. It is categorised as a Write tool in the Trace 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_codemod? +

Register the Trace MCP server in PolicyLayer and add a rule for apply_codemod: 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 Trace. Nothing to install.

What risk level is apply_codemod? +

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

Can I rate-limit apply_codemod? +

Yes. Add a rate_limit block to the apply_codemod 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_codemod completely? +

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

apply_codemod is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Trace, and thousands of servers like it.

This server

All 191 Trace tools →

Across the catalogue

binary_patch_apply on 010 Editor → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →