codebrain_polish · CodeBrain MCP: Risk & Policy

WHAT IT DOES

What codebrain_polish does on CodeBrain

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

WHY IT NEEDS A POLICY

Why codebrain_polish needs a policy

The tool performs code modifications (polishing/refining), which creates or modifies data reversibly. This is a Write operation. Severity is medium because unintended code modifications could degrade functionality, but changes are typically reversible. Confidence is moderate (0.7) due to the empty tool description, relying on inference from the server context and tool name.

From the tool's definition Tool name 'codebrain_polish' implies modifying or refining code. Server description states it handles 'code polishing' which modifies existing code. No description provided for the specific tool.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codebrain_polish Rate-limited

codebrain_polish 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": {
    "codebrain_polish": {
      "limits": [
        {
          "counter": "codebrain_polish_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 CodeBrain, so you can run agents against it safely.

FAQ

Questions about codebrain_polish

What does the codebrain_polish tool do? +

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

How do I enforce a policy on codebrain_polish? +

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

What risk level is codebrain_polish? +

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

Can I rate-limit codebrain_polish? +

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

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

codebrain_polish is provided by the CodeBrain MCP server (tschonsen/codebrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.