save_cli_feedback · Codecks MCP: Risk & Policy

WHAT IT DOES

What save_cli_feedback does on Codecks

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

WHY IT NEEDS A POLICY

Why save_cli_feedback needs a policy

This tool creates and persists new feedback records in the system. While reversible (feedback can presumably be deleted or modified), it modifies the server state by adding new data. The 'save' action indicates data creation rather than retrieval. Severity is medium because feedback submission has limited blast radius—it doesn't delete data, execute arbitrary code, or trigger financial transactions.

From the tool's definition The tool description states 'Save a CLI feedback item' which is a create/write operation that stores new feedback data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_cli_feedback Rate-limited

save_cli_feedback 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": {
    "save_cli_feedback": {
      "limits": [
        {
          "counter": "save_cli_feedback_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 Codecks, so you can run agents against it safely.

FAQ

Questions about save_cli_feedback

What does the save_cli_feedback tool do? +

Save a CLI feedback item for the development team. No auth needed. It is categorised as a Write tool in the Codecks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_cli_feedback? +

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

What risk level is save_cli_feedback? +

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

Can I rate-limit save_cli_feedback? +

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

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

save_cli_feedback is provided by the Codecks MCP server (rangogamedev/codecks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.