feedback_comment · Feedbucket MCP Server MCP: Risk & Policy

WHAT IT DOES

What feedback_comment does on Feedbucket MCP Server

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

WHY IT NEEDS A POLICY

Why feedback_comment needs a policy

The feedback_comment tool creates new comment records on feedback items. While comments are typically non-destructive and easily removable, this is fundamentally a write operation that modifies the feedback item's state by appending new data. The blast radius is low since comments are generally informational and can be deleted or edited without cascading consequences.

From the tool's definition Tool description states 'Add a comment to a specific feedback item' - the verb 'add' indicates creation of new data (a comment). This is a reversible modification operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

feedback_comment Rate-limited

feedback_comment 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": {
    "feedback_comment": {
      "limits": [
        {
          "counter": "feedback_comment_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 Feedbucket MCP Server, so you can run agents against it safely.

FAQ

Questions about feedback_comment

What does the feedback_comment tool do? +

Add a comment to a specific feedback item to ask for clarification or provide updates. It is categorised as a Write tool in the Feedbucket MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on feedback_comment? +

Register the Feedbucket MCP Server MCP server in PolicyLayer and add a rule for feedback_comment: 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 Feedbucket MCP Server. Nothing to install.

What risk level is feedback_comment? +

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

Can I rate-limit feedback_comment? +

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

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

feedback_comment is provided by the Feedbucket MCP Server MCP server (swiftcomza/feedbucket-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.