wb_feedback · Workbench MCP: Risk & Policy

WHAT IT DOES

What wb_feedback does on Workbench

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

WHY IT NEEDS A POLICY

Why wb_feedback needs a policy

The tool creates or modifies feedback records that influence artifact approval decisions in a multi-stage pipeline. While it does not directly execute code or delete data, it writes feedback state that gates downstream actions (release/approval). This is a Write operation because feedback is recorded and reversible (can be updated).

From the tool's definition Tool records feedback signals (+1/-1) on artifacts/code products and appears to affect approval flows ('👍=放行' meaning thumbs up = release/approve). The description indicates this feedback modifies the state of prototypes/code within an approval pipeline.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wb_feedback Rate-limited

wb_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": {
    "wb_feedback": {
      "limits": [
        {
          "counter": "wb_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 Workbench, so you can run agents against it safely.

FAQ

Questions about wb_feedback

What does the wb_feedback tool do? +

对原型/代码产物记录 👍(+1)/👎(-1);👎 必附 comment;原型 👍=放行. It is categorised as a Write tool in the Workbench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on wb_feedback? +

Register the Workbench MCP server in PolicyLayer and add a rule for wb_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 Workbench. Nothing to install.

What risk level is wb_feedback? +

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

Can I rate-limit wb_feedback? +

Yes. Add a rate_limit block to the wb_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 wb_feedback completely? +

Set action: deny in the PolicyLayer policy for wb_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 wb_feedback? +

wb_feedback is provided by the Workbench MCP server (nvrenshiren/workbench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.