ethics_learn · Ethics Check MCP: Risk & Policy

WHAT IT DOES

What ethics_learn does on Ethics Check MCP

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

WHY IT NEEDS A POLICY

Why ethics_learn needs a policy

The tool logs/records ethical concerns and learns from past interactions, which constitutes writing/creating data (logs, learned patterns). It does not execute code, delete data, or involve financial transactions. The description is truncated, slightly lowering confidence, but 'log and learn' clearly implies persisting data. Blast radius is low as it only stores ethical concern records.

From the tool's definition 'ETHICAL CONCERN LOGGING - Call this tool to log and learn from identified ethical concerns'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ethics_learn Rate-limited

ethics_learn 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": {
    "ethics_learn": {
      "limits": [
        {
          "counter": "ethics_learn_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 Ethics Check MCP, so you can run agents against it safely.

FAQ

Questions about ethics_learn

What does the ethics_learn tool do? +

📚 ETHICAL CONCERN LOGGING - Call this tool to log and learn from identified ethical concerns. USE WHEN: (1) You. It is categorised as a Write tool in the Ethics Check MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ethics_learn? +

Register the Ethics Check MCP server in PolicyLayer and add a rule for ethics_learn: 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 Ethics Check MCP. Nothing to install.

What risk level is ethics_learn? +

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

Can I rate-limit ethics_learn? +

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

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

ethics_learn is provided by the Ethics Check MCP server (r-huijts/ethics-check-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.