ember_learn_from_correction · Agent Runtime MCP

WHAT IT DOES

What ember_learn_from_correction does on Agent Runtime

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

WHY IT NEEDS A POLICY

Why ember_learn_from_correction needs a policy

This tool modifies the AI agent's internal model or guidance parameters based on user corrections. It is a Write operation because it updates persistent state (Ember's learned behavior/assessments) in a reversible or incremental way. Severity is medium because misuse could subtly degrade the AI's future decision-making quality by feeding it incorrect corrections, affecting downstream multi-agent pipeline behavior.

From the tool's definition 'Tell Ember when you corrected/overrode its assessment. This helps Ember learn and improve future guidance.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ember_learn_from_correction Rate-limited

ember_learn_from_correction 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": {
    "ember_learn_from_correction": {
      "limits": [
        {
          "counter": "ember_learn_from_correction_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 Agent Runtime, so you can run agents against it safely.

FAQ

Questions about ember_learn_from_correction

What does the ember_learn_from_correction tool do? +

Tell Ember when you corrected/overrode its assessment. This helps Ember learn and improve future guidance. It is categorised as a Write tool in the Agent Runtime MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on ember_learn_from_correction? +

Register the Agent Runtime MCP server in PolicyLayer and add a rule for ember_learn_from_correction: 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 Agent Runtime. Nothing to install.

What risk level is ember_learn_from_correction? +

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

Can I rate-limit ember_learn_from_correction? +

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

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

ember_learn_from_correction is provided by the Agent Runtime MCP server (marc-shade/agent-runtime-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.