knitbrain_learning_outcome · Knitbrain MCP: Risk & Policy

WHAT IT DOES

What knitbrain_learning_outcome does on Knitbrain

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

WHY IT NEEDS A POLICY

Why knitbrain_learning_outcome needs a policy

The tool writes feedback/outcome data about a recalled learning back to the system, updating its memory or model. This is a reversible data write (logging an outcome). No code execution, deletion, or financial action is involved. Severity is low because the blast radius of misuse is minimal — at worst it corrupts a learning record.

From the tool's definition 'Close the loop on a recalled learning: report whether it actually HELPED on this task' — this records/writes an outcome or feedback signal back to the system

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

knitbrain_learning_outcome Rate-limited

knitbrain_learning_outcome 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": {
    "knitbrain_learning_outcome": {
      "limits": [
        {
          "counter": "knitbrain_learning_outcome_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 Knitbrain, so you can run agents against it safely.

FAQ

Questions about knitbrain_learning_outcome

What does the knitbrain_learning_outcome tool do? +

Close the loop on a recalled learning: report whether it actually HELPED on this task (a concrete outcome, not. It is categorised as a Write tool in the Knitbrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on knitbrain_learning_outcome? +

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

What risk level is knitbrain_learning_outcome? +

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

Can I rate-limit knitbrain_learning_outcome? +

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

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

knitbrain_learning_outcome is provided by the Knitbrain MCP server (pdgit12/knitbrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.