knitbrain_record_learning · Knitbrain MCP: Risk & Policy

WHAT IT DOES

What knitbrain_record_learning does on Knitbrain

AI agents use knitbrain_record_learning 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_record_learning needs a policy

This tool writes/creates a new learning record (summary, lesson, tags) to persistent project memory. It is a reversible data creation operation with no code execution, deletion, or financial implications. Misuse risk is low as it only stores metadata/notes about project learnings.

From the tool's definition Record a non-obvious project learning (summary + lesson + tags) for future sessions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

knitbrain_record_learning Rate-limited

knitbrain_record_learning 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_record_learning": {
      "limits": [
        {
          "counter": "knitbrain_record_learning_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_record_learning

What does the knitbrain_record_learning tool do? +

Record a non-obvious project learning (summary + lesson + tags) for future sessions. 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_record_learning? +

Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_record_learning: 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_record_learning? +

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

Can I rate-limit knitbrain_record_learning? +

Yes. Add a rate_limit block to the knitbrain_record_learning 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_record_learning completely? +

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

knitbrain_record_learning 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.