knitbrain_skill_save · Knitbrain MCP: Risk & Policy

WHAT IT DOES

What knitbrain_skill_save does on Knitbrain

AI agents use knitbrain_skill_save 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_skill_save needs a policy

This tool creates or updates skill definitions within the system's local-first memory store. While reversible (updates rather than deletes), it modifies persistent project-specific data. The 'Write' category applies because the tool creates or modifies data without destructive deletion.

From the tool's definition Tool description states "Persist a refined skill playbook" and "Same name updates the skill", indicating creation and modification of data structures (skill playbooks) that persist in the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

knitbrain_skill_save Rate-limited

knitbrain_skill_save 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_skill_save": {
      "limits": [
        {
          "counter": "knitbrain_skill_save_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_skill_save

What does the knitbrain_skill_save tool do? +

Persist a refined skill playbook (telegraphic). Same name updates the skill — skills compound across tasks. 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_skill_save? +

Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_skill_save: 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_skill_save? +

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

Can I rate-limit knitbrain_skill_save? +

Yes. Add a rate_limit block to the knitbrain_skill_save 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_skill_save completely? +

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

knitbrain_skill_save 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.