knitbrain_skill_outcome · Knitbrain MCP: Risk & Policy

WHAT IT DOES

What knitbrain_skill_outcome does on Knitbrain

AI agents use knitbrain_skill_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_skill_outcome needs a policy

The tool updates the server's per-project memory by recording the result of a skill execution. This is a write operation (persisting outcome data) with low blast radius since it only affects internal memory/learning records and is likely reversible or inconsequential if misused. The description is partially truncated, which slightly lowers confidence.

From the tool's definition 'Close the loop on a skill: report whether it actually WORKED after using it' — this records/writes an outcome back to the system's memory or skill tracking

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

knitbrain_skill_outcome Rate-limited

knitbrain_skill_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_skill_outcome": {
      "limits": [
        {
          "counter": "knitbrain_skill_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_skill_outcome

What does the knitbrain_skill_outcome tool do? +

Close the loop on a skill: report whether it actually WORKED after using it (a test passing, a bug fixed — 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_skill_outcome? +

Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_skill_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_skill_outcome? +

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

Can I rate-limit knitbrain_skill_outcome? +

Yes. Add a rate_limit block to the knitbrain_skill_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_skill_outcome completely? +

Set action: deny in the PolicyLayer policy for knitbrain_skill_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_skill_outcome? +

knitbrain_skill_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.