knitbrain_run · Knitbrain MCP: Risk & Policy

WHAT IT DOES

What knitbrain_run does on Knitbrain

AI agents invoke knitbrain_run to trigger actions in Knitbrain. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why knitbrain_run needs a policy

This is an orchestrator/executor that classifies tasks, proposes agents, and issues directives that control downstream agent behavior and execution. While it gathers context via 'context meter' and searches via sibling tools, the core function is orchestrating and triggering agent-based actions in response to user tasks.

From the tool's definition Tool description states it 'proposes guardrailed agents', 'Classifies' tasks, 'finds-or-drafts the SKILL', and directs users to 'Follow the returned directive.' The phrase 'call FIRST when the user states a task' and orchestration of agents indicates this…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

knitbrain_run Rate-limited

knitbrain_run stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_run": {
      "limits": [
        {
          "counter": "knitbrain_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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_run

What does the knitbrain_run tool do? +

THE feedback/orchestrator tool — call FIRST when the user states a task. Classifies it (small→big), finds-or-drafts the SKILL for it, proposes guardrailed agents when multi-domain, lists host slash-commands the agent can run itself, and reports the context meter. Follow the returned directive. It is categorised as a Execute tool in the Knitbrain MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on knitbrain_run? +

Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_run: 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_run? +

knitbrain_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit knitbrain_run? +

Yes. Add a rate_limit block to the knitbrain_run 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_run completely? +

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

knitbrain_run 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.