knitbrain_create_agent · Knitbrain MCP: Risk & Policy

WHAT IT DOES

What knitbrain_create_agent does on Knitbrain

AI agents use knitbrain_create_agent 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_create_agent needs a policy

This tool creates new agent configuration files, which is a reversible write operation. While it modifies project structure and could indirectly affect system behavior through agent definitions, the action itself is write-level (creating new .md files).

From the tool's definition Tool description states it will "Generate a project-specific subagent (.claude/agents/<name>.md)" which involves creating new files in the .claude/agents directory.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

knitbrain_create_agent Rate-limited

knitbrain_create_agent 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_create_agent": {
      "limits": [
        {
          "counter": "knitbrain_create_agent_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_create_agent

What does the knitbrain_create_agent tool do? +

Generate a project-specific subagent (.claude/agents/<name>.md) with 4 guardrails: file scope, allowed-tools, optional review gate, context budget. 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_create_agent? +

Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_create_agent: 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_create_agent? +

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

Can I rate-limit knitbrain_create_agent? +

Yes. Add a rate_limit block to the knitbrain_create_agent 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_create_agent completely? +

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

knitbrain_create_agent 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.