Autonomous goal loop (ONE cycle per call). Runs your verify_cmd as the REAL hard gate, tracks iteration across calls, and drives until the goal is met or max_iters. HONEST: the HOST AGENT does the actual work BETWEEN cycles — this tool does NOT edit code. Each call runs the verify gate; if not me...
AI agents invoke knitbrain_run_loop 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.
This tool executes arbitrary verification commands (verify_cmd) as a control loop, which constitutes Execute-category behavior. While the tool itself doesn't directly edit code, it controls and orchestrates autonomous execution loops that drive external agents through iterative cycles—this is an autonomous execution primitive. The verify_cmd parameter is user-supplied and could execute arbitrary checks/side effects.
From the tool's definition 'Autonomous goal loop' that 'Runs your verify_cmd as the REAL hard gate' and 'drives until the goal is met or max_iters'.
Attacks that exploit this kind of access
Autonomous goal loop (ONE cycle per call). Runs your verify_cmd as the REAL hard gate, tracks iteration across calls, and drives until the goal is met or max_iters. HONEST: the HOST AGENT does the actual work BETWEEN cycles — this tool does NOT edit code. Each call runs the verify gate; if not met it returns a per-cycle directive telling you to make the smallest fix and call again. Stops at grade-pass (met=true) or max_iters (met=false). 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.
Register the Knitbrain MCP server in PolicyLayer and add a rule for knitbrain_run_loop: 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.
knitbrain_run_loop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the knitbrain_run_loop 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.
Set action: deny in the PolicyLayer policy for knitbrain_run_loop. 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.
knitbrain_run_loop 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →