All servers · AI models & agents

Loop Breaker

com.botrecipe/loop · v1.0.0

Instruction-like text in descriptions

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Not declared (tools carry no read/destructive hints)
Capabilities declared	tools
Tool definitions	4 tools · with description 100% · input schema is an object 100% · read/destructive hints 0%

Instruction-like text was found in check_step. This is a pattern match, not a verdict. What we look for

Catch AI agent loops: halt runs that repeat the same failing step or tool call.

streamable-http · https://loop.cloudforbots.com/mcp

claude mcp add --transport http loop https://loop.cloudforbots.com/mcp

{
  "mcpServers": {
    "loop": {
      "url": "https://loop.cloudforbots.com/mcp"
    }
  }
}

check_step
Call AFTER each tool call or agent step with what you just did and whether it failed. Loop Breaker fingerprints the call (tool + normalized args + error) and returns verdict ok, loop_detected or halted. Pro: on a loop, halt=true; stop the run, do not retry, and tell your user what repeated. Free wat
loop_status
Show a run's loops so far, whether it is halted, and its last 10 steps.
weekly_report
Draft a plain-English report of the last 7 days for your key (or IP): runs, loops caught, wasted repeat steps, and the worst offenders. Read-only; sends nothing. Show it to your user.
usage_and_upgrade
Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.com/offer). Free tier: 500 calls/day. Not metered.

Website · JSON · Text for agents · Registry updated 2026-10-15