protogrid

Search / com.botrecipe/loop

Loop Breaker

R0· no sign-in

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

v1.0.0 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality73new
Trust83of 100
Uptime, 30 days100%
Latency p50202 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "loop": {
      "type": "http",
      "url": "https://loop.cloudforbots.com/mcp"
    }
  }
}
claude mcp add --transport http loop https://loop.cloudforbots.com/mcp
[mcp_servers.loop]
url = "https://loop.cloudforbots.com/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "loop": {
      "type": "remote",
      "url": "https://loop.cloudforbots.com/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "loop": {
      "type": "http",
      "url": "https://loop.cloudforbots.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=loop&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbG9vcC5jbG91ZGZvcmJvdHMuY29tL21jcCJ9"
}
{
  "servers": {
    "loop": {
      "type": "http",
      "url": "https://loop.cloudforbots.com/mcp"
    }
  }
}
{
  "mcpServers": {
    "loop": {
      "httpUrl": "https://loop.cloudforbots.com/mcp"
    }
  }
}
extensions:
  "loop":
    enabled: true
    name: "loop"
    type: streamable_http
    uri: "https://loop.cloudforbots.com/mcp"
    timeout: 300

Quality 73 / 100new

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: loop_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); weekly_report (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_step (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
  • pass
    tools.token_costabout 498 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history recorded for 3 of the 7 days needed
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

4 tools, about 498 tokens to load them all · tool set 7139fdcaead3 · tools last changed 2026-10-16 · checked 2026-10-19 10:52 UTC

Tool changes

  • usage_and_upgradechangeddescription
    before

    Show today's usage for your key or IP and the $9/month upgrade link. Free tier: 500 calls/day. Not metered.

    after · 75% of words in common

    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.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository
provenance55
liveness100
freshness100
hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-4d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://loop.cloudforbots.com/mcp streamable-httpnoneyes100%202 ms2025-11-252026-10-19

Tools (4)

check_stepCall 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 watch-only: never halts, returns would_halt and logs it for the weekly report.
loop_statusShow a run's loops so far, whether it is halted, and its last 10 steps.
usage_and_upgradeShow 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.
weekly_reportDraft 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.

Schemas: list_tools.

Similar MCP servers

More from com.botrecipe

And 8 more from this publisher.

Official server.json
{
  "name": "com.botrecipe/loop",
  "title": "Loop Breaker",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://loop.cloudforbots.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://loop.cloudforbots.com",
  "description": "Catch AI agent loops: halt runs that repeat the same failing step or tool call."
}