Skills/npm/loopctl-mcp-server

loopctl-mcp-server@3.17.1

VERIFIED· install only

Publisher claims: "MCP server for loopctl — structural trust for AI development loops" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher mkreyman · publishing for 231 daysInstalls 2,800Last detonated 37 min ago
$claude mcp add loopctl-mcp-server -- npx -y loopctl-mcp-server
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 30 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
LOOPCTL_API_KEYConfiguration, not credentials: ESCALATIONS_PATH, HANDOFF_KEY_PREFIX, LOOPCTL_AGENT_KEY, LOOPCTL_ORCH_KEY, LOOPCTL_SERVER, LOOPCTL_USER_KEY, RUNNERS_PATH, SOURCES_PATH, TUNING_DRAFTS_PATH
Where it talks to
loopctl.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard. It asks for LOOPCTL_API_KEY and talks to loopctl.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets LOOPCTL_API_KEY=loopctl.com -- npx -y loopctl-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 3.13.1

vet-skills diff loopctl-mcp-server 3.13.1 3.17.1

In the sandbox, this version reached for nothing 3.13.1 did not. Compared from the two recorded runs, not from source.

No longer contacted
example.internal

3.17.1 was run less far than 3.13.1 (install only vs full); behavior past startup is not compared. Only one of the two runs produced a tool list; tools are not compared.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.6sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.7sprocess8 of 30 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.7sprocessscript backend runs setup only
0.7sprocessscript backend runs setup only
0.7sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathslib/payload-path.js:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// so a symlink named x.json cannot point at /etc/passwd or /procFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagelib/claim-session.js:15 · npx invocation of non-well-known package — may execute untrusted code* process-lifetime id, every npx respawn or `/mcp` reconnect turns the session's OWN liveFix: Pin versions and sources; vendor anything fetched at install time.
AST06
LOW
Refusal suppressionREADME.md:538 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction file…he declared prefixes. A retry carrying a `dispatch_id` loopctl already holds is never refused for either prefix reason: its claim is already standing, so the declaration on…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈56 tok
1 file · 34 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.