loopctl-mcp-server@3.17.1
VERIFIED· install onlyPublisher claims: "MCP server for loopctl — structural trust for AI development loops" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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.
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 3.17.1In 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 deviationsStatic findings
// 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.* 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.…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.Cost to the agent
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.