Skills/npm/mcp

mcp@10.14.5

VERIFIED

Publisher claims: "Model Context Protocol server for the FerrLabs platform (orgs, projects, subscriptions, docs, tokens, public stats)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ferrlabs · publishing for 179 daysInstalls 2,587Last detonated 4d ago
$claude mcp add mcp -- npx -y @ferrlabs/mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
ferrlabs.com (its own)Also ferrflow.com, ferrvault.com, ferrtrack.com, ferrgrowth.com, ferrfleet.com, ferrlens.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it under the guard; read the third-party hosts first. The code names ferrflow.com, ferrvault.com, ferrtrack.com, ferrgrowth.com, ferrfleet.com, ferrlens.com as well as its own vendor. The guard pins the network to the hosts the honeypot saw.

$vet-skills run --net declared -- npx -y @ferrlabs/mcp

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

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-10 and scored it 85/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 24 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.2sprocessdependency install exit 0
24sfilesystemread ~/.config/ferrlabs/mcp/token.json outside project
24sprocessexec /app/apps/web/node_modules/.bin/xdg-open
24sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/xdg-open
24sprocessexec /app/node_modules/.bin/xdg-open
24sprocessexec /pnpm/xdg-open
24sprocessexec /usr/local/sbin/xdg-open
24sprocessexec /usr/local/bin/xdg-open
24sprocessexec /usr/sbin/xdg-open
24sprocessexec /usr/bin/xdg-open
24sprocessexec /sbin/xdg-open
24sprocessexec /bin/xdg-open
24sclaimed37 tools: get_stats, health_check, get_me, list_tokens, create_token, revoke_token, list_org_tokens, create_org_token, revoke_org_token, list_orgs, list_projects, get_org, update_org, get_org_overview, get_org_usage, list_org_audit, list_org_members, invite_org_member, update_org_member_role, remove_org_member, list_teams, create_team, update_team, delete_team, add_team_member
24sprocessscript backend runs setup only
24sprocessno install scripts to re-run

Static findings

MEDIUM
Access to sensitive file pathsdist/tools/__tests__/docs.test.js:71 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesexpect(() => buildDocUrl('ferrflow', '../../etc/passwd')).toThrow(/invalid slug/);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

No other findings across 1,859 lines in 41 files.

Cost to the agent

Instructions loaded
≈64 tok
1 file · 41 in bundle
Tool list per prompt
≈4,325 tok
37 tools · 117 per tool
Handshake
579 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 109

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for @ferrlabs/mcp@10.14.5 as of 4d ago. This is the package itself, not its dependencies.