Skills/npm/mcp-server

mcp-server@1.41.0

VERIFIED· startup only

Publisher claims: "MCP server for LionChat API — 547 tools + 10 resources + 9 prompts. Audit-log aware, completion API, progress notifications." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher lionchat · publishing for 217 daysInstalls 2,418Last detonated 22 min ago
$claude mcp add mcp-server -- npx -y @lionchat/mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials
Needs
LIONCHAT_API_TOKEN, YOUR_TOKEN — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

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
LIONCHAT_API_TOKENConfiguration, not credentials: LIONCHAT_ACCOUNT_ID, LIONCHAT_BASE_URL, LIONCHAT_CATEGORIES, LIONCHAT_INCLUDE_PUBLIC_API, LIONCHAT_MCP_MAX_RESPONSE, LIONCHAT_MCP_VERSION
Where it talks to
lionchat.com.br (its own)Also site.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names site.com as well as its own vendor. The guard injects LIONCHAT_API_TOKEN only into requests to lionchat.com.br (and its subdomains) and refuses the rest.

$vet-skills run --secrets LIONCHAT_API_TOKEN=lionchat.com.br -- npx -y @lionchat/mcp-server

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

What changed since 1.39.0

vet-skills diff mcp-server 1.39.0 1.41.0

This version reaches for something 1.39.0 did not: 1 new host (site.com). Compared from the two recorded runs, not from source.

New hosts
site.com

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; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 85/100 (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 (it asks for LIONCHAT_API_TOKEN, YOUR_TOKEN); 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 · 47 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
6.8sprocessdependency install exit 0
27sprocessrelaunched with a decoy LIONCHAT_API_TOKEN, YOUR_TOKEN (tagged; nothing real)
47sclaimedstartup only: exited before answering, asking for LIONCHAT_API_TOKEN, YOUR_TOKEN (a decoy value was refused)
47sprocessscript backend runs setup only
47sprocessno install scripts to re-run

Static findings

MEDIUM
MCP server using network transport (SSE/HTTP)dist/prompts.js:74 · MCP server using network transport (SSE/HTTP) — data sent over network// McpServer.server expoe o Server pra esses casos. Tambem anuncia capability completionsFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Destructive file system command detecteddist/client.js:106 · Destructive file system command detected// AIDEV-NOTE: Normalize LionChat API responses to a consistent formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/resources.js:95 · npx invocation of non-well-known package — may execute untrusted code// Tenta multiplos layouts pra cobrir build local, npm/npx e source.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandpackage.json:11 · File permission modification command — agent changes file ownership/permissions"build": "tsc && npm run copy-docs && chmod +x dist/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actiondist/sanitize.js:15 · File type combined with upload action — agent may exfiltrate local data files// _account.json.jbuilder (topsend_api_key, liontrack_token), _user.json.jbuilder (access_token).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈69 tok
1 file · 49 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

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