Skills/npm/mcp-server

mcp-server@1.1.20

VERIFIED

Publisher claims: "MCP server for Ssemble AI Clipping — create viral short-form videos from any AI assistant. Webhook callbacks for n8n, Zapier, and Make automation." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher ssemble · publishing for 240 daysInstalls 2,917Last detonated 14 h ago
$claude mcp add mcp-server -- npx -y @ssemble/mcp-server
WatchReport an issue

Coverage

Started with a decoy SSEMBLE_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in SSEMBLE_API_KEY · MCP initialize and tools/list · every tool description, for hidden instructions · where the decoy credential went · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with a real credential
Needs
SSEMBLE_API_KEY — 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.

Before you give it your token

It will ask for
SSEMBLE_API_KEYConfiguration, not credentials: MCP_PORT, SSEMBLE_API_BASE_URL
Where it talks to
ssemble.com (its own)
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with a real credential

Connect it with a scoped credential, under the guard. It asks for SSEMBLE_API_KEY and talks to ssemble.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.

$vet-skills run --secrets SSEMBLE_API_KEY=ssemble.com -- npx -y @ssemble/mcp-server

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

What changed since 1.1.19

vet-skills diff mcp-server 1.1.19 1.1.20

This version reaches for something 1.1.19 did not: 1 rewritten tool descriptor (create_short). Compared from the two recorded runs, not from source.

Rewritten tool descriptors
create_short

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) on 2026-11-19 and scored it 93/100 (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 · 48 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.4sprocessdependency install exit 0
27sprocessrelaunched with a decoy SSEMBLE_API_KEY (tagged; nothing real)
47sclaimed10 tools with a decoy SSEMBLE_API_KEY: create_short, get_status, get_shorts, list_requests, delete_request, list_templates, list_music, list_game_videos, list_meme_hooks, list_posts
47stools056b57fc0c2943f1
47stools8df7033dae35264f
47stools43878ddec69034a4
47stoolsc3c81e3a1fd9a8be
47stools084c0c4d4f489e64
47stools53289f5ca40852d0
47stoolse5336cf8c0392a20
47stoolse24491cafebe7bcd
47stoolscf8e0cf236b8a9d3
47stools4d097017a0c132cb
47sprocessscript backend runs setup only
47sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagesrc/transports/stdio.js:4 · npx invocation of non-well-known package — may execute untrusted code* Stdio transport — entry point for local usage via npx or Claude Desktop/Code config.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 3,879 lines in 40 files.

Cost to the agent

Instructions loaded
≈74 tok
1 file · 40 in bundle
Tool list per prompt
≈3,518 tok
10 tools · 352 per tool
Handshake
760 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 139

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 @ssemble/mcp-server@1.1.20 as of 14 h ago. This is the package itself, not its dependencies.

mcp-server@1.1.20 safety verdict: Verified — KillerSkills