mcp-server@1.1.20
VERIFIEDPublisher 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.
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.
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 1.1.20This 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 deviationsStatic findings
* 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.No other findings across 3,879 lines in 40 files.
Cost to the agent
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.