mcp-server@0.57.0
VERIFIEDPublisher claims: "MCP server for Clipwright: generate UGC videos from your coding agent" Observed in sandbox: calls api.clipwright.io only, touches nothing outside the project, writes no memory.
Coverage
Started with a decoy CLIPWRIGHT_API_KEY; tool list observed. Tool calls with a real credential not tested.- Tested
- server startup with a tagged decoy in CLIPWRIGHT_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
- CLIPWRIGHT_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
CLIPWRIGHT_API_KEYConfiguration, not credentials: CLIPWRIGHT_API_URL- Where it talks to
- no vendor host named in the codeAlso unused.invalid — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · reached only api.clipwright.io (its own)
- What we could not test
- what the tools do when called with a real credential
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names unused.invalid as well as its own vendor. The guard injects CLIPWRIGHT_API_KEY only into requests to clipwright.io (and its subdomains) and refuses the rest.
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 2026-11-13 and scored it 89/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: calls api.clipwright.io only, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 47 s · 2 scenarios · 0 deviationsStatic findings
| VS Code | `.mcp.json`: `{"mcpServers": {"clipwright": {"type": "http", "url": "https://mcp.clipwright.io/mcp"}}}` | from the client's docs |Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.-- npx -y -p @clipwright/mcp-server@latest clipwright-mcpFix: Pin versions and sources; vendor anything fetched at install time.npx -y -p @clipwright/mcp-server@latest clipwright-mcpFix: Pin versions and sources; vendor anything fetched at install time.| Cursor | `~/.cursor/mcp.json`: `{"mcpServers": {"clipwright": {"url": "https://mcp.clipwright.io/mcp"}}}` | from the client's docs |Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.…KE_UGC_AGENT_PROTOCOL, MAKE_FACELESS_DESCRIPTION, MAKE_FACELESS_AGENT_PROTOCOL, mcpServerInstructions, makeFacelessInput, offeredFacelessInput, REVISION_CHARGE_TEXT, revisionRequest, UPLOAD_IMAGE_DESCRIPTION, UPLOAD_MAX_BYTES, UPLOAD_MEDIA…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.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 @clipwright/mcp-server@0.57.0 as of 26 h ago. This is the package itself, not its dependencies.