Skills/npm/mcp-server

mcp-server@0.73.0

VERIFIED

Publisher 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.

Registry npm (MCP server)Publisher clipwright · publishing for 117 daysInstalls 11,155Last detonated 19 min ago
$claude mcp add mcp-server -- npx -y @clipwright/mcp-server
WatchReport an issue

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 we saw when it ran
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.

$vet-skills run --secrets CLIPWRIGHT_API_KEY=clipwright.io -- npx -y @clipwright/mcp-server

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

What changed since 0.69.0

vet-skills diff mcp-server 0.69.0 0.73.0

This version reaches for something 0.69.0 did not: 2 new tools (quote_upscale, upscale) · 14 rewritten tool descriptors (analyze_reference, create_actor, create_candidate, delete_run_media, …). Compared from the two recorded runs, not from source.

New tools
quote_upscale, upscale
Rewritten tool descriptors
analyze_reference, create_actor, create_candidate, delete_run_media, find_trends, generate_image, generate_video, list_voices, make_faceless, make_ugc, plan_reference_remake, quote_faceless +2

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 2026-11-21 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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
7.2sprocessdependency install exit 0
27sprocessrelaunched with a decoy CLIPWRIGHT_API_KEY (tagged; nothing real)
47snetworkCONNECT tcp://api.clipwright.io:443
47snetworkCONNECT tcp://api.clipwright.io:443
47sclaimed60 tools with a decoy CLIPWRIGHT_API_KEY: list_workflows, get_workflow, prepare_workflow_plan, plan_reference_remake, get_workflow_plan, approve_workflow_plan, quote_workflow_plan, run_workflow_plan, make_ugc, get_run, get_run_shots, delete_run_media, quote_revision, revise_run, quote_candidate, create_candidate, list_generation_models, quote_image, generate_image, quote_video, generate_video, quote_upscale, upscale, quote_ugc, upload_image
47stools1741849627adfc52
47stoolsc8e2af1d228c6c32
47stools6328467b21127e0a
47stools2192a5402ae5c92a
47stools75f408cd69fe171e
47stoolsa9f22348b4fce270
47stoolsf7ef397fbdcb3364
47stools295f69600f429223
47stoolsbc5e0109dbe9606f
47stools99b0b06098b15966
47stools5ba4f8eb4e0e9959
47stools4981badce921d114
47stools9fde0c961b48f3bc
47stools5bb31da8effb4b13
47stoolsf9d4bd584bc09a48
47stoolsac6218b77caed628
47stoolsed6cd8c5b7fc8150
47stools392e14ec63f5544b
47stools4bb60dc87e4a0141
47stools0a61d6fc7f1fdf60
47stools7279c6729dfabab8
47stoolscae9871e3e8cd992
47stoolscad857ec395d1c5e
47stoolsd5618684a59683fa
47stoolsf6ece5142e32c7d8
47stools13f1e4ac414b1330
47stoolse80994443dd7249a
47stools2a59165e1d908627
47stoolsedcc17d511574846
47stools3525bcca53d82206
47stoolsbaf9a0d2a8415c20
47stools9e435199e2e97f67
47stools5737ff7d88d2f1c8
47stoolsb8c293f90a1383a6
47stools6301421cd8040720
47stoolsba83a87c6ab57ac8
47stoolsefd9d9cf1a90b7e9
47stools7dc48b80eca0cec2
47stoolsff255acdb3923f2c
47stools02417d2e0d08f2c0
47stoolsb95983b391330c91
47stools62e50b58c849df0c
47stoolsb85ec71659f471c6
47stools03c5cf4828332cdc
47stoolsfe8f8be8b2285d5b
47stoolsa7447afeebaddb84
47stools3fd430b0971a8768
47stools03e24eea32a0f285
47stools1ceec12c62c88a42
47stools9de11583f82935f1
47stools1baebdfbb6128eae
47stoolsfc4cbb79bf4dbb7a
47stools2fc6e7a909fba746
47stools64f7105fbe489cdc
47stools553f9780e1c1a8e7
47stoolsb6b714ad3defe921
47stools6c1b60236dd55b2b
47stoolsd7696c707da46e17
47stools9fc915c097ecbc99
47stoolse3adec4432ba1d17
47sprocessscript backend runs setup only
47sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageSKILL.md:196 · npx invocation of non-well-known package — may execute untrusted code-- npx -y -p @clipwright/mcp-server@latest clipwright-mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)dist/server.js:6 · MCP server using network transport (SSE/HTTP) — data sent over network…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.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)SKILL.md:142 · MCP server using network transport (SSE/HTTP) — data sent over network| 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.
AST04
MEDIUM
npx invocation of non-well-known packageSKILL.md:158 · npx invocation of non-well-known package — may execute untrusted codenpx -y -p @clipwright/mcp-server@latest clipwright-mcpFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)SKILL.md:143 · MCP server using network transport (SSE/HTTP) — data sent over network| 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.
AST04

Cost to the agent

Instructions loaded
≈9,479 tok
1 file · 26 in bundle
Tool list per prompt
≈18,595 tok
60 tools · 310 per tool
Handshake
3005 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 325

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.