Skills/npm/mandarinclips-mcp

mandarinclips-mcp@1.1.0

VERIFIED

Publisher claims: "Search 180,000+ authentic Chinese cinema clips, HSK grammar, and expressions for TCSL educators." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher mandarinclips · publishing for 22 daysInstalls 0Last detonated 3d ago
$claude mcp add mandarinclips-mcp -- npx -y mandarinclips-mcp
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
MANDARINCLIPS_API_KEYConfiguration, not credentials: MANDARINCLIPS_API_BASE, MANDARINCLIPS_PATREON_URL, MANDARINCLIPS_WEB_BASE
Where it talks to
mandarinclips.com (its own)Also patreon.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
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 patreon.com as well as its own vendor. The guard injects MANDARINCLIPS_API_KEY only into requests to mandarinclips.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets MANDARINCLIPS_API_KEY=mandarinclips.com -- npx -y mandarinclips-mcp

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 2026-11-11 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 · 26 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.9sprocessdependency install exit 0
26sclaimed5 tools: search_cinema_clips, get_grammar_guide, get_expression_guide, get_hsk_vocabulary, get_word_detail
26sprocessscript backend runs setup only
26sprocessno install scripts to re-run

Static findings

No findings across 438 lines in 4 files.

Cost to the agent

Instructions loaded
≈72 tok
1 file · 4 in bundle
Tool list per prompt
≈473 tok
5 tools · 95 per tool
Handshake
486 ms
launch to tools/list, stdio
Undocumented tools
5
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

No advisories in OSV for mandarinclips-mcp@1.1.0 as of 3d ago. This is the package itself, not its dependencies.