Skills/npm/doubao-vision-mcp-server

doubao-vision-mcp-server@1.1.1

VERIFIED

Publisher claims: "MCP server for Doubao vision models via Volcengine Ark API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher kira4094 · publishing for 156 daysInstalls 1,130Last detonated 28 min ago
$claude mcp add doubao-vision-mcp-server -- npx -y doubao-vision-mcp-server
WatchReport an issue

Coverage

Started with a decoy ARK_API_KEY; tool list observed. Tool calls with a real credential not tested.
Tested
server startup with a tagged decoy in ARK_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
ARK_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
API_KEYARK_API_KEYConfiguration, not credentials: DOUBAO_BASE_URL, DOUBAO_MODEL, SEEDANCE_MODEL, SEEDREAM_I2I_MODEL, SEEDREAM_MODEL
Where it talks to
no vendor host named in the codeAlso volces.com — not the publisher's domain; check what for before connecting.
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, and read the third-party hosts first. The code names volces.com as well as its own vendor. The guard injects API_KEY, ARK_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y doubao-vision-mcp-server

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 2026-11-21 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 · 45 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
5.2sprocessdependency install exit 0
25sprocessrelaunched with a decoy ARK_API_KEY (tagged; nothing real)
45sclaimed4 tools with a decoy ARK_API_KEY: doubao_vision_understand, doubao_seedream_generate, doubao_seedance_generate, doubao_seedance_query
45stoolsf77d92fb97ec98bd
45stools33cf86d02fd867c7
45stoolsf47ebf22ef767d9b
45stools260e3096be087020
45sprocessscript backend runs setup only
45sprocessno install scripts to re-run

Static findings

No findings across 642 lines in 6 files.

Cost to the agent

Instructions loaded
≈56 tok
1 file · 6 in bundle
Tool list per prompt
≈741 tok
4 tools · 185 per tool
Handshake
445 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 210

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.