Skills/npm/mcp

mcp@1.2.12

VERIFIED

Publisher claims: "WaveSpeed MCP server — run any model on the live WaveSpeed catalog (image, video, audio, 3D) with schema introspection, local-file upload, and price quotes." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher wavespeed · publishing for 88 daysInstalls 11,675Last detonated 11 min ago
$claude mcp add mcp -- npx -y @wavespeed/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
WAVESPEED_API_KEYConfiguration, not credentials: IMAGE_MODEL_KEYS, VIDEO_MODEL_KEYS, WAVESPEED_BASE_URL, WAVESPEED_CLIENT_NAME
Where it talks to
wavespeed.ai (its own)
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. It asks for WAVESPEED_API_KEY and talks to wavespeed.ai. 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.

$vet-skills run --secrets WAVESPEED_API_KEY=wavespeed.ai -- npx -y @wavespeed/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 2026-11-15 and scored it 92/100 (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 · 34 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
13sprocessdependency install exit 0
33sclaimed16 tools: list_models, get_model_schema, run_model, generate_image, edit_image, generate_video, edit_video, extend_video, get_price, get_balance, list_predictions, list_billings, get_usage, delete_predictions, upload_file, get_prediction
33stools272a1fd974995951
33stoolsb352e9d31e2b7cb7
33stools6aa8a2cafdc309f2
33stoolsf214ac680174c3cf
33stoolse2af2445e4ffe184
33stoolsc98a7f0dc4061e46
33stools964d9880154cb72d
33stoolse0c21852031b31ec
33stoolsd4360a2c1178cbe1
33stools47b6938ffe583276
33stoolsfc4185a9fef761e9
33stools3d9dc646fbf58818
33stoolsc88a2e606da73a4b
33stools677ae99d98f2dc4a
33stools51a6e356a663577c
33stools72bf13a3e7468a5e
33sprocessscript backend runs setup only
33sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/index.js:2 · npx invocation of non-well-known package — may execute untrusted code// stdio entry point: `wavespeed-mcp` (or `npx -y @wavespeed/mcp@latest`).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 2,352 lines in 18 files.

Cost to the agent

Instructions loaded
≈74 tok
1 file · 18 in bundle
Tool list per prompt
≈4,877 tok
16 tools · 305 per tool
Handshake
1079 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 280

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.