mcp@7.0.1

VERIFIED

Publisher claims: "MCP server for Nexub Design System: gives Claude, Cursor and any MCP client the components, patterns, tokens and design rules of the installed release." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher nexub · publishing for 24 daysInstalls 15,299Last detonated 5d ago
$claude mcp add mcp -- npx -y @nexub/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

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-09 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
6.0sprocessdependency install exit 0
26sclaimed5 tools: get_guidelines, list_components, get_component, get_tokens, get_react_native
26sprocessscript backend runs setup only
26sprocessno install scripts to re-run

Static findings

No findings across 5,486 lines in 80 files.

Cost to the agent

Instructions loaded
≈2,528 tok
1 file · 80 in bundle
Tool list per prompt
≈445 tok
5 tools · 89 per tool
Handshake
452 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 177

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 @nexub/mcp@7.0.1 as of 5d ago. This is the package itself, not its dependencies.