mcp@21.38.0

VERIFIED

Publisher claims: "MCP Server para documentação do PO UI — acessa componentes, guias e busca via Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher po-ui · publishing for 232 daysInstalls 3,147Last detonated 6 h ago
$claude mcp add mcp -- npx -y @po-ui/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
no credential variables read in the code
Where it talks to
po-ui.io (its own)Also githubusercontent.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 real credentials

Connect it under the guard; read the third-party hosts first. The code names githubusercontent.com as well as its own vendor. The guard pins the network to the hosts the honeypot saw.

$vet-skills run --net declared -- npx -y @po-ui/mcp

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

What changed since 21.37.0

vet-skills diff mcp 21.37.0 21.38.0

In the sandbox, this version reached for nothing 21.37.0 did not. Compared from the two recorded runs, not from source.

Tool descriptor hashes were not recorded for both runs; renamed or added tools are compared, rewritten descriptions are not.

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 2026-11-19 and scored it 95/100 (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 · 24 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.3sprocessdependency install exit 0
24sclaimed6 tools: list_components, get_component_docs, get_component_examples, get_best_practices, search_docs, get_guide
24stools1686440546414d95
24stools31ebb63898f76236
24stoolsce04bf919863c380
24stoolsa7f376a58329376e
24stools3fdbe40ef4740ff6
24stoolsb119fd3f7bb1470a
24sprocessscript backend runs setup only
24sprocessno install scripts to re-run

Static findings

No findings across 1,235 lines in 11 files.

Cost to the agent

Instructions loaded
≈59 tok
1 file · 11 in bundle
Tool list per prompt
≈952 tok
6 tools · 159 per tool
Handshake
463 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 164

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 @po-ui/mcp@21.38.0 as of 6 h ago. This is the package itself, not its dependencies.