Skills/npm/mcp-server

mcp-server@2.127.0

VERIFIED· startup only

Publisher claims: "MCP Server for withPICA — enables AI assistants to interact with your withPICA music catalog" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher withpica · publishing for 233 daysInstalls 9,830Last detonated 7 h ago
$claude mcp add mcp-server -- npx -y @withpica/mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
MCP_HTTP_SECRETPICA_API_KEYPICA_CREDENTIALS_PATHConfiguration, not credentials: ADR_224_STRUCTURED_ERRORS, MCP_LAYERED_DISCOVERY, MCP_PORT, MCP_TRANSPORT, PICA_API_URL
Where it talks to
withpica.com (its own)Also amazonaws.com, spotify.com, deezer.com, youtube.com, youtu.be — 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
the tool list (the server exited before answering) · 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 amazonaws.com, spotify.com, deezer.com, youtube.com, youtu.be as well as its own vendor. The guard injects MCP_HTTP_SECRET, PICA_API_KEY, PICA_CREDENTIALS_PATH only into requests to withpica.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets MCP_HTTP_SECRET=withpica.com,PICA_API_KEY=withpica.com,PICA_CREDENTIALS_PATH=withpica.com -- npx -y @withpica/mcp-server

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

What changed since 2.126.1

vet-skills diff mcp-server 2.126.1 2.127.0

In the sandbox, this version reached for nothing 2.126.1 did not. Compared from the two recorded runs, not from source.

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; startup only; authenticated tool behavior not tested) on 2026-11-18 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 32 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
12sprocessdependency install exit 0
32sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-ejeOed/task/home/work/acme-api/.claude/skills/mcp-server/dist/resources/index.js' } Node.js v22.23.5
32sprocessscript backend runs setup only
32sprocessno install scripts to re-run

Static findings

MEDIUM
Unicode escape sequence detecteddist/skills/sep2640.js:73 · Unicode escape sequence detected — may contain obfuscated payloadsconst YAML_UNSAFE = /[\u007F-\u009F\u2028\u2029\uFEFF\uFFFE\uFFFF]/g;Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Process kill commanddist/tools/files.js:83 · Process kill command — agent can terminate processes"'revoke the delivery from yesterday', 'kill the access to the master', " +Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/tools/signup.js:13 · npx invocation of non-well-known package — may execute untrusted code* distributed `npx @withpica/mcp-server` binaries can never see it. SameFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/tools/files.d.ts:12 · Process kill command — agent can terminate processes* the org an audit trail of who received what and when, and a kill switchFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈61 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
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 @withpica/mcp-server@2.127.0 as of 6 h ago. This is the package itself, not its dependencies.

mcp-server@2.127.0 safety verdict: Verified (startup only) — KillerSkills