Skills/npm/mcp-server

mcp-server@0.1.75

VERIFIED· startup only

Publisher claims: "PandaNpc MCP Server — PandaNote and Agent connection management for Codex, Claude Code, and other MCP clients" Observed in sandbox: calls download.pandanpc.com only, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher pandanpc · publishing for 219 daysInstalls 1,963Last detonated 21 min ago
$claude mcp add mcp-server -- npx -y @pandanpc/mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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
no credential variables read in the code
Where it talks to
pandanpc.com (its own)
What we saw when it ran
no credential files read · reached only download.pandanpc.com (its own)
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable and talks to pandanpc.com, its own; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y @pandanpc/mcp-server

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

What changed since 0.1.72

vet-skills diff mcp-server 0.1.72 0.1.75

This version reaches for something 0.1.72 did not: 2 new install scripts (node ./install.js, node install.js). Compared from the two recorded runs, not from source.

New install scripts
node ./install.js, node install.js

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 (3 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 84/100 (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: calls download.pandanpc.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 25 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
2.0snetworkCONNECT tcp://download.pandanpc.com:443
2.0sprocessinstall script run in the sandbox
2.3snetworkCONNECT tcp://download.pandanpc.com:443
2.3snetworkCONNECT tcp://download.pandanpc.com:443
22sfilesystemread ~/.pandanpc-mcp/runtime/linux-x64/active.json · ~/.pandanpc-mcp/runtime/linux-x64/candidate.json outside project
22sclaimedstartup only: exited (0) before answering · [pandanpc-mcp] binary not found at /tmp/ks-detonate-G8INf4/task/home/work/acme-api/.claude/skills/@pandanpc/mcp-server/bin/pandanpc-mcp-v0.1.75; reinstall @pandanpc/mcp-server
22sprocessscript backend runs setup only
24sprocesssecond launch, clock +45 days, CI unset
24snetworkCONNECT tcp://download.pandanpc.com:443
24snetworkCONNECT tcp://download.pandanpc.com:443
24snetworkCONNECT tcp://download.pandanpc.com:443

Static findings

LOW
Unpinned dependencyindex.js:30 · Unpinned dependencyif (result.status === 'manual-update-required') console.error('Update the launcher: npm install -g @pandanpc/mcp-server@latest')Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
MEDIUM
Process kill commandproxy.js:57 · Process kill command — agent can terminate processes* from a private copy and waits for it, so the server may sit one level below; kill those twoFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandproxy.js:393 · Process kill command — agent can terminate processesconst last = timeout(5000, 'kill timed out')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈2,333 tok
2 files · 16 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

Not checked against OSV yet; the weekly check has not reached this version.