Skills/npm/mcp-server

mcp-server@2.522.0

VERIFIED· startup only

Publisher claims: "MCP server for MemLab heap snapshot analysis — gives AI coding assistants tools to explore JavaScript heap snapshots, find memory leaks, and identify optimization opportunities" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher memlab · publishing for 244 daysInstalls 16,755Last detonated 1 h ago
$claude mcp add mcp-server -- npx -y @memlab/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
no credential variables read in the code
Where it talks to
no vendor host named in the code
What we saw when it ran
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 under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

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

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

What changed since 2.313.0

vet-skills diff mcp-server 2.313.0 2.522.0

In the sandbox, this version reached for nothing 2.313.0 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 2026-11-22 and scored it 85/100 (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 · 36 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
16sprocessdependency install exit 0
36sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-W8w6W8/task/home/work/acme-api/.claude/skills/mcp-server/dist/tools/load-snapshot.js' } Node.js v22.23.5
36sprocessscript backend runs setup only
36sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/run-manifest.js:236 · File type combined with upload action — agent may exfiltrate local data filesthrow new Error(`no run.json at ${file}. Pass the hunt's output directory (the one holding run.json and snapshots/), or supply paths + cycles_per_rung by hand.`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/run-manifest.js:206 · File type combined with upload action — agent may exfiltrate local data files* Load `run.json` from a hunt output directory (or a direct path to the file).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionbin/memlab-cli.js:933 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify(tool.inputSchema ?? {}, null, 2));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsdist/battery-child.js:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...process.env, ...env, [CHILD_ENV]: '1' },Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdist/tools/sweep.js:647 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst env = meta?.env ?? 'unknown';Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandbin/memlab-cli.js:131 · Process kill command — agent can terminate processes* the container may ever use — and the failure mode is an OOM-kill by theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/tools/eval.js:5462 · Process kill command — agent can terminate processes…defined`, and the iterator SKIPS those rather than letting the throw escape and kill the eval. No `try`/`catch` boilerplate is needed, and none should be written — a…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandbin/memlab-cli.js:201 · Process kill command — agent can terminate processes// which is the OOM-kill this lookup exists to prevent. The GB-roundedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/battery-child.js:37 · Process kill command — agent can terminate processes* reported. Rethrowing one would kill the child just the same.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈82 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 @memlab/mcp-server@2.522.0 as of 35 min ago. This is the package itself, not its dependencies.

mcp-server@2.522.0 safety verdict: Verified (startup only) — KillerSkills