mcp-server@2.522.0
VERIFIED· startup onlyPublisher 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.
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.
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 2.522.0In 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 deviationsStatic findings
throw 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.* 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.console.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.env: { ...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.const env = meta?.env ?? 'unknown';Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.* 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.…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.// 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.* reported. Rethrowing one would kill the child just the same.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
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.