mcp@0.19.9

CAUTION· startup only

Publisher claims: "Deploy and operate multiplayer game servers on Edgegap's global edge network." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher edgegap · publishing for 67 daysInstalls 5,985Last detonated 1 h ago

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: Caution 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
EDGEGAP_API_TOKENEDGEGAP_REGISTRY_TOKENConfiguration, not credentials: EDGEGAP_APP_ALLOWLIST, EDGEGAP_BASE_URL, EDGEGAP_ENABLE_SKILLS_UPDATE, EDGEGAP_MAX_AGENT_DEPLOYMENTS, EDGEGAP_MAX_DEPLOYS_PER_RUN, EDGEGAP_MAX_DURATION_MINUTES, EDGEGAP_READ_ONLY, EDGEGAP_SKILLS_CHECK, EDGEGAP_SKILLS_RAW_URL, EDGEGAP_STOP_OWN_ONLY, EDGEGAP_TIMEOUT_MS
Where it talks to
edgegap.com (its own)Also githubusercontent.com, amazonaws.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
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 githubusercontent.com, amazonaws.com as well as its own vendor. The guard injects EDGEGAP_API_TOKEN, EDGEGAP_REGISTRY_TOKEN only into requests to edgegap.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets EDGEGAP_API_TOKEN=edgegap.com,EDGEGAP_REGISTRY_TOKEN=edgegap.com -- npx -y @edgegap/mcp

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

What changed since 0.17.0

vet-skills diff mcp 0.17.0 0.19.9

In the sandbox, this version reached for nothing 0.17.0 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 2026-11-20 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 37 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-LbrI41/task/home/work/acme-api/.claude/skills/mcp/dist/skills.generated.js' } Node.js v22.23.5
36sprocessscript backend runs setup only
36sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/auth.js:242 · npx invocation of non-well-known package — may execute untrusted code'pass through Edgegap infrastructure — the local server (npx @edgegap/mcp) ' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Destructive file system command detecteddist/dockerfile.js:45 · Destructive file system command detected' apt-get clean && rm -rf /var/lib/apt/lists/*',Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commanddist/dockerfile.js:146 · File permission modification command — agent changes file ownership/permissions: `RUN chmod +x /app/${executable}`,Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commanddist/dockerfile.js:173 · File permission modification command — agent changes file ownership/permissions? `RUN sed -i 's/\\r$//' /app/${executable} && chmod +x /app/${executable}`Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commanddist/dockerfile.js:145 · File permission modification command — agent changes file ownership/permissions? `# Scripts saved on Windows carry CRLF endings, which break the shebang.\nRUN sed -i 's/\\r$//' /app/${executable} && chmod +x /app/${executable}`Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
CRITICAL
Prompting user to enter sensitive credentialsdist/auth.js:165 · Prompting user to enter sensitive credentials — social engineeringdescription: 'Paste the token value. It is held in one variable in memory for ' +Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File permission modification commanddist/dockerfile.js:174 · File permission modification command — agent changes file ownership/permissions: `RUN chmod +x /app/${executable}`,Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedist/hosted.js:24 · npx invocation of non-well-known package — may execute untrusted code* hosted server refuses it as foreign. The stdio server (npx @edgegap/mcp)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commanddist/dockerfile.js:121 · File permission modification command — agent changes file ownership/permissions`RUN chmod +x /root/build/${executable}`,Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedist/hosted.js:53 · npx invocation of non-well-known package — may execute untrusted code'so prefer the local server (npx -y @edgegap/mcp), which keeps the token ' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/index.js:60 · npx invocation of non-well-known package — may execute untrusted code// commands and neither named `mcp`, `npx @edgegap/mcp` cannot pick one andFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/tools.js:3756 · npx invocation of non-well-known package — may execute untrusted code'runs each outdated install\'s own updater (npx ' + SKILLS_CLI + ' update for the Edgegap skills only, or claude plugin ' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/tools.js:4034 · npx invocation of non-well-known package — may execute untrusted code'(npx -y @edgegap/mcp) with EDGEGAP_API_TOKEN instead.'Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/hosted.js:64 · npx invocation of non-well-known package — may execute untrusted code'(npx -y @edgegap/mcp).\n\n' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/tools.js:3802 · npx invocation of non-well-known package — may execute untrusted codeconst howToUpdate = 'Reinstall the way they were installed: npx skills add edgegap/llm-agent-skills --skill "*" (add -g for user-wide); ' +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commanddist/serverconfig.js:160 · File permission modification command — agent changes file ownership/permissionswarn('no-chmod', 'No "chmod +x" on the server binary. Builds copied from Windows often lose the executable bit, giving "permission denied" at start.', 'Add "RUN chmod +x /path/to/ServerBuild".');Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedist/skillsversion.js:108 · npx invocation of non-well-known package — may execute untrusted code…LS_PACK.version}. A newer @edgegap/mcp may carry it: restart the server through npx -y @edgegap/mcp@latest, or update the Edgegap extension. The bundled skills are st…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/skillsinstall.js:33 · npx invocation of non-well-known package — may execute untrusted code// npx and claude are .cmd shims on Windows, which only start through aFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/tools.js:3547 · File type combined with upload action — agent may exfiltrate local data files'returned config to a file (e.g. matchmaker-config.json) and have the developer upload it ' +Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈73 tok
1 file · 22 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.

What would make this Verified

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim edgegap: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim edgegapPropose a patch to the maintainer
mcp@0.19.9 safety verdict: Caution (startup only) — KillerSkills