mcp@0.5.15

VERIFIED· startup only

Publisher claims: "Model Context Protocol server for aiGentyc — content & authoring tools for LLM agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher aigentyc · publishing for 220 daysInstalls 915Last detonated 3 h ago
$claude mcp add mcp -- npx -y @aigentyc/mcp
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
NEXT_PUBLIC_AIGENTYC_API_KEYVITE_AIGENTYC_API_KEYConfiguration, not credentials: AIGENTYC_CONFIG
Where it talks to
aigentyc.ai (its own)Also your-app.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 your-app.com as well as its own vendor. The guard injects NEXT_PUBLIC_AIGENTYC_API_KEY, VITE_AIGENTYC_API_KEY only into requests to aigentyc.ai (and its subdomains) and refuses the rest.

$vet-skills run --secrets NEXT_PUBLIC_AIGENTYC_API_KEY=aigentyc.ai,VITE_AIGENTYC_API_KEY=aigentyc.ai -- npx -y @aigentyc/mcp

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

What changed since 0.5.14

vet-skills diff mcp 0.5.14 0.5.15

In the sandbox, this version reached for nothing 0.5.14 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 2026-11-19 and scored it 86/100 (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 · 41 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
21sprocessdependency install exit 0
41sclaimedstartup only: exited (0) before answering · code: 'ENOENT', syscall: 'stat', path: '/tmp/ks-detonate-922ury/task/home/.aigentyc/config.json' }
41sprocessscript backend runs setup only
41sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commanddist/config.js:3 · File permission modification command — agent changes file ownership/permissionsimport { readFile, writeFile, stat, mkdir, chmod } from "node:fs/promises";Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedist/install-cmd.js:93 · npx invocation of non-well-known package — may execute untrusted codeconsole.log(` ${ANSI.dim("→")} Run ${ANSI.cyan("npx -y @aigentyc/mcp@latest doctor")} any time to sanity-check.\n`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commanddist/config.js:76 · File permission modification command — agent changes file ownership/permissionsthrow new Error(`Refusing to use ${file}: permissions are ${mode.toString(8)} (must be 600). Fix with: chmod 600 ${file}`);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsdist/tools/embed.js:160 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…T set NEXT_PUBLIC_AIGENTYC_API_KEY (Next.js) or VITE_AIGENTYC_API_KEY (Vite) in .env, otherwise /api/kb/chat returns 401. Generate a project-scoped key from the das…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondist/tools/documents.js:110 · File type combined with upload action — agent may exfiltrate local data files…ment from a local file", description: "Read a local text file (.md, .txt, .json, .csv, .html, …) and store its contents as a manual-text document in the knowledge base — the file-fed twin of documents_create_from_text. Token-efficient: the…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagedist/install-cmd.js:182 · npx invocation of non-well-known package — may execute untrusted code// Prefer the absolute npx path if we can resolve it; fall back to "npx"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈56 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 @aigentyc/mcp@0.5.15 as of 2 h ago. This is the package itself, not its dependencies.