agent-bom runs on your own machine — the client starts it, so there is no endpoint to ping. 2 942 installs a week from pypi. Last commit 1 Nov 2026.
Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.
What the code does
We read the source, 14 h ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
`then mkdir -p .next/standalone/.next && rm -rf .next/standalone/.next/static .next/standalone/public && ` +
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
if os.path.exists("/.dockerenv") or os.environ.get("AGENT_BOM_IN_CONTAINER", "").strip().lower() in truthy:
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[4345],{58137:(e,s,n)=>{Promise.resolve().then(n.bind(n,90209)),Promise.resolve().then(n.t.bind(n,98500,23))}},e=>{e.O(0,[8670,8500,8441,3794,7358],()=>e(e.s=58137)),_N_E=e.O()}]);
этот файл ставится пользователю, но в репозитории его нет
result = subprocess.run([path, "version"], capture_output=True, text=True, timeout=3) # noqa: S603
__import__(mod)
return yaml.load(content, Loader=_LineLoader) # nosec B506 - SafeLoader subclass, no arbitrary object construction
lock_path = os.path.join(lock_directory, f"{digest[:2]}.lock")
…er(e=>e.v===t&&e.w===r||e.v===r&&e.w===t):n}};function l(e,t){e[t]?e[t]++:e[t]=1}function d(e,t){void 0===e[t]||--e[t]||delete e[t]}function a(e,t,r,n){let i=""+t,o=""+r;if(!e&&i>o){let e=i;i=o,o=e}return i+"\x01"+o+"\x01"+(void 0===n?"\0":n)}function h(e,t){return a(e,t.v,t.w,t.…
cred_file = _expand(os.environ.get("AWS_SHARED_CREDENTIALS_FILE", "~/.aws/credentials"))
f"Service '{name}' mounts /var/run/docker.sock, which grants root-equivalent control of the host's Docker daemon.",
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch agent-bom and you get told the day something new turns up.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agent-bom -- uvx agent-bom{
"mcpServers": {
"agent-bom": {
"command": "uvx",
"args": [
"agent-bom"
]
}
}
}[mcp_servers.agent-bom]
command = "uvx"
args = ["agent-bom"]{
"mcpServers": {
"agent-bom": {
"command": "uvx",
"args": [
"agent-bom"
]
}
}
}{
"servers": {
"agent-bom": {
"type": "stdio",
"command": "uvx",
"args": [
"agent-bom"
]
}
}
}Optional settings from the registry entry, left out of the block above:
NVD_API_KEY (NVD API key for higher rate limits on vulnerability enrichment).
Alternatives to agent-bom
same job, measured the same wayScan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.
Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
Prompt-injection scanner for agents: risk score, categories and spans for text, pages, MCP tools
Independent effect verification and signed receipts for consequential AI agent actions.
Dependency policy and MCP server to stop AI coding agents from installing risky npm packages.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Scan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.
agent-bom — questions
Answers built from our own checks of this server.