agent-bom runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 4 Nov 2026.
Scan AI/MCP dependencies, descriptor injection, risky tool inputs and authentication configuration.
What changed 1
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 10 October 2026. No other catalogue keeps this.
What the code does
We read the source, 5 h ago · rules 995398eba69f
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:
with subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, start_new_session=os.name != "nt") as proc:
return yaml.load(content, Loader=_LineLoader) # nosec B506 - SafeLoader subclass, no arbitrary object construction
__import__(mod)
_SECRET_NAMES = {"id_rsa", "id_dsa", "id_ecdsa", "id_ed25519", "credentials", ".npmrc", ".pypirc", ".netrc", ".pgpass", "kubeconfig"}
f"Service '{name}' mounts /var/run/docker.sock, which grants root-equivalent control of the host's Docker daemon.",
control_plane_db, graph_db = _resolve_quickstart_databases(dict(os.environ))
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
# Root is used only to prepare the mounted directory; the entrypoint drops all # groups and switches to uid/gid 10001 before importing or starting the API. USER root
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to agent-bom
same job, measured the same wayScan 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.
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
agent-bom — questions
Answers built from our own checks of this server.