mcp-vm-blackbox@1.2.14
VERIFIED· not startedPublisher claims: "MCP server for controlling VirtualBox VMs — screenshots, keyboard input, PowerShell, vagrant, WinRM, podman, and CI build pipelines" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
ANTHROPIC_API_KEYAPI_KEY_21STCI_JOB_TOKENGITLAB_TOKENMCP_VM_BLACKBOX_PG_SUPERPASSWORDOPENROUTER_API_KEYVM_GUEST_PASSWORDConfiguration, not credentials: CI_PROJECT_ID, CI_PROJECT_PATH, CI_SERVER_URL, DASHBOARD_URL, GITLAB_HOST, GITLAB_PROJECT_PATH, MCP_VM_BLACKBOX_AGENT_ID, MCP_VM_BLACKBOX_DATA_ROOT, MCP_VM_BLACKBOX_INFRA_DIR, MCP_VM_BLACKBOX_PACKER_API_HOST, MCP_VM_BLACKBOX_PACKER_API_PORT, MCP_VM_BLACKBOX_PACKER_CACHE_DIR, MCP_VM_BLACKBOX_PG_HOST, MCP_VM_BLACKBOX_PG_PORT, MCP_VM_BLACKBOX_PG_SUPERUSER, MCP_VM_BLACKBOX_SCRATCH_DIR, MCP_VM_BLACKBOX_TARGETS_TOML, MCP_VM_BLACKBOX_VBOXAPI_PATHS, PYTHON_GITLAB_CFG, VM_GUEST_USERNAME- Where it talks to
- no vendor host named in the codeAlso an.dev — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names an.dev as well as its own vendor. The guard injects ANTHROPIC_API_KEY, API_KEY_21ST, CI_JOB_TOKEN, GITLAB_TOKEN, MCP_VM_BLACKBOX_PG_SUPERPASSWORD, OPENROUTER_API_KEY, VM_GUEST_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-10 and scored it 82/100 (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 · 0 s · 2 scenarios · 0 deviationsStatic findings
f"Run: sudo rmmod {vendor_module} && sudo rmmod kvm"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.kill_command: str = Field(description="Command to kill the tmux session")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(cmd, capture_output=True, text=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert "sudo rmmod" in result.kvm_conflictFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.JSONResponse with the relay token payload on success, or an errorFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(cmd, check=False, capture_output=True, text=True, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(command, check=False, cwd=root, env=env, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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 mcp-vm-blackbox@1.2.14 as of 4d ago. This is the package itself, not its dependencies.