Virtualbox MCP Server (usemanusai/Virtualbox-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 92 tools. No publisher has claimed this listing.

D
Caution
54/100

Virtualbox MCP Server

A Model Context Protocol server for managing Virtualbox and Vagrant virtual machines via a TypeScript interface. It enables users to programmatically create new VMs and monitor their status through simple JSON-RPC tools.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

usemanusai

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 12 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// tools this server exposes46 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

create_vm

Create a new Vagrant VM

get_vm_status

Get the status of a specific Vagrant VM

list_vms

List all managed VMs and their statuses

destroy_vm

Destroy a Vagrant VM (force)

exec_command

Execute a shell command inside a VM

upload_file

Upload a file from host to VM

search_files

Search for files inside the VM (using grep)

configure_sync

Configure file synchronization and watchers

sync_status

Get the current alignment status of the sync engine

resolve_conflict

Resolve a file sync conflict

create_dev_vm

Create and configure a development VM with Vagrant (advanced)

ensure_dev_vm

Ensure development VM is running, create if it doesn't exist

exec_with_sync

Execute a command in the VM with file synchronization before and after

run_background_task

Run a command in the VM as a background task

setup_dev_environment

Install language runtimes, tools, and dependencies in the VM

install_dev_tools

Install specific development tools in the VM

configure_shell

Configure shell environment in the VM

sync_to_vm

Sync files from host to VM

sync_from_vm

Sync files from VM to host

tail_vm_log

Reads the last N lines of a specific file inside the VM (e.g., /var/log/syslog, /var/log/nginx/error.log). Essential for debugging service failures.

get_task_output

Retrieves the stdout and stderr buffers of a specific background task started via run_background_task. Essential for monitoring long-running jobs.

grep_log_stream

Searches within a log file for a specific pattern. Locates events within active log streams.

snapshot_save

Creates a lightweight Vagrant snapshot. Use before risky operations to enable rollback if something breaks.

snapshot_restore

Reverts the VM to a specific named snapshot. Enables rapid recovery without destroying and rebuilding the VM.

snapshot_list

Lists all available snapshots for a VM.

snapshot_delete

Deletes a specific snapshot from a VM.

list_processes

Returns a structured list of running processes in the VM (like ps aux). Use to verify service health and resource usage.

kill_process

Sends a signal (SIGTERM/SIGKILL) to a specific process in the VM. Required to stop runaway tasks or stuck servers.

check_vm_port

Verifies if a port is listening in the VM and optionally accessible from the host. Differentiates 'App failed' from 'Port forwarding failed'.

get_vm_dashboard

Returns a comprehensive dashboard with VM status, resource usage (CPU/RAM/Disk), active background tasks, and recent logs.

start_download

Starts a tracked file download operation. Returns an operation_id that MUST be used with `wait_for_operation`.

get_operation_progress

Gets real-time progress of a specific operation (bytes downloaded, percentage, ETA).

wait_for_operation

Blocks execution until an operation completes OR times out. CRITICAL: Use this after starting any long-running task.

cancel_operation

Cancels a running operation.

list_active_operations

Lists all currently running operations.

scan_system_health

Checks system health (disk space, memory) and identifies potential 'Zombie' VMs. Can optionally perform a security scan on a specific VM.

cleanup_zombies

Safely cleans up identified Zombie VMs. REQUIRES explicit list of VM names to avoid accidents.

sequentialthinking

A detailed tool for dynamic and reflective problem-solving. MUST be used between steps to analyze state. Features: Checks resources (RAM/Disk) before VM creation, verifies hypothesis, allows branching/backtracking. Parameters: - thought: The current thinking step. MUST include technical checks (e.

set_display_mode

Controls Headless vs GUI state of a VM.

atomic_transaction_exec

Executes a command with auto-snapshot safety. Reverts on failure if rollback_on_fail is true.

sentinel_await

Wait until a specific condition is met in the VM (port, file, log, or service).

forensic_blackbox_capture

Aggregates a diagnostic bundle (logs, processes, system state) for failure analysis.

resize_vm_resources

Modifies VM CPU/RAM/GUI settings. Triggers a reboot if the VM is running.

package_box

Exports the VM to a portable .box file using `vagrant package`.

inject_secrets

Securely injects environment variables into the VM's .profile. Parameters are redacted from MCP logs.

audit_security

Scans the VM for common security issues (open ports, weak ssh config).

// known CVEs in dependencies12 high6 medium13 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.0.3GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highaxios@1.13.2GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.13.2GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

highaxios@1.13.2GHSA-43fc-jf86-j433

Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig

highaxios@1.13.2GHSA-6chq-wfr3-2hj9

Axios: Header Injection via Prototype Pollution

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configLOG_LEVEL"": "info",
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

92/92 tools missing one or more hints — create_vm (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_vm_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_vms (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +89 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 12 high severity in production deps — @modelcontextprotocol/sdk@1.0.3 (high), axios@1.13.2 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Domain consistency

npm scope @use.manus.ai doesn't match GitHub owner usemanusai

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/usemanusai/virtualbox-mcp-server?variant=verified)](https://m8ven.ai/mcp/usemanusai/virtualbox-mcp-server)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: d639e57153b09c07a71171c9a281281ef47dc163
code hash: c1297c817deb16bc5d2f5f1cf77df60ac6b7eaa2eaa97dc900c1c9781067e0ea
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client