Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.bryanjbelanger/desktop-hypervisor-mcp

MCPB · DESKTOP-HYPERVISOR-MCP-2.1.2.MCPB

VirtualBox and VMware Fusion/Workstation behind one provider-neutral MCP tool surface.

0 this week 52 Trust /100

Last scanned (20 hours ago)

Scores higher than 84% of MCPB servers

Category Cloud Infrastructure

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security0
  • No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
  • Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
Provenance & Transparency45
Schema Quality & AI Usability70
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1700 tokens (~188/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_command" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (12)

  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (4)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  • Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  • Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
  • Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 0
    • Provenance: unverified → fail ▼ security
    • Stability: 0.97 → pass security
  • 3 Nov 26 +1
    • Provenance: fail → unverified ▼ security
  • 2 Nov 26 −1
    • Stability: pass → 0.93 functional
  • 27 Oct 26 0
    • Stability: 0.97 → pass security
  • 26 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 24 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 22 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Analysed mcpb/https://github.com/bryanjbelanger/desktop-hypervisor-mcp/releases/download/v2.1.2/desktop-hypervisor-mcp-2.1.2.mcpb@2.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem mcpb
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 9 exposed · ~1,521 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
artifact ~176

OS images by short name. catalog: what exists. resolve: which artifact fits the selected provider and host arch. fetch: download it verified (per-source checksums; Vagrant boxes are extracted to their importable file) into the shared image cache.

NameTypeReqDescription
actionstringyescatalog|resolve|fetch
dirstring–fetch: image cache directory (default ~/.hypervisor-images, or HV_IMAGE_DIR)
dry_runboolean–fetch: report version/URL/size/checksum without downloading
imagestring–image name (talos, talos-iso, ubuntu, kali, vagrant:org/box, …)
providerstring–provider id; defaults to the only ready one
versionstring–version/tag where the source supports it (default latest)

No output schema declared.

No examples provided.

execute_command ~66

Raw provider escape hatch: full argv for VBoxManage or vmrun on the selected provider.

NameTypeReqDescription
argsnull|arrayyesfull argv after the provider CLI name (VBoxManage …/vmrun …)
providerstring–provider id; defaults to the only ready one

No output schema declared.

No examples provided.

guest ~193

Inside a running guest (agent required; credentials from server env, never parameters): exec, script (interpreter + text — the one-liner path), copy_in, copy_out, screenshot.

NameTypeReqDescription
actionstringyesexec|script|copy_in|copy_out|screenshot
argsnull|array–exec: program arguments
deststring–copy_in: guest path; copy_out/screenshot: host path
interpreterstring–script: guest interpreter (default /bin/bash; Windows: powershell.exe path)
programstring–exec: absolute program path in the guest
providerstring–provider id; defaults to the only ready one
scriptstring–script: script text for the interpreter
srcstring–copy_in: host path; copy_out: guest path
vmstringyesVM name

No output schema declared.

No examples provided.

network ~327

Intent-based networking: ensure_cluster_network (shared NAT with DHCP), expose_guest_port (host→guest forward), make_iso (kickstart/seed ISOs), repack_iso (add kernel args to an installer ISO’s GRUB — Ubuntu autoinstall). Native network mechanism stays behind execute_command.

NameTypeReqDescription
actionstringyesensure_cluster_network|expose_guest_port|make_iso|repack_iso
boot_argsstring–repack_iso: kernel args added to every GRUB linux line (e.g. 'autoinstall ds=nocloud')
cidrstring–ensure_cluster_network: subnet (default 192.168.100.0/24)
deststring–make_iso: output .iso path
grub_cfgstring–repack_iso: GRUB config path inside the ISO (default /boot/grub/grub.cfg)
guest_ipstring–expose_guest_port: guest address
guest_portinteger–expose_guest_port
host_portinteger–expose_guest_port
isostring–repack_iso: source installer .iso
labelstring–make_iso: volume label (OEMDRV for kickstart)
namestring–cluster network name (default cluster-net; VMware always uses vmnet8)
protostring–expose_guest_port: tcp|udp (default tcp)
providerstring–provider id; defaults to the only ready one
src_dirstring–make_iso: host directory to pack

No output schema declared.

No examples provided.

provider ~31

Hypervisor discovery: installed providers with status, capabilities, formats, and remediation.

NameTypeReqDescription
actionstringyeslist

No output schema declared.

No examples provided.

snapshot ~117

Snapshots: take, restore, delete (children=true cascades on VMware), list (tree=true for hierarchy).

NameTypeReqDescription
actionstringyestake|restore|delete|list
childrenboolean–delete: cascade to child snapshots (VMware only)
namestring–snapshot name (restore: empty = most recent on VirtualBox)
providerstring–provider id; defaults to the only ready one
treeboolean–list: show the hierarchy
vmstringyesVM name

No output schema declared.

No examples provided.

vm_config ~202

Configure a VM: resources (cpus/memory), nested_virt, attach_iso (empty path detaches), guestinfo (pre-boot key/value config; VMware only — inverts Talos bring-up order).

NameTypeReqDescription
actionstringyesresources|nested_virt|attach_iso|guestinfo
cpusinteger–resources: vCPUs
enablednull|boolean–nested_virt: on/off (default on)
isostring–attach_iso: host path; empty detaches
keysobject–guestinfo: pre-boot key/value config (e.g. guestinfo.talos.config)
memory_mbinteger–resources: RAM MB
providerstring–provider id; defaults to the only ready one
slotstring–attach_iso: provider-native slot (SATA:1 / sata0:1)
vmstringyesVM name

No output schema declared.

No examples provided.

vm_info ~112

Read-only: list all VMs, running VMs, show one VM, or resolve a guest IP (in-guest tools, else hypervisor DHCP leases by MAC — works for agentless guests like Talos).

NameTypeReqDescription
actionstringyeslist|running|show|ip
networkstring–ip: network to search leases on (default: all)
providerstring–provider id; defaults to the only ready one
vmstring–VM name (show/ip)

No output schema declared.

No examples provided.

vm_lifecycle ~297

Create, start, stop, suspend (start resumes), reset, delete, clone (optionally linked/from snapshot), import (ova/ovf/vmx), export (ova).

NameTypeReqDescription
actionstringyescreate|start|stop|suspend|reset|delete|clone|import|export
cpusinteger–create: vCPUs (default 2)
deststring–clone: new VM name; export: output .ova path
disk_gbinteger–create: disk GB (0 = none on VirtualBox, 25 on VMware)
firmwarestring–create: efi|bios (provider default when empty)
guest_osstring–create: provider-native guest OS id
guiboolean–start: show the console window (default headless)
hardboolean–stop/reset: force it, skipping the guest-OS path
linkedboolean–clone: linked clone
memory_mbinteger–create: RAM MB (default 2048)
nested_virtboolean–create: enable nested virtualization
pathstring–import: .ova/.ovf/.vmx artifact path
providerstring–provider id; defaults to the only ready one
snapshotstring–clone: source snapshot
vmstring–VM name

No output schema declared.

No examples provided.

Install

How do I install the io.github.bryanjbelanger/desktop-hypervisor-mcp server?

io.github.bryanjbelanger/desktop-hypervisor-mcp ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. The MCP registry declares no SHA-256 for this bundle, so there is no published digest to check the download against.

mcpb · desktop-hypervisor-mcp-2.1.2.mcpb

Download bundle

The MCP registry declares no SHA-256 for this bundle, so there is no published digest to check it against. Open it with an MCPB-capable host such as Claude Desktop.

Common questions

What is the io.github.bryanjbelanger/desktop-hypervisor-mcp server?

io.github.bryanjbelanger/desktop-hypervisor-mcp is listed in the public MCP registry as io.github.bryanjbelanger/desktop-hypervisor-mcp. VirtualBox and VMware Fusion/Workstation behind one provider-neutral MCP tool surface. This page covers its MCPB bundle (https://github.com/bryanjbelanger/desktop-hypervisor-mcp/releases/download/v2.1.2/desktop-hypervisor-mcp-2.1.2.mcpb).

Is the io.github.bryanjbelanger/desktop-hypervisor-mcp server safe to use?

io.github.bryanjbelanger/desktop-hypervisor-mcp scores 52 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.bryanjbelanger/desktop-hypervisor-mcp server expose?

io.github.bryanjbelanger/desktop-hypervisor-mcp exposes 9 tools: artifact, execute_command, guest, network, provider, and 4 more. Their descriptions and schemas cost roughly 1,521 tokens of context every time the server is loaded.

What licence is the io.github.bryanjbelanger/desktop-hypervisor-mcp server under?

io.github.bryanjbelanger/desktop-hypervisor-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.bryanjbelanger/desktop-hypervisor-mcp server?

VerifyMCP ran 12 checks on io.github.bryanjbelanger/desktop-hypervisor-mcp, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about io.github.bryanjbelanger/desktop-hypervisor-mcp: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.