Server providing Argo CD integration for MCP clients.
Nothing to run from here
Proxmox Ops is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
16
tools declared
local
runs on your machine
—
downloads a day
What it does
Proxmox VE diagnostics, backup audits, maintenance planning and guarded VM operations.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'PROXMOX_HOST=${PROXMOX_HOST}' --env 'PROXMOX_TOKEN_ID=${PROXMOX_TOKEN_ID}' --env 'PROXMOX_TOKEN_SECRET=${PROXMOX_TOKEN_SECRET}' --transport stdio proxmox-ops-mcp '--' uvx proxmox-ops-mcp
# 2 — ask your agent for something these tools do
# backup_audit, cluster_health, ceph_health and 13 more
It needs PROXMOX_HOST, PROXMOX_TOKEN_ID, PROXMOX_TOKEN_SECRET: this reads them from your environment, so export them first.
Proxmox Ops costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DEAll 1 server
derdennis10121 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Proxmox Ops as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads PROXMOX_HOST (Hostname or IP of any cluster node), PROXMOX_TOKEN_ID (API token id, user@realm!tokenname), PROXMOX_TOKEN_SECRET (API token secret) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx PROXMOX_HOST …, setx PROXMOX_TOKEN_ID …, setx PROXMOX_TOKEN_SECRET … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'PROXMOX_HOST=${PROXMOX_HOST}' --env 'PROXMOX_TOKEN_ID=${PROXMOX_TOKEN_ID}' --env 'PROXMOX_TOKEN_SECRET=${PROXMOX_TOKEN_SECRET}' --transport stdio proxmox-ops-mcp '--' uvx proxmox-ops-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: PROXMOX_HOST — Hostname or IP of any cluster node; PROXMOX_TOKEN_ID — API token id, user@realm!tokenname; PROXMOX_TOKEN_SECRET — API token secret. You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Find guests with missing or stale backups, unscheduled guests and failed jobs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| max_age_hours | integer | no | Backups older than this are stale. |
| node | string | no | Only audit guests on this node. |
Check quorum, node availability, CPU/memory pressure, storage fill levels and HA.
Takes no parameters.
Analyse Ceph: health checks, OSD up/in counts, PG states, monitor quorum, capacity.
Takes no parameters.
Compare live CPU, I/O wait, load, memory, swap and versions across nodes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| nodes | array | no | Nodes to compare. Defaults to all online nodes. |
List tasks that failed recently, grouped by type. Good first stop after an incident.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hours | integer | no | Time window to look back, in hours. |
| task_type | string | no | e.g. 'vzdump', 'qmigrate', 'qmstart'. |
| limit | integer | no | Maximum number of failed tasks to return. |
List all cluster nodes with status, CPU and memory utilisation.
Takes no parameters.
List VMs and containers across the cluster with resource usage, tags and HA state.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | string | no | Only guests on this node. |
| status | string | no | Filter by state. |
| guest_type | string | no | 'qemu' (VM) or 'lxc' (container). |
| tag | string | no | Only guests carrying this tag. |
| include_templates | boolean | no | Also list VM and container templates. |
Show one guest's live status and full configuration (secrets redacted).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vmid | integer | yes | VM or container id. |
Return the state of a Proxmox task and the tail of its log.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | string | yes | Node the task ran on. |
| upid | string | yes | Task id (UPID) as returned by write tools. |
| log_lines | integer | no | Log lines to return from the end of the task log. |
Start, gracefully shut down, reboot or hard-stop a VM/container. Two-phase.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vmid | integer | yes | VM or container id. |
| action | yes | start | shutdown (graceful) | reboot (graceful) | stop (hard power-off, requires admin tier). | |
| confirmation_token | string | no | — |
Create a snapshot of a VM/container, e.g. before an upgrade. Two-phase.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vmid | integer | yes | VM or container id. |
| name | string | yes | Snapshot name: letter first, [A-Za-z0-9_-]. |
| description | string | no | Free-text note stored with the snapshot. |
| include_ram | boolean | no | VMs only: also save RAM state (larger, slower). |
| confirmation_token | string | no | — |
Move a VM (live if running) or container (restart if running) to another node.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vmid | integer | yes | VM or container id. |
| target_node | string | yes | Destination node. |
| with_local_disks | boolean | no | Copy local disks to the target (VMs, slow). |
| confirmation_token | string | no | — |
Rank nodes for a new VM/container by memory headroom, CPU load and vCPU over-commit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cores | integer | yes | vCPUs the guest needs. |
| memory_gib | number | yes | Memory in GiB. |
| disk_gib | number | no | Disk size in GiB (0 = skip). |
| storage | string | no | Require this storage id. |
| exclude_nodes | array | no | Never pick these. |
Plan how to empty a node for maintenance without breaking HA or overloading others.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | string | yes | Node to drain for maintenance. |
| exclude_targets | array | no | Nodes that must not receive guests. |
| memory_limit | number | no | Max memory use allowed on targets. |
Check ZFS pools and physical disks for anything that threatens data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | string | no | Only this node. Default: all. |
Show pending Proxmox updates, needed reboots and expiring node certificates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| node | string | no | Only this node. Default: all. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Proxmox Ops or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 0.1.0 · scanned 30 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest3cf623cba883668b2fa29f52deae7c72cdba80c52bd46eab59f0c61afc7157b7
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (16 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| backup_audit | no tags | |
| cluster_health | no tags | |
| ceph_health | no tags | |
| compare_nodes | no tags | |
| recent_task_failures | no tags | |
| list_nodes | no tags | |
| list_guests | no tags | |
| get_guest | no tags | |
| get_task_status | no tags | |
| guest_power | no tags | |
| create_snapshot | no tags | |
| migrate_guest | no tags | |
| recommend_placement | no tags | |
| plan_node_evacuation | no tags | |
| storage_health | no tags | |
| node_maintenance_status | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest3cf623cba883668b
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Proxmox Ops can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.