What can you do with this server?

This server provides governed Proxmox VE operations across VMs, containers, backups, snapshots, disks, cluster/storage/firewall/HA, diagnostics, and undo/audit tracking. * Inspect cluster nodes, resources, status, tasks/logs, VMIDs, pools, storage, firewall, and HA state. * Manage QEMU VMs: list/get/config, start/stop/shutdown/reboot, reconfigure, clone/delete/migrate, resize/move disks, snapshots create/delete/list/rollback, and guest-agent ping. * Manage LXC containers: list, start, and stop. * Create/list/restore backups with dry-run, force-overwrite guard, and async task tracking. * Run read-only diagnostics/RCA for node pressure and guest health. * Apply recorded undo tokens and inspect audit/risk-tier metadata.

Which integrations are available for this server?

Provides tools for managing Proxmox VE VMs and containers, including list, get, config, start, stop, shutdown, reboot, reconfigure, clone, delete, migrate, snapshot operations, and cluster/storage operations.

How do I use io.github.AIops-tools/proxmox-aiops?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@io.github.AIops-tools/proxmox-aiops list all VMs on pve-lab" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

io.github.AIops-tools/proxmox-aiops

by AIops-tools

Overview Schema Source Related Servers Discussions Admin

Python

Local

Proxmox AIops

Audit availability: Real writes require a committed pending audit row and stop before contacting the platform if storage is unavailable. Reads and previews may continue with a warning; new audit rows store outcome summaries rather than full responses.

Disclaimer: Community-maintained open-source project. Not affiliated with, endorsed by, or sponsored by Proxmox Server Solutions GmbH. "Proxmox" is a trademark of its owner. MIT licensed.

AI-powered Proxmox VE VM and container lifecycle operations with a built-in governance harness — unified audit log, token/runaway budget guard, undo-token recording, and descriptive risk-tier labels. Self-contained: no external dependencies beyond proxmoxer and the MCP SDK. Coverage is not yet exhaustive across every Proxmox operation.

Verification status: live-verified against real Proxmox VE 8.4.19 across three rounds — read-only surfaces, the QEMU write surface, and a two-node cluster (quorum, live migration, move-disk, a backup that actually succeeded). Rounds 2 and 3 each found a real bug the mocks could not see. See docs/VERIFICATION.md for exactly what was proven and what is still uncovered.

What works

CLI (proxmox-aiops ...): vm list/get/config/start/stop/shutdown/reboot/reconfigure/clone/delete/migrate, vm resize-disk/move-disk/agent-ping, vm snapshot-create/snapshot-delete/snapshot-list/snapshot-rollback, backup create/list/restore, ct list/start/stop, cluster nodes/status/task-status/resources/node-status/task-log/next-vmid, ha status/resources, pool list/members, firewall vm-rules/cluster-status, storage list/content, diagnose node-pressure/guest-health, undo list/apply, init, secret set/list/rm/migrate/rotate-password, doctor, mcp.
MCP server (proxmox-aiops mcp or proxmox-aiops-mcp): 43 tools, every one wrapped with the bundled @governed_tool harness.
Diagnostics / RCA (read-only): diagnose node-pressure ranks cluster nodes by CPU/memory/root-fs pressure; diagnose guest-health scans VMs/containers for stopped guests, memory saturation, and disks near full. Every finding cites the measured number that tripped it and a concrete action — transparent heuristics, not a black-box verdict.
Credentials: proxmox-aiops init (onboarding wizard) and proxmox-aiops secret ... manage an encrypted secret store — no plaintext passwords in config.yaml.
Reversibility: write ops with a clean inverse (start/stop/shutdown/reconfigure/clone/migrate/snapshot-create/move-disk, container start/stop, and restore-into-a-free-vmid) record an inverse undo descriptor; irreversible ops (delete, snapshot-rollback, forced restore) declare none and are tagged high risk. Disk resize is grow-only (shrink refused).
Async tasks: Proxmox writes return a task UPID — poll completion with cluster task-status / read lines with cluster task-log (the runaway budget guard prevents poll loops from running away).

Related MCP server: proxmox-mcp

What this tool does, and does not, decide

It delivers Proxmox VE operations — reads and writes — accurately and efficiently, and records every one of them. It does not decide whether a write is allowed to happen. That is the agent's judgement, or the permission of the account you connect it with: use a Proxmox VE user or API token granted only read privileges (no VM./Datastore. write roles), and the writes fail at the server — the place that actually owns the permission.

So there is no read-only switch, no policy file, no approval gate to configure. The one thing the tool guarantees is that nothing is silent: every call, over MCP and over the CLI alike, lands an audit row in ~/.proxmox-aiops/audit.db, and destructive writes still capture their before-state and record an inverse where one exists.

Each tool declares a risk_level, carried into the audit row as a descriptive tier (none/confirm/review) — so a reviewer can see at a glance that a row was a high-risk delete. It is a label, not a gate.

Running a smaller / local model? See agent-guardrails.md — it lists the guardrails this tool now enforces for you (so you don't spend prompt budget restating them) and gives a ready-made system prompt for what's left.

Quick start

As a Claude Code plugin

One install gives an agent both the skill and the MCP server:

/plugin marketplace add AIops-tools/marketplace
/plugin install proxmox-aiops@aiops-tools

The MCP server is fetched with uv and pinned to the package version this plugin declares, so an audit row can be traced back to the code that wrote it. Credentials are still configured with proxmox-aiops init — see below.

As an OpenClaw plugin

The same bundle is published on ClawHub, where one install delivers the skill and its MCP server together:

openclaw plugins install clawhub:@zw008/proxmox-aiops
openclaw skills info proxmox-aiops          # expect: Visible to model: yes

Restart the OpenClaw gateway afterwards so it loads the plugin. The MCP server is fetched with uv, pinned to this exact release, so uvx has to be on PATH — without it the skill still installs but reports Visible to model: no. Credentials are configured exactly as below.

As a CLI or standalone MCP server

uv tool install proxmox-aiops
mkdir -p ~/.proxmox-aiops
# create ~/.proxmox-aiops/config.yaml with a targets: list
# put secrets in ~/.proxmox-aiops/.env  (chmod 600)
proxmox-aiops doctor

Example ~/.proxmox-aiops/config.yaml:

targets:
  - name: pve-lab
    host: 10.0.0.10
    user: "claude@pve!ops"    # API token: user@realm!tokenid — a dedicated,
                              # least-privilege user, NOT root@pam
    node: pve1
    auth_kind: token
    verify_ssl: false          # self-signed lab certs only

~/.proxmox-aiops/.env (chmod 600): PROXMOX_PVE_LAB_SECRET=<token-uuid>

Audit & safety

All operations are logged to a local SQLite audit DB under ~/.proxmox-aiops/ (relocatable via PROXMOX_AIOPS_HOME). Every write tool passes through the governance harness: token/runaway budget guard, risk-tier tagging, and audit logging. Destructive CLI commands (vm stop, vm delete, vm snapshot-delete, vm snapshot-rollback, ct stop) require double confirmation and support --dry-run (notably backup restore, which is high risk). API-returned text is run through a prompt-injection sanitizer.

Contributing & feature requests

Coverage is intentionally focused. Missing a device, action, or feature you need? Open an issue or pull request at github.com/AIops-tools/Proxmox-AIops — feature requests, contributions, and comments are all welcome.

License: MIT.

Available Tools

43 tools

backup_listA

Read-only

[READ] List backup archives on a storage (optionally filtered by vmid).

Args: storage: Storage id to list backups from. vmid: Optional guest id filter. target: Proxmox target name from config. node: Node name; omit to use the configured default node.

Inputs: storage (required), node, vmid, target.

backup_restoreA

Destructive

[WRITE] Restore a QEMU VM from a backup archive. HIGH RISK. Returns task UPID.

With force=True this OVERWRITES an existing VM (destructive, no undo). Restoring into a free vmid records a delete as the safe inverse. Confirm with the user before calling. Pass dry_run=True to preview: it runs the same existing-VM guard (a preview that would be refused for overwriting without force refuses too) and reports whether it would overwrite or create.

Args: vmid: Target VM id to restore into. archive: Backup volume id / archive path (see backup_list). storage: Storage to place the restored disks on. force: Overwrite vmid if it already exists (destructive). dry_run: If True, preview (runs the existing-VM guard) without restoring. target: Proxmox target name from config. node: Node name; omit to use the configured default node.

Inputs: vmid (required), archive (required), storage (required), node, +3 more.

cluster_firewall_statusA

Read-only

[READ] Cluster-wide firewall options (notably whether it is enabled).

Args: target: Proxmox target name from config.

Inputs: target.

cluster_resourcesA

Read-only

[READ] Aggregate /cluster/resources view of VMs, nodes, and storage.

Single-call cluster-wide inventory. Use this to enumerate everything before drilling into vm_get / node_status.

Args: resource_type: Optional filter — 'vm', 'node', or 'storage'. target: Proxmox target name from config.

Inputs: target, resource_type.

cluster_statusA

Read-only

[READ] Return cluster membership + quorum status.

The type=cluster row's quorate field indicates whether the cluster currently has quorum.

Args: target: Proxmox target name from config.

Inputs: target.

ct_listA

Read-only

[READ] List LXC containers with name, vmid, status, cpu, mem.

Args: target: Proxmox target name from config; omit to use the default. node: Node name; omit to use the configured default / all nodes.

Inputs: node, target.

ct_startA

Destructive

[WRITE] Start an LXC container. Returns the task UPID. Inverse: ct_stop.

Pass dry_run=True to preview.

Args: vmid: Numeric container id (see ct_list). dry_run: If True, preview without starting. target: Proxmox target name from config. node: Node name; omit to auto-locate the container.

Inputs: vmid (required), node, target, dry_run.

ct_stopA

Destructive

[WRITE] Stop an LXC container. Returns the task UPID. Inverse: ct_start.

Pass dry_run=True to preview.

Args: vmid: Numeric container id (see ct_list). dry_run: If True, preview without stopping. target: Proxmox target name from config. node: Node name; omit to auto-locate the container.

Inputs: vmid (required), node, target, dry_run.

guest_health_rcaA

Read-only

[READ] Scan VMs and containers for stopped guests, memory saturation, and disks near full.

Pulls the /cluster/resources guest view (qemu + lxc) and reports worst-first findings plus the list of stopped guests, each finding citing the measured number and a concrete remediation.

Args: target: Proxmox target name from config; omit to use the default.

Inputs: target.

ha_resource_listB

Read-only

[READ] HA-managed resources (VMs/CTs); empty when HA is not configured.

Args: target: Proxmox target name from config.

Inputs: target.

ha_statusA

Read-only

[READ] Current HA status entries, or a not-configured signal.

Returns {"configured": bool, "entries": [...]}. Do NOT infer "HA is set up" from a non-empty entries list: every quorate cluster reports a quorum row, and master/lrm rows once the HA stack has run, with zero resources defined. "configured" is true only when HA actually manages something; when it is false a message explains that the rows describe the stack itself.

Args: target: Proxmox target name from config.

Inputs: target.

next_vmidC

Read-only

[READ] Return a free VMID for a new guest (/cluster/nextid).

Args: target: Proxmox target name from config.

Inputs: target.

node_listB

Read-only

[READ] List Proxmox cluster nodes with status, cpu load, and memory.

Args: target: Proxmox target name from config; omit to use the default.

Inputs: target.

node_pressure_rcaA

Read-only

[READ] Rank cluster nodes by CPU / memory / root-fs pressure.

Pulls the /cluster/resources node view and flags each node over the CPU (85%), memory (90%), or disk (85%) thresholds, worst-first, citing the measured percentage and a concrete action for every finding.

Args: target: Proxmox target name from config; omit to use the default.

Inputs: target.

node_statusA

Read-only

[READ] Detailed status for one node: cpu, load average, memory, uptime.

Args: node: Node name (see node_list). target: Proxmox target name from config.

Inputs: node (required), target.

pool_listB

Read-only

[READ] List resource pools (poolid + comment).

Args: target: Proxmox target name from config.

Inputs: target.

pool_membersB

Read-only

[READ] List the members of a pool (VMs, CTs, storage).

Args: poolid: Pool id (see pool_list). target: Proxmox target name from config.

Inputs: poolid (required), target.

storage_contentA

Read-only

[READ] List volumes on a storage pool (ISOs, disk images, backups, templates).

Args: storage: Storage pool id (see storage_list). content: Optional filter — 'iso', 'images', 'backup', 'vztmpl'. target: Proxmox target name from config. node: Node name; omit to use the configured default node.

Inputs: storage (required), node, target, content.

storage_listA

Read-only

[READ] List storage pools on a node (id, type, total/used/avail bytes).

Args: target: Proxmox target name from config; omit to use the default. node: Node name; omit to use the target's configured default node.

Inputs: node, target.

task_logA

Read-only

[READ] Fetch the log lines of an async task by its UPID.

Returns {"lines": [...], "returned": N, "limit": L, "truncated": bool}. When truncated is true there are more lines than were returned — raise limit or narrow the query rather than assuming you have the whole log.

Args: upid: The task UPID. limit: Max log lines to return. target: Proxmox target name from config. node: Node the task runs on; omit to parse it from the UPID.

Inputs: upid (required), node, limit, target.

task_statusA

Read-only

[READ] Poll a Proxmox async task (clone / migrate / backup) by its UPID.

Use after a write that returned a task UPID to check completion instead of re-issuing the operation. The node is parsed from the UPID when omitted.

Args: upid: The task UPID returned by an async write tool. target: Proxmox target name from config. node: Node the task runs on; omit to parse it from the UPID.

Inputs: upid (required), node, target.

undo_applyA

Destructive

[WRITE][risk=medium] Apply a recorded undo by dispatching its inverse tool.

The inverse runs through its own governed tool, so its own risk tier is recorded on the audit row there. Pass dry_run=True to preview the inverse call without executing it. A token can only be applied once.

Args: undo_id: The undoId from undo_list (or an _undo_id in a write result). dry_run: If True, preview the inverse tool + params without running it. target: Passed through to the inverse tool when it accepts a target.

Inputs: undo_id (required), target, dry_run.

undo_listA

Read-only

[READ] List recorded, not-yet-applied undo tokens (most recent first).

Each entry names the original tool, the inverse tool that undo_apply would run, and a human note. Use the undoId with undo_apply.

Returns {"undos": [...], "returned": N, "limit": L, "truncated": bool}. truncated is measured (one extra row is fetched), not guessed from a length coincidence: when it is true there are MORE tokens than shown, so re-run with a higher limit rather than reporting the list as complete.

Each entry carries effectVerified. False means the original write lost its response, so the change it reverses is PROBABLE, not confirmed — check the live state before applying, and do not report the result as a restore of a state that may never have been reached.

Args: limit: Max rows to return (default 50, capped at 500). target: Unused (undo state is host-local); accepted for CLI uniformity.

Inputs: limit, target.

vm_agent_pingA

Read-only

[READ] Ping a VM's QEMU guest agent to check it is installed and responsive.

A non-running or absent agent yields responsive=False with an explanation rather than an error.

Args: vmid: Numeric Proxmox VM id. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target.

vm_backupA

Destructive

[WRITE] Create a vzdump backup of a VM/CT to a storage. Returns task UPID.

Args: vmid: Numeric Proxmox guest id (VM or container). storage: Backup-capable storage id (see storage_list / storage_content). mode: 'snapshot' (default, no downtime), 'suspend', or 'stop'. target: Proxmox target name from config. node: Node name; omit to auto-locate the guest.

Inputs: vmid (required), storage (required), mode, node, +1 more.

vm_cloneA

Destructive

[WRITE] Clone a VM to a new vmid. Returns the task UPID. Inverse: vm_delete(newid).

Cloning is asynchronous — poll completion with task_status, do not re-issue. Pass dry_run=True to preview.

Args: vmid: Source VM id to clone from. newid: New (unused) VM id for the clone. name: Optional name for the clone. dry_run: If True, preview without cloning. target: Proxmox target name from config. node: Node name; omit to auto-locate the source VM.

Inputs: vmid (required), newid (required), name, node, +2 more.

vm_configB

Read-only

[READ] Return a VM's config (cores, memory, ostype, boot order).

Args: vmid: Numeric Proxmox VM id. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target.

vm_deleteA

Destructive

[WRITE] Permanently destroy a VM. IRREVERSIBLE — no undo token.

Confirm with the user before calling. Audited to ~/.proxmox-aiops/audit.db. Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id to destroy. dry_run: If True, preview without destroying. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target, dry_run.

vm_firewall_rules_listA

Read-only

[READ] List the firewall rules attached to a VM.

Args: vmid: Numeric Proxmox VM id. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target.

vm_getA

Read-only

[READ] Return current status detail for a single VM by vmid.

Args: vmid: Numeric Proxmox VM id (see vm_list). target: Proxmox target name from config. node: Node name; omit to auto-locate the VM across nodes.

Inputs: vmid (required), node, target.

vm_listA

Read-only

[READ] List QEMU VMs with name, vmid, status, cpu, mem.

Scans the given node, the configured default node, or all cluster nodes. Use vm_get for full status of a single VM.

Args: target: Proxmox target name from config; omit to use the default. node: Node name; omit to use the target's configured node / all nodes.

Inputs: node, target.

vm_list_snapshotsB

Read-only

[READ] List snapshots for a VM (name + description).

Args: vmid: Numeric Proxmox VM id. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target.

vm_migrateA

Destructive

[WRITE] Migrate a VM to another node. Returns task UPID. Inverse: migrate back.

Asynchronous — poll completion with task_status. Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id. target_node: Destination node name. online: True (default) for live migration; False to migrate while stopped. dry_run: If True, preview without migrating. target: Proxmox target name from config. node: Source node name; omit to auto-locate the VM.

Inputs: vmid (required), target_node (required), node, online, +2 more.

vm_move_diskA

Destructive

[WRITE] Move a VM disk to another storage. Returns task UPID. Async.

Records a reverse move as the undo token when the source storage is known. Pass dry_run=True to read the disk's current placement and preview the move.

Args: vmid: Numeric Proxmox VM id. disk: Disk key, e.g. 'scsi0'. storage: Destination storage id. delete: Remove the source copy after the move completes. dry_run: If True, preview the from→to move without moving anything. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: disk (required), vmid (required), storage (required), node, +3 more.

vm_rebootA

Destructive

[WRITE] Reboot a VM (graceful). No undo token — reboot has no inverse.

Args: vmid: Numeric Proxmox VM id. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target.

vm_reconfigureA

Destructive

[WRITE] Change a VM's cores and/or memory (MiB). Inverse: restore prior values.

Provide at least one of cores / memory. The previous values are captured so the harness records a reverse reconfigure as the undo token. Pass dry_run=True to read the current cores/memory and preview the change.

Args: vmid: Numeric Proxmox VM id. cores: New vCPU core count (omit to leave unchanged). memory: New memory in MiB (omit to leave unchanged). dry_run: If True, preview what would change without applying it. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, cores, memory, +2 more.

vm_resize_diskA

Destructive

[WRITE] Grow a VM disk. GROW-ONLY — shrink requests are refused.

No undo token: growing a disk cannot be reversed. Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id. disk: Disk key, e.g. 'scsi0', 'virtio0', 'sata0'. size: '+G' increment (e.g. '+10G') or a larger absolute size. dry_run: If True, preview without resizing. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: disk (required), size (required), vmid (required), node, +2 more.

vm_shutdownA

Destructive

[WRITE] Graceful ACPI shutdown of a VM (vs the hard vm_stop). Inverse: vm_start.

Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id. dry_run: If True, preview without shutting down. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target, dry_run.

vm_snapshot_createA

Destructive

[WRITE] Create a named snapshot of a VM. Inverse: vm_snapshot_delete.

Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id. name: Snapshot name (must be unique for the VM). dry_run: If True, preview without creating. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: name (required), vmid (required), node, target, +1 more.

vm_snapshot_deleteA

Destructive

[WRITE] Delete a named snapshot from a VM. Destroys a rollback point — no undo.

Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id. name: Snapshot name to delete (see vm_snapshot_list). dry_run: If True, preview without deleting. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: name (required), vmid (required), node, target, +1 more.

vm_snapshot_rollbackA

Destructive

[WRITE] Roll a VM back to a snapshot. IRREVERSIBLE — discards changes since then.

No undo token (the discarded state cannot be recovered). Confirm with the user. Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id. name: Snapshot name to roll back to (see vm_list_snapshots). dry_run: If True, preview without rolling back. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: name (required), vmid (required), node, target, +1 more.

vm_startA

Destructive

[WRITE] Start a VM. Returns the Proxmox task UPID. Inverse: vm_stop.

Args: vmid: Numeric Proxmox VM id. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target.

vm_stopA

Destructive

[WRITE] Hard-stop (power off) a VM. Returns the task UPID. Inverse: vm_start.

This is an immediate power-off (not a graceful guest shutdown); the guest filesystem may be left dirty. Audited to ~/.proxmox-aiops/audit.db. Pass dry_run=True to preview.

Args: vmid: Numeric Proxmox VM id. dry_run: If True, preview without stopping. target: Proxmox target name from config. node: Node name; omit to auto-locate the VM.

Inputs: vmid (required), node, target, dry_run.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored 2026-10-17 02:56 across 43 tools

Disambiguation4/5

Most tools map to a distinct resource and action, and descriptions clarify overlaps such as vm_get/vm_config and vm_stop/vm_shutdown/vm_reboot. Some broader inventory tools overlap (cluster_resources vs node_list/vm_list/ct_list), but an agent can generally distinguish intended use.

Naming Consistency4/5

Names are almost entirely snake_case with predictable resource prefixes and verb/action patterns (vm_start, ct_stop, node_list, task_status). Minor deviations like vm_list_snapshots vs vm_snapshot_create and vm_firewall_rules_list keep it from perfect consistency.

Tool Count2/5

43 tools is well beyond the 25+ threshold and includes redundant read surfaces such as cluster_resources vs individual list tools, plus backup_list overlapping storage_content. Proxmox is broad, but the set still feels over-expanded and would benefit from consolidation.

Completeness3/5

Core VM lifecycle coverage is strong (start/stop/shutdown/reboot/clone/migrate/snapshot/backup/restore/disk operations), but CT coverage is mostly limited to list/start/stop. VM creation from scratch and firewall rule write operations are absent, leaving notable lifecycle gaps.

Maintenance

ActivityNo data

ResponsivenessOutdated data

Resources

Related MCP Connectors

microservices.sh
sh.microservices
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Cloud Platforms Agent Orchestration Developer Tools
21
https://api.microservices.sh/mcp
mttrly
com.mttrly
AI-powered incident management and server monitoring via MCP.
Monitoring Observability
3
https://api.mttrly.com/mcp
server
com.devopness.mcp
Devopness MCP server for DevOps happiness! Empower AI Agents to deploy apps and infra, to any cloud.
Cloud Platforms CI/CD & DevOps Developer Tools
3
https://mcp.devopness.com/mcp/
Os Automation McpC
io.github.varvararatta
MCP server for OS Automation
OS Automation Command Line
2
https://os-automation-mcp.mcpize.run/mcp

Related MCP Servers

mcp-server-proxmox
Virtualization Cloud Platforms
heybearc
A
license
B
quality
C
maintenance
A Model Context Protocol (MCP) server for Proxmox Virtual Environment that enables AI assistants to manage virtual machines, containers, nodes, and resources through natural language interactions.
Updated 17 days ago (2026-10-26 12:16 UTC)
10
4
MIT
proxmox-mcp
Virtualization Cloud Platforms
nick-holmquist
A
license
Not graded
quality
D
maintenance
MCP server for full Proxmox VE management - VMs, containers, storage, backups, networking.
Updated 4 months ago (2026-07-08 15:42 UTC)
2
MIT
proxmox-mcp
Virtualization Cloud Platforms
LeonRLewis
F
license
Not graded
quality
D
maintenance
MCP server for Proxmox VE that enables AI assistants to inspect and manage LXC containers, VMs, snapshots, and resource pools via the Proxmox API.
Updated 4 months ago (2026-06-30 21:52 UTC)
-
pve-mcp
Virtualization Shell Access
tiancode
A
license
A
quality
D
maintenance
MCP server for managing Proxmox VE resources, VM/CT lifecycle, snapshots, backups, and clones via natural language.
Updated 4 months ago (2026-07-06 23:39 UTC)
23
MIT

Proxmox AIops

What works

What this tool does, and does not, decide

Quick start

As a Claude Code plugin

As an OpenClaw plugin

As a CLI or standalone MCP server

Audit & safety

Contributing & feature requests

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

mcp-server-proxmox

proxmox-mcp

proxmox-mcp

pve-mcp