Skip to content
cccskills
FreePublished on GitHub

proxmox-mcp-tools

Comprehensive MCP tool reference for Proxmox Virtual Environment management - 92 tools across 14 domains including QEMU VMs, LXC containers, cluster operations, storage, networking, Ceph, certificates, ACME, and notifications

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (17)

  • SKILL.md9.7 KB
  • references/proxmox-access-control.md9.0 KB
  • references/proxmox-acme.md2.1 KB
  • references/proxmox-ceph.md5.1 KB
  • references/proxmox-certificates.md2.4 KB
  • references/proxmox-cluster.md18.7 KB
  • references/proxmox-lxc.md10.8 KB
  • references/proxmox-mcp.md5.1 KB
  • references/proxmox-networking.md7.2 KB
  • references/proxmox-nodes.md15.7 KB
  • references/proxmox-notifications.md2.0 KB
  • references/proxmox-pools.md1.4 KB
  • references/proxmox-snapshots-backups.md6.2 KB
  • references/proxmox-storage.md8.8 KB
  • references/proxmox-vm-lxc-shared.md15.1 KB
  • references/proxmox-vm.md13.4 KB
  • references/proxmox-workflows.md7.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Proxmox MCP Tools Reference

AI Agent Skill: Complete reference for 92 Proxmox Virtual Environment management tools via Model Context Protocol

Overview

This skill teaches AI agents how to use the @bldg-7/proxmox-mcp server, which provides 92 comprehensive tools for managing Proxmox VE infrastructure through the Model Context Protocol (MCP).

What you'll learn:

  • How to connect to Proxmox VE via MCP
  • 92 tools organized into 14 functional domains
  • Permission model (basic vs elevated operations)
  • Common workflows and patterns
  • Troubleshooting API quirks

Target audience: AI agents managing Proxmox infrastructure, automating VM/LXC provisioning, monitoring cluster health, or performing operational tasks.


Quick Start

Connection Setup

Required Environment Variables:

PROXMOX_HOST=pve.example.com
PROXMOX_TOKEN_NAME=mytoken
PROXMOX_TOKEN_VALUE=abc123-def456-ghi789

Optional Configuration:

PROXMOX_USER=root@pam          # Default: root@pam
PROXMOX_SSL_MODE=verify         # strict|verify|insecure (default: strict)
PROXMOX_ALLOW_ELEVATED=true     # Enable create/modify/delete (default: false)
PROXMOX_PORT=8006               # Default: 8006

SSH Configuration (for proxmox_lxc_exec):

PROXMOX_SSH_ENABLED=true        # Enable SSH-based LXC exec (default: false)
PROXMOX_SSH_HOST=pve.example.com # SSH host (falls back to PROXMOX_HOST)
PROXMOX_SSH_PORT=22             # SSH port (default: 22)
PROXMOX_SSH_USER=root           # SSH username (default: root)
PROXMOX_SSH_KEY_PATH=~/.ssh/id_rsa # Path to SSH private key (required when SSH enabled)
PROXMOX_SSH_NODE=pve1           # Proxmox node name (required when SSH enabled)
PROXMOX_SSH_HOST_KEY_FINGERPRINT=sha256:... # Optional host key verification

Permission Model

LevelOperationsEnv Var Required
BasicRead-only (list, get, status)None
Elevated 🔒Create, modify, deletePROXMOX_ALLOW_ELEVATED=true

102 basic tools + 207 elevated tools = 92 total

SSL Modes

  • strict: Full certificate verification (production)
  • verify: Allow self-signed certificates (common for Proxmox)
  • insecure: No verification (development only)

Tool Categories

DomainToolsKey OperationsReference
Nodes47Node status, network config, system ops, console accessproxmox-nodes.md
QEMU VMs26VM lifecycle, config, disks, network, commandsproxmox-vm.md
LXC Containers20Container lifecycle, config, mount points, network, execproxmox-lxc.md
VM/LXC Shared22Agent, firewall, migration (works for both)proxmox-vm-lxc-shared.md
Snapshots & Backups14Create/restore snapshots, backup jobsproxmox-snapshots-backups.md
Storage16Storage config, content, file operations, node disksproxmox-storage.md
Networking20SDN (VNets, zones, controllers, subnets)proxmox-networking.md
Cluster54HA, firewall, aliases, ipsets, backup jobs, replication, configproxmox-cluster.md
Access Control25Users, groups, roles, ACLs, domains, API tokensproxmox-access-control.md
Ceph16Ceph OSDs, MONs, MDS, pools, filesystemsproxmox-ceph.md
Pools5Resource pool managementproxmox-pools.md
Certificates7Node certificates, custom SSL, ACME orderingproxmox-certificates.md
ACME8ACME accounts, plugins, directoriesproxmox-acme.md
Notifications5Notification targets, SMTP/Gotify testingproxmox-notifications.md

Total: 92 tools


Common Workflows

1. Create and Configure a VM

1. proxmox_get_next_vmid → Get available VM ID
2. proxmox_create_vm → Create VM with basic config
3. proxmox_vm_disk → Attach storage
4. proxmox_guest_network → Configure network
5. proxmox_guest_start → Power on
6. proxmox_guest_status → Verify running

2. Clone VM for Testing

1. proxmox_guest_config → Review source VM
2. proxmox_guest_snapshot → Snapshot before clone
3. proxmox_guest_clone → Create clone (full or linked)
4. proxmox_guest_start → Start cloned VM

3. Backup and Restore

# Backup
1. proxmox_backup → Create backup to storage
2. proxmox_backup → Verify backup exists

# Restore
1. proxmox_backup → Find backup file
2. proxmox_backup → Restore to new/existing VM

4. Migrate VM Between Nodes

1. proxmox_node → List available target nodes
2. proxmox_guest_status → Check VM is running
3. proxmox_guest_migrate → Live or offline migration
4. proxmox_guest_status → Verify on new node

5. Configure HA for Critical VMs

1. proxmox_ha_group → Define node group
2. proxmox_ha_resource → Add VM to HA
3. proxmox_ha_resource → Monitor HA state

6. Monitor Cluster Health

1. proxmox_cluster → Overall cluster state
2. proxmox_node → Node-level health
3. proxmox_node_task → Recent operations
4. proxmox_ceph → Ceph cluster (if used)

7. Manage Storage

1. proxmox_storage_config → Available storage
2. proxmox_storage_content → Browse content
3. proxmox_storage_content → Upload ISO/template
4. proxmox_storage_content → Clean old backups

More workflows: See proxmox-workflows.md


Troubleshooting Quick Reference

1. Connection Refused

Symptom: ECONNREFUSED or timeout
Fix: Verify PROXMOX_HOST, check port 8006, firewall rules

2. Authentication Failed

Symptom: 401 Unauthorized
Fix: Verify token name/value, ensure token has permissions in Proxmox

3. SSL Certificate Errors

Symptom: UNABLE_TO_VERIFY_LEAF_SIGNATURE
Fix: Use PROXMOX_SSL_MODE=verify for self-signed certs

4. Permission Denied

Symptom: 🚫 Permission Denied
Fix: Set PROXMOX_ALLOW_ELEVATED=true for create/modify/delete operations

5. VM Not Found (500 instead of 404)

Symptom: API returns 500 error for missing VM
Fix: This is a Proxmox API quirk - treat 500 as "not found" in some contexts

More troubleshooting: See proxmox-troubleshooting.md


Tool Response Format

All tools return structured MCP responses:

Success:

{
  "content": [{"type": "text", "text": "✅ Operation successful\n\n• Details..."}],
  "isError": false
}

Error:

{
  "content": [{"type": "text", "text": "❌ Error: Reason..."}],
  "isError": true
}

Permission Denied:

{
  "content": [{"type": "text", "text": "🚫 Permission Denied: Set PROXMOX_ALLOW_ELEVATED=true"}],
  "isError": true
}

References

Domain-Specific Documentation

Operational Guides


Usage Tips

  1. Always check permissions: Use basic tools first, only enable elevated when needed
  2. Verify before destructive ops: Use get_vm_status before delete_vm
  3. Use snapshots: Create snapshot before major changes
  4. Monitor tasks: Use get_node_tasks to track long-running operations
  5. Handle 500 errors: Proxmox sometimes returns 500 instead of 404 - check context
  6. SSL mode for self-signed: Most Proxmox installations use self-signed certs - use verify mode

License

MIT License - Part of @bldg-7/proxmox-mcp package

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.

The English summary is being prepared. Showing the original description.

jcasnellie69/homelab-config2Updated Oct 16, 2026

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

The English summary is being prepared. Showing the original description.

jcasnellie69/homelab-config2Updated Oct 16, 2026

Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

The English summary is being prepared. Showing the original description.

jcasnellie69/homelab-config2Updated Oct 16, 2026

Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.

The English summary is being prepared. Showing the original description.

jcasnellie69/homelab-config2Updated Oct 16, 2026

Use when adding, modifying, or reviewing VS Code configuration policies. Covers the full policy lifecycle from registration to export to platform-specific artifacts. Run on ANY change that adds a `policy:` field to a configuration property.

The English summary is being prepared. Showing the original description.

jcasnellie69/homelab-config2Updated Oct 16, 2026

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)

The English summary is being prepared. Showing the original description.

jcasnellie69/homelab-config2Updated Oct 16, 2026

See all skills by jcasnellie69

Report a problem with this skill