io.github.antonio-mello-ai/mcp-proxmox

AI 与智能体

by antonio-mello-ai

通过 AI 助手管理 Proxmox VE 集群,支持虚拟机、容器等资源的操作与维护。

什么是 io.github.antonio-mello-ai/mcp-proxmox

通过 AI 助手管理 Proxmox VE 集群,支持虚拟机、容器等资源的操作与维护。

README

mcp-proxmox

<!-- mcp-name: io.github.antonio-mello-ai/mcp-proxmox --> <a href="https://glama.ai/mcp/servers/antonio-mello-ai/mcp-proxmox"> <img width="380" height="200" src="https://glama.ai/mcp/servers/antonio-mello-ai/mcp-proxmox/badge" alt="mcp-proxmox MCP server" /> </a>

MCP server for managing Proxmox VE clusters through AI assistants like Claude, Cursor, and Cline.

Provision, manage, and monitor your entire Proxmox infrastructure through natural language. Create VMs and containers, manage snapshots, browse storage, and more.

Quick Start

bash
# Run directly with uvx (no install needed)
uvx mcp-proxmox

# Or install with pip
pip install mcp-proxmox

Configuration

Set these environment variables (or create a .env file):

bash
PROXMOX_HOST=192.168.1.100          # Your Proxmox VE host
PROXMOX_TOKEN_ID=user@pam!mcp       # API token ID
PROXMOX_TOKEN_SECRET=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx  # API token secret

Optional:

bash
PROXMOX_PORT=8006                   # Default: 8006
PROXMOX_VERIFY_SSL=false            # Default: false

Creating a Proxmox API Token

  1. Log into your Proxmox web UI
  2. Go to Datacenter > Permissions > API Tokens
  3. Click Add and create a token for your user
  4. Uncheck "Privilege Separation" for full access, or assign specific permissions:
    • VM.Audit — read VM/CT status and config
    • VM.PowerMgmt — start/stop/shutdown/reboot
    • VM.Snapshot — create/rollback/delete snapshots
    • VM.Allocate — create/delete/clone VMs and containers
    • VM.Clone — clone operations
    • Datastore.Audit — list storages and browse content
    • Datastore.AllocateSpace — allocate disk space for new VMs/CTs
    • Sys.Audit — read node status and tasks
    • VM.Config.Disk — resize disks
    • VM.Config.CPU — change CPU allocation
    • VM.Config.Memory — change memory allocation
    • VM.Monitor — access QEMU monitor (for metrics)
    • VM.Migrate — migrate VMs/CTs between nodes
    • Sys.Modify — manage firewall rules
    • VM.Config.Cloudinit — configure cloud-init parameters

Integration

Claude Desktop

Add to ~/.claude/claude_desktop_config.json:

json
{
  "mcpServers": {
    "proxmox": {
      "command": "uvx",
      "args": ["mcp-proxmox"],
      "env": {
        "PROXMOX_HOST": "192.168.1.100",
        "PROXMOX_TOKEN_ID": "user@pam!mcp",
        "PROXMOX_TOKEN_SECRET": "your-token-secret"
      }
    }
  }
}

Claude Code

Add to .claude/settings.json or ~/.claude/settings.json:

json
{
  "mcpServers": {
    "proxmox": {
      "command": "uvx",
      "args": ["mcp-proxmox"],
      "env": {
        "PROXMOX_HOST": "192.168.1.100",
        "PROXMOX_TOKEN_ID": "user@pam!mcp",
        "PROXMOX_TOKEN_SECRET": "your-token-secret"
      }
    }
  }
}

Cursor

Add to Cursor Settings > MCP with the same configuration as above.

Available Tools

Discovery

ToolDescription
list_nodesList all cluster nodes with CPU, memory, and uptime
get_node_statusDetailed node info: CPU model, memory, disk, versions
list_vmsList QEMU VMs (filter by node or status)
list_containersList LXC containers (filter by node or status)
get_guest_statusDetailed VM/CT status by VMID (auto-detects type and node)

Lifecycle

ToolDescription
start_guestStart a stopped VM or container
stop_guestForce-stop (requires confirmation)
shutdown_guestGraceful ACPI/init shutdown
reboot_guestReboot (requires confirmation)

Storage

ToolDescription
list_storagesList storage pools with capacity and usage (filter by node)
list_storage_contentBrowse ISOs, templates, backups, and disk images

Provisioning

ToolDescription
create_vmCreate a QEMU VM with configurable CPU, memory, disk, ISO, and network
create_containerCreate an LXC container from a template
clone_guestClone a VM or CT (full or linked clone, cross-node support)
delete_guestPermanently delete a stopped VM or CT (requires confirmation)

Backup & Restore

ToolDescription
list_backupsList backup files (filter by node, storage, or VMID)
create_backupCreate a vzdump backup (snapshot/suspend/stop modes, zstd/lzo/gzip)
restore_backupRestore a VM or CT from a backup file (requires confirmation)

Command Execution

ToolDescription
exec_commandRun a command inside a QEMU VM via guest agent

Note: exec_command requires qemu-guest-agent installed and running inside the VM. Not supported for LXC containers (Proxmox API limitation).

Snapshots

ToolDescription
list_snapshotsList all snapshots for a VM/CT
create_snapshotCreate a new snapshot
rollback_snapshotRollback to a snapshot (requires confirmation)
delete_snapshotDelete a snapshot (requires confirmation)

Network

ToolDescription
list_networksList bridges, bonds, and physical interfaces on a node

Resize

ToolDescription
resize_guestResize CPU, memory, and/or disk of a VM or container (requires confirmation)

Monitoring

ToolDescription
get_guest_metricsCPU, memory, network, disk I/O over time
list_tasksRecent tasks on a node (backups, migrations, etc.)

Firewall

ToolDescription
list_firewall_rulesList firewall rules for a VM/CT, node, or the cluster
add_firewall_ruleAdd a firewall rule (action, direction, protocol, port, source/dest)
delete_firewall_ruleDelete a firewall rule by position (requires confirmation)

Migration

ToolDescription
migrate_guestLive or offline migrate a VM/CT to another node (requires confirmation)

Templates & Cloud-init

ToolDescription
list_templatesList all VM templates available for cloning
create_templateConvert a stopped VM into a template (requires confirmation, irreversible)
configure_cloud_initSet user, password, SSH keys, IP config, and DNS on a VM

Safety

Destructive operations (stop_guest, reboot_guest, rollback_snapshot, delete_snapshot, delete_guest, resize_guest, restore_backup, delete_firewall_rule, migrate_guest, create_template) require explicit confirm=true. The first call returns a warning describing the impact; only a second call with confirmation executes the action.

Examples

Once connected, you can ask your AI assistant:

  • "List all my VMs and their status"
  • "How much memory is VM 100 using?"
  • "Shut down container 105"
  • "Create a snapshot of VM 200 called before-upgrade"
  • "Show me the CPU usage of VM 100 over the last day"
  • "What tasks ran on node pve recently?"
  • "Which VMs are stopped?"
  • "What storage pools do I have and how full are they?"
  • "Show me available ISO images"
  • "Create a new Ubuntu VM with 4 cores and 8GB RAM"
  • "Clone VM 100 as a test environment"
  • "Create a Debian container from template"
  • "Delete the old test VM 999"
  • "Back up VM 100 to the zfs-backup-storage"
  • "Show me all backups for VM 200"
  • "Restore the latest backup of container 101"
  • "Run 'df -h' on VM 100"
  • "Check if nginx is running on VM 200"
  • "Show me the network bridges on node pve"
  • "Give VM 100 more CPU — bump it to 8 cores"
  • "Add 50GB of disk to container 101"
  • "Show me the firewall rules on VM 100"
  • "Allow TCP port 443 on container 101"
  • "Migrate VM 200 to node pve2"
  • "List all templates in the cluster"
  • "Convert VM 102 into a template"
  • "Set cloud-init on VM 100: user admin, IP dhcp, DNS 8.8.8.8"

Troubleshooting

Missing required environment variables

This error means one or more required connection settings are not available to the server process. Copy .env.example to .env, then set PROXMOX_HOST, PROXMOX_TOKEN_ID, and PROXMOX_TOKEN_SECRET. If you configure an MCP client directly, make sure the same variables are present in that client's env block.

403 Permission check failed

A 403 usually means the API token is valid but does not have enough Proxmox privileges for the requested operation. Revisit Creating a Proxmox API Token and either uncheck "Privilege Separation" for full access or assign the specific privileges listed there, such as VM.Audit, VM.PowerMgmt, VM.Snapshot, or storage permissions for datastore operations.

exec_command fails for guest-agent or LXC reasons

exec_command only works for QEMU VMs with qemu-guest-agent installed and running inside the guest. If the tool reports that the QEMU guest agent is not responding, start or install the agent in the VM and retry. LXC containers are not supported by this Proxmox API path, so use another container access method instead.

Self-signed certificate or connection errors

Proxmox commonly runs on port 8006, so check that PROXMOX_HOST and PROXMOX_PORT point to the same endpoint you use for the Proxmox web UI. For homelab clusters with self-signed certificates, leave PROXMOX_VERIFY_SSL=false or set it explicitly. Use PROXMOX_VERIFY_SSL=true only when the Proxmox certificate chains to a CA trusted by your runtime.

Development

bash
git clone https://github.com/antonio-mello-ai/mcp-proxmox.git
cd mcp-proxmox
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

# Run tests
pytest

# Lint
ruff check src/ tests/
ruff format src/ tests/

# Type check
mypy src/

License

MIT

常见问题

io.github.antonio-mello-ai/mcp-proxmox 是什么?

通过 AI 助手管理 Proxmox VE 集群,支持虚拟机、容器等资源的操作与维护。

相关 Skills

Claude接口

by anthropics

Universal
热门

面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。

想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心

AI 与智能体
未扫描164.6k

RAG架构师

by alirezarezvani

Universal
热门

聚焦生产级RAG系统设计与优化,覆盖文档切块、检索链路、索引构建、召回评估等关键环节,适合搭建可扩展、高准确率的知识库问答与检索增强应用。

面向RAG落地,把知识库、向量检索和生成链路系统串联起来,做架构设计时更清晰,也更少踩坑。

AI 与智能体
未扫描23.3k

多智能体架构

by alirezarezvani

Universal
热门

聚焦多智能体系统架构设计,梳理 Supervisor、Swarm、分层和 Pipeline 等模式,覆盖角色定义、通信协作与性能评估,适合规划稳健可扩展的 AI agent 编排方案。

帮你系统解决多智能体应用的架构设计与协同编排难题,适合构建复杂 AI 工作流,成熟度高、社区认可也很亮眼。

AI 与智能体
未扫描23.3k

相关 MCP Server

知识图谱记忆

编辑精选

by Anthropic

热门

Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。

帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。

AI 与智能体
89.0k

顺序思维

编辑精选

by Anthropic

热门

Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。

这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。

AI 与智能体
88.1k

by deusdata

热门

持久化的代码库知识图谱,可跨会话保留上下文,在 session 重启或上下文压缩后仍能继续使用。

专治 AI 编程助手“会话失忆”,把代码库沉淀为持久知识图谱,重启或压缩上下文后也能无缝续上开发状态。

AI 与智能体
26.9k

评论