MCP PVE is a server for managing Proxmox VE resources such as virtual machines, containers, and networking through natural language interfaces. It supports multiple access tiers and offers a variety of tools for interacting with the Proxmox VE REST API.
From the registry: Manage Proxmox VE through AI assistants
Please install the `mcp-pve` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Proxmox VE API token** — Create API token in PVE UI: Datacenter > Permissions > API Tokens
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@samik081/mcp-pve"]
- required environment variables:
- `PVE_BASE_URL`: URL of your PVE instance (example: `https://pve.example.com:8006`)
- `PVE_TOKEN_ID`: API token ID (user@realm!tokenname) (example: `root@pam!mcp`)
- `PVE_TOKEN_SECRET`: API token UUID secret (example: `<your-token-secret>`)
- optional environment variables:
- `PVE_ACCESS_TIER`: read-only, read-execute, or full (example: `full`)
- `PVE_CATEGORIES`: Comma-separated category allowlist (example: `qemu,lxc`)
- `PVE_VERIFY_SSL`: Verify SSL certificates (example: `false`)
- `MCP_TRANSPORT`: Transport mode: stdio or http (example: `stdio`)
Note: Also supports HTTP transport via MCP_TRANSPORT=http.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.PVE_BASE_URLrequiredURL of your PVE instance (e.g. `https://pve:8006`)PVE_TOKEN_IDrequiredAPI token ID (`user@realm!tokenname`)PVE_TOKEN_SECRETrequiredAPI token UUID secretReal-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.
Gives AI development tools Firebase-specific capabilities and expertise.
All Azure MCP tools to create a seamless connection between AI agents and Azure services.
MCP tools for interacting with Microsoft Fabric