Proxmox VE MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROXMOX_URL | Yes | HTTPS origin, e.g. https://pve.example.com:8006; /api2/json suffix accepted | |
| PROXMOX_TIMEOUT | No | HTTP timeout in seconds, greater than 0 and at most 300 | 30 |
| PROXMOX_TOKEN_ID | Yes | Full ID, e.g. mcp@pve!assistant | |
| PROXMOX_CA_BUNDLE | No | PEM CA bundle path | |
| PROXMOX_READ_ONLY | No | Omit write tools and block writes in the API client | true |
| PROXMOX_HTTP_TOKEN | No | Required for HTTP; separate random bearer token, 32–256 URL-safe characters | |
| PROXMOX_VERIFY_SSL | No | Certificate and hostname verification | true |
| PROXMOX_TOKEN_SECRET | Yes | API token secret | |
| PROXMOX_OUTPUT_FIELDS | No | JSON object replacing selected output views' field lists; see output policy | |
| PROXMOX_ALLOW_TASK_LOGS | No | Expose task-log tool; logs may contain arbitrary sensitive text | false |
| PROXMOX_ALLOW_RAW_CONFIG | No | Expose full guest configuration tool, with known secret fields redacted | false |
| PROXMOX_ALLOW_DESTRUCTIVE | No | Enable force-stop, snapshot delete and rollback; requires writes enabled | false |
| PROXMOX_MAX_REQUEST_BYTES | No | Maximum MCP HTTP request body (1 KiB–4 MiB) | 1048576 |
| PROXMOX_OPERATION_TIMEOUT | No | Total operation/HTTP-request deadline in seconds, including slow response streams (0–300, exclusive of 0) | 30 |
| PROXMOX_MAX_RESPONSE_BYTES | No | Maximum upstream response size; enforced while streaming (1 KiB–128 MiB) | 4194304 |
| PROXMOX_MAX_CONCURRENT_REQUESTS | No | Concurrent HTTP requests and concurrent tool API calls per server instance (1–64); excess work is rejected | 8 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_versionA | Get the connected Proxmox VE version and release. |
| get_cluster_statusA | Get cluster quorum and member status (also useful on standalone nodes). |
| list_resourcesB | List cluster resources visible to this token; vm includes QEMU and LXC. |
| list_nodesA | List nodes with uptime, CPU, and memory usage. |
| get_node_statusA | Get a node's CPU, memory, swap, load, and uptime. |
| list_storageB | List storage availability and capacity on a node. |
| list_storage_contentA | List volumes, backups, ISOs, or container templates in a storage. |
| list_guestsA | List QEMU virtual machines or LXC containers on one node. |
| get_guest_statusA | Get a guest's power state and current resource usage. |
| get_guest_configB | Read an allowlisted configuration summary; omitted fields are not unset. |
| list_snapshotsB | List guest snapshots and their parent relationships. |
| list_tasksA | List recent node tasks; use start and limit for pagination. |
| get_task_statusA | Poll a task; completion succeeds only if status=stopped and exitstatus=OK. |
| get_next_vmidA | Find an available VM ID. This does not reserve it; concurrent users may claim it. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Most tools target distinct resources such as version, cluster, nodes, storage, guests, and tasks. The only potential confusion is list_nodes versus get_node_status, which both expose node CPU/memory/uptime, but the added detail and singular/plural distinction are clarified in the descriptions.
All tools follow a consistent list_ and get_ convention: list_ prefixes for collections and get_ prefixes for singular resources or statuses. There are no mixed naming styles or vague verbs.
14 tools sits within the ideal well-scoped range and each one serves a clear monitoring or query purpose. No redundant or trivial tools are present.
Read-only coverage is solid: cluster, nodes, storage, guests, snapshots, and tasks are all queryable. However, there are no lifecycle operations to create, modify, delete, start, or stop guests, and get_next_vmid strongly implies provisioning without a corresponding create tool, creating a dead-end.