ProxmoxMCP-Plus
Proxmox VE MCP server for VMs, LXCs, snapshots, backups, storage, and cluster operations.
ProxmoxMCP-Plus
Control Proxmox VE from LLMs, AI agents, MCP clients, and OpenAPI tooling with one safer interface for VMs, LXCs, backups, snapshots, ISOs, container commands, and persistent long-running jobs.
Quick Start | Demo | Capabilities | Scenarios | Docs | Wiki
Platform Overview
ProxmoxMCP-Plus provides a unified Proxmox VE control surface in two forms:
MCPfor Claude Desktop, Open WebUI, and other LLM or AI agent clientsOpenAPIfor HTTP automation, dashboards, internal tools, and no-code workflows
Instead of stitching together raw Proxmox API calls, shell scripts, and custom glue code, the project consolidates core operational workflows in one interface:
- VM and LXC lifecycle actions
- snapshot create, rollback, and delete
- backup and restore workflows
- ISO download and cleanup
- node, storage, and cluster inspection
- SSH-backed container command execution with guardrails
- persistent job tracking for async Proxmox tasks
Design Priorities
ProxmoxMCP-Plus is designed for the gap between low-level Proxmox primitives and production-facing workflows that need to be usable from both LLM-native clients and standard automation systems.
Dual-surface architecture: MCP for conversational workflows, OpenAPI for standard automationOperator-oriented scope: focused on day-2 tasks, not just raw low-level endpointsSafer-by-default execution: auth, command policy, and explicit execution pathsObservable long-running workflows: stableJob IDs, progress polling, retry, cancel, and audit historyOperationally grounded: documented workflows are backed by live-environment verification
Quick Start
1. Prepare Proxmox access
Read the official Proxmox docs first if you are setting up a fresh lab:
- Proxmox VE installation guide
- Proxmox VE API guide
- Proxmox VE administration guide
- Linux Container guide
Create it from the example first:
cp proxmox-config/config.example.json proxmox-config/config.json
Then edit proxmox-config/config.json with your environment. At minimum, it needs:
proxmox.hostproxmox.portauth.userauth.token_nameauth.token_value
Add an ssh section as well if you want container command execution.
Add a jobs section if you want job state persisted somewhere other than the default local SQLite file.
For real live verification, use a separate proxmox-config/config.live.json created from proxmox-config/config.live.example.json.
Do not point live e2e at a placeholder or local-only config.json unless you intentionally run a local API tunnel there.
Minimal job persistence config:
{
"jobs": {
"sqlite_path": "proxmox-jobs.sqlite3"
}
}
2. Choose one runtime path
PyPI
uvx proxmox-mcp-plus
Or install it first:
pip install proxmox-mcp-plus
proxmox-mcp-plus
Docker / GHCR
docker run --rm -p 8811:8811 \
-v "$(pwd)/proxmox-config/config.json:/app/proxmox-config/config.json:ro" \
ghcr.io/rekklesna/proxmoxmcp-plus:latest
Source
git clone https://github.com/RekklesNA/ProxmoxMCP-Plus.git
cd ProxmoxMCP-Plus
uv venv
uv pip install -e ".[dev]"
python main.py
3. Run the HTTP/OpenAPI surface
docker compose up -d
curl -f http://localhost:8811/health
curl http://localhost:8811/openapi.json
4. Point an MCP client at the server
Minimal MCP client shape:
{
"mcpServers": {
"proxmox-mcp-plus": {
"command": "python",
"args": ["/path/to/ProxmoxMCP-Plus/main.py"],
"env": {
"PROXMOX_MCP_CONFIG": "/path/to/ProxmoxMCP-Plus/proxmox-config/config.json"
}
}
}
}
Client-specific examples for Claude Desktop and Open WebUI are in the Integrations Guide.
Demo
This demo is a direct terminal recording of qwen/qwen3.6-plus driving a live MCP session in English against a local Proxmox lab. It shows natural-language control flowing through MCP tools to create and start an LXC, execute a container command, and confirm the HTTP /health surface.

Core Platform Capabilities
ProxmoxMCP-Plus provides a unified control surface for the operational tasks most teams actually need in Proxmox VE. The same server can expose these workflows to MCP clients for LLM and AI-agent use cases, and to HTTP consumers through the OpenAPI bridge.
Supported workflow areas:
| Capability Area | Availability |
|---|---|
| VM create / start / stop / delete | Available |
| VM snapshot create / rollback / delete | Available |
| Backup create / restore | Available |
| ISO download / delete | Available |
| LXC create / start / stop / delete | Available |
| Container SSH-backed command execution | Available |
| Container authorized_keys update | Available |
| Persistent job store for long tasks | Available |
MCP job control tools (list_jobs, get_job, poll_job, cancel_job, retry_job) | Available |
OpenAPI /jobs endpoints with explicit status codes | Available |
Local OpenAPI /health and schema | Available |
Docker image build and /health | Available |
Validation and contract entry points in this repository:
pytest -qtests/integration/test_real_contract.pytests/scripts/run_real_e2e.py
tests/scripts/run_real_e2e.py now prefers proxmox-config/config.live.json or PROXMOX_MCP_E2E_CONFIG.
This avoids accidentally running live checks against a machine-specific default config.json.
Long-Running Jobs
Many Proxmox mutations are asynchronous. ProxmoxMCP-Plus now wraps those tasks in a persistent job layer so MCP and OpenAPI clients can track them through a stable Job ID.
Long-running tools such as VM create/start/stop, container create/start/stop, snapshot changes, backup/restore, and ISO download/delete now return both:
task_id: the raw ProxmoxUPIDjob_id: the stable server-side job record
The job record stores:
- current status and progress
- retry count and prior
UPIDs - latest result payload or failure reason
- audit history for create, poll, retry, and cancel actions
By default the job store persists to proxmox-jobs.sqlite3, so restart does not lose in-flight or completed job metadata.
MCP Job Tools
list_jobsget_jobpoll_jobcancel_jobretry_job
OpenAPI Job Routes
When the OpenAPI proxy is enabled and a local JobStore is available, these routes are exposed directly:
| Path | Method | Purpose | Success Codes |
|---|---|---|---|
/jobs | GET | list persisted jobs | 200 |
/jobs/{job_id} | GET | fetch one job, optional refresh=true | 200 |
/jobs/{job_id}/poll | POST | refresh status from Proxmox | 200 |
/jobs/{job_id}/cancel | POST | request cancellation | 202 |
/jobs/{job_id}/retry | POST | replay a stored retry recipe | 202 |
Common error codes:
404: unknownjob_id409: the job exists but that operation is not valid now503: the OpenAPI proxy was started without a localJobStore
tests/scripts/run_real_e2e.py now prefers proxmox-config/config.live.json or PROXMOX_MCP_E2E_CONFIG.
This avoids accidentally running live checks against a machine-specific default config.json.
Positioning Against Common Approaches
| Capability | Official Proxmox API | One-off scripts | ProxmoxMCP-Plus |
|---|---|---|---|
| MCP for LLM and AI agent workflows | No | No | Yes |
| OpenAPI surface for standard HTTP tooling | No | Usually no | Yes |
| VM and LXC operations in one interface | Low-level only | Depends | Yes |
| Snapshot, backup, and restore workflows | Low-level only | Depends | Yes |
| Persistent async job tracking and retry | No | Rare | Yes |
| Container command execution with policy controls | No | Custom only | Yes |
| Docker distribution path | No | Rare | Yes |
| Repository-level live-environment verification | N/A | Rare | Yes |
Scenario Templates
Ready-to-copy examples live in docs/examples/:
These are written for both human operators and LLM-driven usage.
Documentation
The README is intentionally optimized for fast GitHub comprehension. Longer operational docs live in docs/wiki/ and can also be published to the GitHub Wiki.
| If you need to... | Start here |
|---|---|
| Understand the project and deployment flow | Wiki Home |
| Configure and run against a Proxmox environment | Operator Guide |
| Connect Claude Desktop or Open WebUI | Integrations Guide |
| Install from MCP-aware IDEs and agents | Agent Installation |
| Review security and command policy | Security Guide |
| Inspect tool parameters, prerequisites, and behavior | API & Tool Reference |
| Debug startup, auth, or health issues | Troubleshooting |
| Work on the codebase or release it | Developer Guide |
| Review release and upgrade notes | Release & Upgrade Notes |
Published wiki:
Repo Layout
src/proxmox_mcp/: MCP server, config loading, security, OpenAPI bridgemain.py: MCP entrypoint for local and client-driven usagedocker-compose.yml: HTTP/OpenAPI runtimerequirements/: auxiliary dependency sources and runtime install listsscripts/: helper startup scripts for local workflowstests/scripts/run_real_e2e.py: live Proxmox and Docker/OpenAPI pathtests/: unit and integration coveragedocs/examples/: scenario-driven prompts and HTTP examplesdocs/wiki/: longer-form operator, integration, and reference docs
Development Checks
pytest -q
ruff check .
mypy src tests main.py tests/scripts/run_real_e2e.py
python -m build
License
Server Terkait
Cyclops MCP
Manage Kubernetes applications safely by creating and updating Cyclops Modules for AI agents.
Portainer MCP Docker
Dockerized Portainer MCP Server (stdio/streamable HTTP) for easy deployment alongside Portainer
PayPal Account Updater Subscription Connector
Integrates with PayPal's Account Updater service to maintain fresh payment card information in e-commerce systems.
OSDU MCP Server
Access OSDU platform capabilities including search, data management, and schema operations.
fal-ai/minimax/image-01
Advanced text-to-image generation model using the fal.ai API. Requires a FAL_KEY environment variable.
ThingsPanel MCP
An MCP server for interacting with the ThingsPanel IoT platform.
LlamaCloud
Connect to and manage data indexes on the LlamaCloud platform.
Coolify MCP Server
An MCP server for integrating with Coolify, the self-hostable alternative to Netlify and Vercel.
Dazzle
Cloud stages for AI agents — isolated browser environments that render and broadcast your content to Twitch, Kick, Restream, and custom RTMP.
Shared Memory MCP
An example project for deploying a remote MCP server on Cloudflare Workers without authentication.