proximo-proxmox

Enter the ludus ↗ · Quickstart · Setup · Trust layer · Demo · Tools · Install · Security · Docs

Named for Proximo, the lanista of Gladiator. The story is the design, joint for joint.

He armed his fighter with exactly what he needed, never more. He answered for every move in the arena. A lanista, not a jailer.

The Spaniard doesn't get his name up front. He earns it, by conduct, on the record. The helmet comes off: truth said plainly, at cost. That's the "not yet proven, said plainly" section below, and AGENTS.md leading with Proximo's own sharp edges.

His last act opened the cages, holding the wooden sword of his own freedom. A tool should hope to end that well.

"Win the crowd and you will win your freedom."

The others make you choose. A read-only inspector that's safe because it can't touch anything. Or a loaded gun aimed at a cluster you care about.

Proximo refuses the trade. Every dangerous move is planned: see the blast radius first. Every move is proven: a tamper-evident record. And undoable wherever the platform gives us a primitive: a config change hands back the exact prior state, and a risky in-container command can take a snapshot first — and refuses to run if it can't.

Trust built into the substrate, not bolted on after. Hand an AI agent the keys; keep the receipts.

Sovereign and agent-agnostic. Your metal, your token, a ledger you own. No cloud, no phone-home, no standing server unless you opt in.

Don't take our word for any of it. Verify it yourself.

Verify in 60 seconds — three receipts, no trust required

# 1. The tool count is real — ask the server itself, cold (=> 906).
#    (in a clone of this repo, after `uv sync`)
uv run python -c "import asyncio; from proximo import server; \
print(len(asyncio.run(server.mcp.list_tools())))"

# 2. The container image is what the repo built — sigstore provenance (exit 0 = verified):
gh attestation verify oci://ghcr.io/john-broadway/proximo:latest --owner john-broadway

# 3. The security posture is graded by a third party, not by us:
#    https://scorecard.dev/viewer/?uri=github.com/john-broadway/proximo

The rest is in VERIFY.md: forge a ledger byte and watch verify() refuse, grep the outbound surface for phone-home (there is none). These checks work on any tool, from any vendor. Demand them everywhere.

_{Every transport enters one governed dispatch and crosses the same trust spine; the token floor beneath it all is enforced by Proxmox itself. Watch it hold in the Demo.}

What it does

Ask, in plain English: "why is ct 105 thrashing?" An AI agent pulls node and guest status, tails the logs, and runs a diagnostic inside the container to find out.

If there's a fix, it shows you the plan before it touches anything. Takes a snapshot first if you ask it to — and won't run if it can't. Applies. Hands you a signed receipt of exactly what changed.

That's the product: a hypervisor an AI can operate without being able to wreck it.

Read-only by default. No mutation runs on the first call: it returns its blast radius as a plan for you to see first. A tamper-evident receipt for every change.

The comparison isn't Proximo vs. the GUI. It's Proximo vs. handing an LLM your root token and hoping.

Quickstart

// your MCP client config (Claude Desktop / Claude Code / Cursor / …)
{
  "mcpServers": {
    "proximo": {
      "command": "uvx",
      "args": ["proximo-proxmox"],
      "env": {
        "PROXIMO_API_BASE_URL": "https://your-pve:8006/api2/json",
        "PROXIMO_NODE": "your-node",
        "PROXIMO_TOKEN_PATH": "/path/to/token-file"   // USER@REALM!TOKENID=SECRET — by reference, never inlined
      }
    }
  }
}

Or install with one click:

_{Both prompt for the token file path; the secret never lands in client config. No token yet? uvx proximo-proxmox mint prints the least-privilege runbook.}

Then preflight what your token can actually do (read-only):

uvx proximo-proxmox doctor

Start with a read-only token. Proximo is useful long before you grant it write. Full token-first walkthrough: docs/SETUP.md · more install paths: Install & run.

Why Proximo exists

The Proxmox MCP landscape is split. API-based servers manage nodes and VMs but structurally cannot run a command inside an LXC: the REST API has no exec endpoint. SSH-based servers can, through broad shell access with little scoping.

Proximo builds the principled whole. Both halves, one audited surface, least-privilege. Trust by construction:

	Read-only inspector	Full-access executor	Proximo
Can mutate	no — that's the safety	yes	yes — plan recorded first, then confirm=true
Preview before a change	n/a	rarely	default — blast radius + live state, every mutation
Record of what happened	no	app logs, editable	keyed hash-chained ledger, tamper-evident, on by default
Undo	n/a	rare	snapshot-first, wherever the platform can snapshot
Command inside an LXC	no	broad SSH	opt-in, fail-closed CTID allowlist
Products covered	usually PVE	usually PVE	PVE + PBS + PMG + PDM — one audited plane
Verify the artifact you run	varies	varies	signed image · PyPI provenance · SBOM · Scorecard

(The archetype columns describe the split above, not any specific project. There is no official Proxmox MCP; Proximo is a community project, standing on its own.)

The trust layer — what makes Proximo different

Four controls on by default:

Control	What it does
PLAN	Every mutation first returns a recorded preview — the exact change, live state, blast radius, an advisory risk rating. Nothing mutates without its plan recorded; one confirm=true call records and performs.
PROVE	Keyed (HMAC-SHA256), hash-chained audit ledger — audit_verify catches edits, reordering, insertion. Pin the head off-box (expected_head) to catch truncation too: that's the strong guarantee, and it's opt-in.
UNDO	Where the platform has a primitive: a config change returns its prior_config automatically (revert with pve_guest_config_revert), ct_exec/ct_psql take snapshot=true for an auto-snapshot and then fail closed — if the snapshot can't be taken the command does not run — and pve_rollback restores a guest snapshot. The exec snapshot is per call, not automatic. Planes with no snapshot primitive (firewall/SDN/ACL) have no rollback — said plainly.
DIAGNOSE	Read-only evidence battery + node health → advisory flags that surface incompleteness too, so an empty list never reads as a false clean bill.

Six more ship off until you configure them — per-plan CONSENT, a CONTAIN kill-switch, an arm-LEASE, an arm-time SCOPE, a FORBID/RATE ENVELOPE, and TAINT (the prompt-injection mitigation). What each one actually defends against: SECURITY.md.

Honesty note (load-bearing): risk ratings are an advisory heuristic, not a sandbox — LOW means "no state change," not "safe," and the absence of a HIGH flag is not a safety signal. Review every change yourself. The floor beneath it all is the token you mint: Proxmox RBAC holds even if Proximo's process is fully compromised — a stronger guarantee than anything Proximo's own code provides. Scope it to exactly what you mean to grant: SECURITY.md.

Hold any tool to this, including this one: The Keys Test. Ten questions to ask before you hand an AI agent real infrastructure. Proximo's own scorecard published, partials included.

Demo

The record defends itself:

_{Three agent moves land in the keyed ledger; one entry gets edited in place — audit_verify() breaks at the exact line, ok=False; the truncation a forward walk would miss is caught against the pinned head. Real code, real crypto, nothing staged — recorded on 0.30.0. Run it yourself anywhere: scripts/demo/hand_the_keys.py (needs only the pip package) · against your own host: --live · verify by hand: VERIFY.md.}

Surfaces & tools — one control plane

Surface	Backend	For
Proxmox VE	REST API + scoped token	node/guest lifecycle, storage, SDN, identity, HA, firewall
Proxmox Backup Server	REST API + scoped token	datastores, namespaces, snapshots, sync, GC, verify, tape
Proxmox Mail Gateway	Ticket auth	mail flow, quarantine, filtering rules, domains, services
Proxmox Datacenter Manager	API token	federated fleet — reads plus governed control (power/snapshot/migrate, dry-run-first)
Container exec	ssh → pct exec	run-command-in-container, psql, log tailing — what the API structurally can't do

Those backends are deliberately boring. Anyone can call them. The product is the trust layer over them.

906 tools is an estate, not a starting point — and you only carry the part you use. Since 0.30 the floor IS the default: a bare install serves the search-and-call facade (~1,449 tokens of context) with every tool this box serves still callable; one domain like pve.guests runs ~9,123, a whole plane ~97,432, PROXIMO_TOOLSETS=catalog the classic auto-scoped catalog. The estate is 906. The doorway is yours to size. Coverage and context stopped being the same number.

Where an operator actually starts:

You want to…	Start with	Worth knowing
See the whole cluster at once	pve_cluster_resources, pve_list_guests	one call, every node
Find out why a container is sick	ct_diagnose, ct_logs, pve_guest_status	read-only evidence battery
Preflight a token / config	proximo doctor (CLI) or pve_doctor, pve_overbroad_grants	run this before wiring an agent
Power / lifecycle	pve_guest_power	returns a PLAN first — nothing moves without confirm=true
Snapshot before touching anything	pve_snapshot_create, pve_rollback	UNDO's foundation
Check backups are actually fresh	pve_backup_freshness, pbs_snapshots_list	walks real archives — "task OK" is never evidence
Run a command in a container	ct_exec	opt-in (PROXIMO_ENABLE_EXEC=1), fail-closed allowlist
Trace / release mail	pmg_tracker_list, pmg_quarantine_spam	full PMG plane behind it
Operate the federated fleet	pdm_resources_list, pdm_pve_lxc_list	governed control, dry-run-first
Prove the record wasn't touched	audit_verify	registered on every surface, always

Every tool with typed inputs: docs/TOOLS.md · sizing the surface to your model: docs/SETUP.md.

Install & run

📦 0.31.0 — on PyPI, GitHub, and GHCR (signed multi-arch image).

New in 0.31.0 — scoping your planes no longer opts you out of the door. PROXIMO_SURFACES picked the doorway as well as the planes, so an install that scoped itself silently kept the pre-0.30 catalog: on a PVE+PBS box, 569 resident tools where the facade serves 5. Surfaces now scope the searchable catalog and leave the door at the default; PROXIMO_TOOLSETS=catalog or all ask for the old doors by name, and nothing becomes unreachable either way. proximo doctor now derives the facade size and how the catalog was narrowed from the live registry instead of the environment, so it can no longer name a tool the box does not serve.

Recent: 0.30.0 made the search-and-call facade the default door (~1,449 tokens instead of a ~97k catalog) and turned Tier-1 estate memory on by default. See SECURITY.md for what each control honestly holds.

Proximo runs on your machine, on demand. No daemon, no open port.

uvx proximo-proxmox            # zero-install run (PyPI package: proximo-proxmox; command stays `proximo`)
# or: pip install proximo-proxmox            the MCP core
# or: pip install "proximo-proxmox[a2a]"     + the optional A2A face
# or: pip install "proximo-proxmox[http]"    + the optional HTTP/OpenAPI face
# or: pip install "proximo-proxmox[mcp-http]" + the optional MCP-over-streamable-HTTP face
# or, from source:  git clone https://github.com/john-broadway/proximo.git && cd proximo && uv pip install -e .

Wire it into your MCP client as the command proximo, with the PROXIMO_* env vars — see packaging/proximo.env.example.

Docker (GHCR): docker run -i --rm … ghcr.io/john-broadway/proximo:latest. Multi-arch, SBOM, sigstore-signed provenance (gh attestation verify oci://ghcr.io/john-broadway/proximo --owner john-broadway). Mirrored to Docker Hub (docker.io/jebroadway/proximo, identical digest); GHCR stays the signed primary.

Safe by default: API-only out of the box. The two near-root edges are opt-in and say so loudly: LXC exec (PROXIMO_ENABLE_EXEC=1, near-root on the host) and the qemu-guest-agent edge (PROXIMO_ENABLE_AGENT=1, near-root in a guest). Each is scoped by its own fail-closed allowlist.

Smallest footprint by design: you don't have to load the whole estate — what a box serves is autoscoped to what it configures. A PBS-only box gets that plane's tools plus the always-on audit trail; PROXIMO_SURFACES=pve,exec scopes the searchable catalog to that pair (316 tools); a typo'd surface refuses startup rather than serving a surprise. Surfaces choose which planes are searchable, never how many schemas load — the doorway stays the default unless you name another with PROXIMO_TOOLSETS. Scoping is context hygiene, not an authorization control: it changes what is advertised, never what a token is allowed to do. The default doorway (dynamic mode) keeps three search-and-call tools resident plus the two ledger tools (audit_verify proves the chain, audit_entries reads who did what) and proximo_recall while estate memory is on (the default; PROXIMO_MEMORY=0 opts out) — with the full catalog reachable by name. That narrowing is guarded at every entry point (0.27.0 closed a path where an opt-in flag could silently cut the registry to 5 tools), and the gates don't shrink with the doorway: PLAN and PROVE apply however small the visible surface gets.

The network faces (experimental, opt-in): proximo-a2a speaks Agent2Agent. proximo-http serves plain HTTP + generated /openapi.json for no-code clients. proximo-mcp-http serves MCP itself over Streamable HTTP (the SDK's native transport) for networked MCP clients: no third-party stdio→HTTP bridge, so the perimeter stays Proximo's.

All three serve the full surface through the same spine as MCP. No second code path; trust spine and token scope inherited. Fail-closed perimeter: loopback, bearer-token required off-localhost, DNS-rebind and CSRF defended. Details: SECURITY.md.

At scale

One container is the demo. A cluster is the point.

• The whole cluster in one call. pve_cluster_resources: every VM, node, storage pool, SDN object.
• One tamper-evident record across every node. "Show me every state-changing action this month, and prove the log wasn't touched" becomes a query you can actually answer. No human at the CLI walks away with that.
• Where the time comes back. On one node a senior at the CLI is faster, and that's fine. Across a dozen nodes and hundreds of guests, a bounded, audited agent earns its keep.

Many boxes, one Proximo: register remotes in a TOML file (secrets by reference, never inlined), point PROXIMO_TARGETS at it, aim any tool with proximo_target="edge-pve". The target travels with the call. PLAN and EXECUTE hit the same box, the ledger records which, cross-plane calls error. Config shape: packaging/targets.example.toml.

Status — the arena record

• 🩸 0.31.0 — the door fix the flip needed. 0.30.0 made the facade the default, but an install that scoped its planes silently kept the old catalog: 569 resident tools where the facade serves 5, no error, no warning. An outside re-vet found it by probing the running server; our own suite could not, because the test guarding the very sentence that was wrong checks the filter rather than what a client is served. The fix held under three lenses.

Every release before it — every pillar, every redteam, every fix — lives in CHANGELOG.md.

The numbers, honestly: 906 MCP tools, proved in two deliberate layers. 11,000+ in-process tests (ruff + pyright clean) pin every tool's shape. A separate live-smoke harness drives real Proxmox hardware: a 3-node PVE 9.2 cluster, PBS 4.2, PMG 9.1, PDM 1.1.4, a real cross-datacenter move. The two are kept apart on purpose: passing shape tests never gets to masquerade as "works on a real host." And this workspace administers its own Proxmox estate through Proximo daily (dogfood). The blast-radius engine carries the destructive surface: across eleven op-classes it names the specific guests, nodes, principals, or disks at risk. Nothing falls back to a bare confirm.

Proven live (not mocks): the trust spine end-to-end; identity/storage/SDN/firewall/HA create→read→delete with the ledger verified throughout; offline + online live-migration and HA fencing (softdog) on a real 3-node cluster; full PBS/PMG/PDM planes including a real cross-datacenter move. Not yet proven — said plainly: hardware-watchdog fencing (needs physical iTCO/IPMI) and behavior at production scale. The unrecoverable ops (SDN apply, etc.) are deliberately never fired live: proven by plan, held back by design, not a gap. Per-surface detail: CHANGELOG.md.

Documentation

Document	What it answers
Setup	Token-first walkthrough: mint a least-privilege token, verify it, widen deliberately.
Verify	Every trust claim paired with the command that proves it — run them cold.
Security	The two-deployment trust model, all ten controls, what each honestly holds, reporting.
Threat model	What Proximo defends against, what it doesn't, where the boundaries sit.
Tools	All 906 tools, grouped by surface, typed inputs.
Agents	The page written for the agent itself — Proximo's sharp edges, stated first.
Known issues	What's broken or odd right now, said plainly.
Contributing	Dev setup, the CI gates, what a PR is expected to keep intact.
Changelog	Every release, every redteam, every fix — the full build history.

License

Apache-2.0 — chosen for the patent grant that suits infrastructure tooling. Full text in LICENSE.

Credits

Built by John Broadway with Claude and Maude — a human–AI partnership, and the first thing we made on this box to give away to the world. Claude Opus 4.8 built the trust pillars and the original tool surface and has carried the work since; Claude Fable 5 ran the 101-agent release audit and the first publish. Every commit carries its co-author trailer. And to meyergru, who put a real measurement on the table instead of an opinion — the context-cost work above exists because of that report.

"Are you not entertained?" — stars, issues, and sparring partners welcome. Strength and honor. ⚔️