Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/nandi-services/proxmox-mcp/setupgit clone --depth 1 https://github.com/NANDI-Services/proxmox-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/nandi-services/proxmox-mcp/setup)<a href="https://agentmods.dev/commands/nandi-services/proxmox-mcp/setup"><img src="https://agentmods.dev/badge/commands/nandi-services/proxmox-mcp/setup.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00013 | $0.00734 |
| Opus 5 | $0.00006 | $0.00367 |
| Sonnet 5 | $0.00003 | $0.00147 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide the user through connecting nandi-proxmox-mcp to their own Proxmox. They
may never have configured an MCP server before, so explain each step in one
sentence before running it and never assume they know Proxmox terminology.
Work through these in order, stopping at each one until it succeeds.
1. Find out where they are
Run npx nandi-proxmox-mcp list.
- If it lists an instance, configuration already exists. Skip to step 4.
- If it says nothing is configured, continue.
2. Get an API token
Ask whether they already have a Proxmox API token.
If they do not, run npx nandi-proxmox-mcp bootstrap --tier read-only and tell
them to:
- Open the Proxmox web UI in a browser.
- Go to Datacenter → Shell.
- Paste the block the command printed.
- Copy the
valuefrom the table it prints — Proxmox shows it exactly once.
Point out why --privsep 0 is in there: a token created through the web UI form
has privilege separation on by default and therefore no permissions at all,
which fails later as a 401 that looks like a wrong password.
Suggest --tier read-only unless they say otherwise. It can be raised later by
re-running setup, and starting permissive is hard to undo.
3. Run setup
Tell them to run npx nandi-proxmox-mcp setup in their own terminal, not
through you — it asks for a token secret, which should not pass through a
transcript.
Explain the two questions that carry consequences:
- How much the AI can do.
read-onlyinspects,read-executeadds power management,fulladds create, delete and running commands inside containers. - Whether they need commands inside containers. Answering no skips SSH
entirely. Almost everything works over the API without it, so no is the right
answer unless they specifically want
pct exec.
4. Check it
Run npx nandi-proxmox-mcp doctor.
Read the report back in plain language. A [SKIP] line is not a problem — it is
a check that was not requested. Only [RED] needs action, and each red line
carries a fix: line under it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 75 lines · 13 tokens per session scan A ac39162ece74
setup is a command published in the GitHub repository NANDI-Services/proxmox-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 13 tokens to every session and 734 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
apply-self-review
Apply the approved improvements from the latest memory-self-review PROPOSAL. Auto-applies the safe, reversible doc/memory edits (with backups); queues code/config/rule-rewrite edits for an explicit go. Never commits or pushes.
publish-core
Trigger the canonical publish pipelines in this repo.
release
Create a new release for the Starpod workspace.
distil-onboard
Intelligently onboard the user onto distil — assess their setup, then set up and guide with judgment.
distil-shadow
Decision-equivalence report — did compression preserve your agent's next action?
distil-certify
Trajectory-level certificate — bound how many solvable tasks compression may cost.