--- title: "Proxmox server controlled from chat by a Gemini agent" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/158620e4-0776-47ef-8b29-e2b2819e1145" updated: "2026-11-12" --- # Proxmox server controlled from chat by a Gemini agent > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow with a chat window. A Gemini agent turns a request into a Proxmox API call, the workflow runs it with your token, and a second agent explains the result. Proxmox server controlled from chat by a Gemini agent is an n8n workflow in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow lets you run a Proxmox server by chatting. You describe a task, such as listing the VMs on a node or starting one. A Gemini agent turns it into a Proxmox API call and picks the method, the path and the body. The workflow sends the call with your API token. A second agent explains the result in plain words. Twenty four nodes do the work, beside seven sticky notes. ### Who it suits Homelab owners and small IT teams who run Proxmox and want to try an agent on routine tasks. Start in a lab. A request can create, change or delete a VM at once, so keep the token narrow and the first tries harmless. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | IT operations | Sysadmins | Ask for the state of VMs without opening the console | A sysadmin asks which VMs on a node are running. | | Homelab | Hobbyists | Start and stop test machines by chat | A hobbyist asks to start VM 202 before a test. | | Training | Instructors | Show students how an agent maps words to an API | An instructor types a request and opens each node to show the call it made. | | Software | Developers | Build a first agent that acts on an API | A developer swaps the Proxmox calls for another system’s API and keeps the routing. | You need some n8n and some Proxmox: import a file, add two credentials and replace the sample hosts. Nothing in the file states a setup time. ### Where to use it Any n8n that can reach your Proxmox on port 8006 and Google’s Gemini API will run it. - Your own n8n server: on the same network as Proxmox, which is the simplest case - n8n Cloud: only if your Proxmox is reachable from the internet, which is a risk of its own - Other triggers: swap the chat trigger for another one, and make the prompt in \`AI Agent\` read the field it sends - Other models: swap the Gemini nodes for any chat model n8n supports ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Two credentials cover every step. What you need first | Need | Detail | | --- | --- | | n8n | On a server that can reach your Proxmox on port 8006 | | Proxmox | An API token, ideally one that can only read | | Google | A Gemini API key for a Google Gemini (PaLM) API credential | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. In Proxmox, create an API token. In n8n, add a Header Auth credential named `Authorization` with the value `PVEAPIToken=user@pam!tokenname=`, using your own user, login type and token name. 3. Select it in `Proxmox` and in `HTTP Request` to `HTTP Request4`. In those six nodes, replace `` with the address of one of your nodes. 4. In the prompt of `AI Agent` and the description of `Proxmox`, put your own addresses and node names in place of the sample ones. 5. Add a Gemini credential and select it in the three Google Gemini Chat Model nodes. 6. Save, open the chat and ask for something harmless, such as listing the VMs on a node. ### How to use it Open the chat and ask for a task in plain words. Start with a read, such as listing the VMs on a node, before you try a change. Open the run to see the call the agent chose. What to change for a different result | To change | Where | | --- | --- | | What the agent knows about your nodes | The prompt in \`AI Agent\` and the description in \`Proxmox\` | | What it may do | \`Switch\`: remove the DELETE rule to forbid deletion | | The summary’s tone | The prompt in \`AI Agent1\` | | The models | The three Google Gemini Chat Model nodes | | The trigger | The chat trigger, swapped for another | ### Example You type “Start VM 202 on psb1”. The agent answers with a POST to `/nodes/psb1/qemu/202/status/start`. `Switch` sends it down the POST path and an HTTP request calls your Proxmox. The workflow then turns the task id it gets back into one sentence with the operation, the node, the user and the time. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. The first agent only writes the call. The routing boxes then run it, and the second agent explains what came back. An API is how programs ask Proxmox to act, and the token is the key it checks. **For experts.** The agent’s answer is forced into a fixed JSON shape, and a Switch on `response_type` decides which HTTP node runs. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`AI Agent\` | Version 1.7, a ReAct agent with an output parser, three tools and a long prompt | n8n marks the ReAct type deprecated and says it is removed in version 3 | | \`Structured Output Parser\` | Version 1.2, a shape taken from an example with \`response\_type\`, \`url\`, \`details\` and \`message\` | \`Auto-fixing Output Parser\` retries a bad answer with \`Google Gemini Chat Model1\` | | \`Switch\` | Version 3.2, six outputs by \`response\_type\` | PUT (named Update), OPTIONS and Invalid lead nowhere | | \`HTTP Request\` and its four siblings | Version 4.2 with Header Auth, ignoring SSL certificate problems | The path comes from \`output.url\` and the body from \`output.details\` | | \`Structgure Response from Proxmox\` | A Code node that splits the task id Proxmox returns | It reads node, operation, user and time from fixed positions | ### Good to know A model decides, and your server obeys. - It changes things: POST and DELETE calls run at once, with your token’s rights, from what a model understood. There is no confirmation step, so a request to delete a VM deletes it. Use a narrow token and a lab you can rebuild - Certificates: the five HTTP Request nodes ignore SSL certificate problems, so they trust any certificate. That suits a Proxmox with its own certificate, but turn it off if yours is valid - Dead ends: PUT, OPTIONS and Invalid have nothing wired to them, so the run ends with no call and no answer. The agent’s own examples include PUT, for things such as resizing a disk - Models: the original copy named \`models/gemini-2.0-flash-exp\`. Google’s deprecations page, read on 12 November 2026, says the \`gemini-2.0-flash\` family shut down on 1 June 2026 and names \`gemini-3.6-flash\` as its replacement, so Mindket’s copy uses that - Agent types: n8n marks the ReAct and Conversational types used here as deprecated and says they are removed in version 3 - A repair: the GET branch read its path from a field the agent’s answer does not have. Mindket’s copy reads \`output.url\`, as the other branches do - Your data: your requests and what Proxmox returns, such as VM names and status, go to Google’s Gemini - Where it runs: from n8n’s Chat window in the editor. Nothing in the file opens a public chat - Credentials: the JSON holds none, and the hosts in it are placeholders ## README ```markdown # Proxmox server controlled from chat by a Gemini agent An n8n workflow with a chat window. You describe what you want done on a Proxmox cluster, such as listing the VMs on a node or starting one. A Gemini agent turns the request into a Proxmox API call with a method, a path and a body. The workflow runs the call with your API token, and a second agent explains the result in plain words. ## What is inside - `workflow.json`: the workflow as n8n exports it, 24 nodes beside 7 sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy Mindket cleaned up and repaired the copy: - Three trigger nodes led nowhere: Telegram, Gmail and a webhook. Each would have asked for a credential before the workflow could be published, so Mindket removed them. A sticky note still says any trigger can feed the agent. - A sticky note held a donation link and personal contact details. Mindket's copy drops it. - The original copy held someone's own Proxmox addresses: one public host and some private ones. They are now ``, `` and ``, and one request node that called a different host from the rest now calls the same one. - The GET branch read its path from `output.properties.url.pattern`, a field the agent's answer does not have. The prompt and the output example put it in `url`, as the other branches read it, so Mindket's copy reads `output.url` there and in the summary agent's text. - The three chat models named `models/gemini-2.0-flash-exp`. Google's deprecations page, read on 12 November 2026, says the `gemini-2.0-flash` family shut down on 1 June 2026 and names `gemini-3.6-flash` as its replacement. The page does not list the `exp` name. Mindket's copy uses `models/gemini-3.6-flash`. - No credential is inside. ## Before you start - An n8n instance, on n8n Cloud or your own server, that can reach your Proxmox on port 8006. - A Proxmox API token. A token that can only read is the safe way to start. - A Google Gemini API key, for a Google Gemini (PaLM) API credential. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. In Proxmox, create an API token. In n8n, add a Header Auth credential with the name `Authorization` and the value `PVEAPIToken=user@pam!tokenname=`, using your own user, login type and token name. 3. Select that credential in `Proxmox`, `HTTP Request`, `HTTP Request1`, `HTTP Request2`, `HTTP Request3` and `HTTP Request4`. 4. In those same six nodes, replace `` with the address of one of your nodes. 5. In the prompt of `AI Agent` and the description of `Proxmox`, replace the three host placeholders with your own addresses and `psb1`, `psb2` and `psb3` with your node names. Delete lines for nodes you do not have. 6. Add a Gemini credential and select it in `Google Gemini Chat Model`, `Google Gemini Chat Model1` and `Google Gemini Chat Model2`. 7. Save, open the chat and ask for something harmless, such as listing the VMs on a node. ## How a run goes 1. `When chat message received` starts a run when you send a message. 2. `AI Agent` is a ReAct agent with `Google Gemini Chat Model`. It can call three tools: `Proxmox`, which reads the cluster status, and `Proxmox API Documentation` and `Proxmox API Wiki`, which read two pages from Proxmox's site. It answers in JSON with `response_type`, `url` and `details`. `Structured Output Parser` sets that shape, and `Auto-fixing Output Parser` asks `Google Gemini Chat Model1` to repair an answer that does not fit. 3. `Switch` sends the request by `response_type`: GET, POST, PUT, OPTIONS, DELETE or Invalid. 4. For GET, `HTTP Request` calls the path. `Structure Response` turns each item into one line of text, and `AI Agent1`, a Conversational agent with `Google Gemini Chat Model2`, explains it in words. 5. For POST, `If` checks whether the answer has `details`. With them, `HTTP Request1` posts them as the body. Without, `HTTP Request2` posts with no body. `Merge` joins the two. 6. For DELETE, `If1` leads to `HTTP Request3` or `HTTP Request4`. Both send DELETE with no body, and `Merge1` joins them. 7. `Structgure Response from Proxmox` splits the task id that Proxmox returns into node, operation, user and time. `Format Response and Hide Sensitive Data` writes one sentence from them. ## Change the look - What the agent may do and how it writes calls: the prompt in `AI Agent`. - Taking deletion away: remove the DELETE rule in `Switch`, or the nodes after it. - The input: swap the chat trigger for another trigger. The prompt reads `{{ $json.chatInput }}`. - The summary's tone: the prompt in `AI Agent1`. - The models: the three Gemini nodes. ## Good to know - It changes things. POST and DELETE calls run at once, with your token's rights, from what a model understood. There is no confirmation step, so a request to delete a VM deletes it. Use a narrow token and a lab you can rebuild. - The five HTTP Request nodes have the option that ignores SSL certificate problems turned on, so they trust any certificate. That suits a Proxmox with its own certificate, but turn it off if yours is valid. - PUT, OPTIONS and Invalid have nothing wired to them, so the run ends with no call and no answer. The agent's own examples include PUT, for things such as resizing a disk, so those requests are lost. - n8n marks the ReAct and Conversational agent types used here as deprecated and says they are removed in version 3. A newer AI Agent node replaces them. - Your requests and what Proxmox returns, such as VM names and status, go to Google's Gemini. - It runs from n8n's Chat window in the editor. Nothing in the file opens a public chat. - The JSON holds no credential. ``` ## What is in it 3 files, 39 KB, downloaded as a zip. ```text NOTICE.md 644 B README.md 6 KB workflow.json 33 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 16 steps, starting on a chat message - AI: 2 steps call an AI model: AI Agent and AI Agent1 - Sign-ins: Signs in to: a web service and Google Gemini - API keys: No API key is left in the file - Step types: Mindket’s checker reads 6 of its 7 step types. It does not read: AI Agent ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/158620e4-0776-47ef-8b29-e2b2819e1145) - [Its page on Mindket](https://mindket.com/p/158620e4-0776-47ef-8b29-e2b2819e1145)