# Servprivacy Mcp

> MCP server for ServPrivacy - deploy KYC-free, crypto-paid offshore VPS, dedicated, Windows RDP and GPU AI servers from any AI agent.

- **Type:** MCP server
- **Install:** `agentstack add mcp-servprivacy-servprivacy-mcp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ServPrivacy](https://agentstack.voostack.com/s/servprivacy)
- **Installs:** 0
- **Category:** [Finance & Payments](https://agentstack.voostack.com/c/finance-and-payments)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ServPrivacy](https://github.com/ServPrivacy)
- **Source:** https://github.com/ServPrivacy/servprivacy-mcp
- **Website:** https://servprivacy.com

## Install

```sh
agentstack add mcp-servprivacy-servprivacy-mcp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# ServPrivacy MCP server

> Deploy **KYC-free, crypto-paid offshore servers — VPS, dedicated, Windows RDP and GPU AI boxes** — straight from an AI agent. Claude, Claude Code, Cursor, Cline, Continue, or your own [MCP](https://modelcontextprotocol.io) client.

[](LICENSE)
[](https://www.python.org/)
[](https://modelcontextprotocol.io)
[](https://github.com/astral-sh/ruff)

`servprivacy-mcp` exposes the [ServPrivacy Agent API](https://servprivacy.com/agents) as Model Context Protocol tools, so an AI assistant can run the whole hosting workflow in natural language: **compare plans, pick an offshore jurisdiction, top up a balance with Monero or Bitcoin, and spin up a server — or rent an H100 with vLLM and Llama-3.3-70B pre-loaded — without ever touching a dashboard or showing an ID.**

[ServPrivacy](https://servprivacy.com) is a privacy-first [offshore hosting](https://servprivacy.com/offshore-hosting) provider operating in **7 jurisdictions** (Iceland, Panama, Moldova, Romania, Switzerland, Netherlands, Russia). Accounts need **no email, no phone, no name and no KYC** — a 16-character token issued on your first crypto payment is the entire identity floor — and billing is crypto-native across 20 coins. The API was built for agents from day one (a public [OpenAPI 3.1 spec](https://servprivacy.com/openapi.json), an [agent capability card](https://servprivacy.com/.well-known/agent.json) and a hosted [MCP endpoint](https://servprivacy.com/mcp)), which makes it a natural fit for a local stdio MCP server too.

---

## Why this exists

Agentic workflows increasingly need infrastructure on demand, and most clouds stop an autonomous agent dead at a credit-card form or an ID upload. ServPrivacy has neither. An agent can stand up a throwaway box for a scraper, a [Tor relay](https://servprivacy.com/use-cases/tor-hosting), a [self-hosted VPN](https://servprivacy.com/use-cases/vpn-hosting), a [crypto full node](https://servprivacy.com/use-cases/crypto-node-hosting) or a [seedbox](https://servprivacy.com/use-cases/seedbox-hosting) — paying with [Monero or Bitcoin](https://servprivacy.com/bitcoin-hosting) against a host that demands no identity documents and ignores DMCA in [DMCA-resistant jurisdictions](https://servprivacy.com/dmca-ignored-hosting).

### The GPU AI angle

The standout for agent builders is [GPU AI hosting](https://servprivacy.com/gpu). Order an **RTX 4090, RTX 5090, H100 or dual-H100** box and configure it *at deploy time*: pre-install AI stacks (`vllm`, `comfyui`, `ollama-webui`, `axolotl`, `unsloth`, …), pre-download HuggingFace models (`llama-3.3-70b`, `deepseek-r1`, `flux-dev`, `sdxl-base`, …), attach an `hf_token` for gated weights, expose a Let's Encrypt HTTPS endpoint, and set an `auto_shutdown_hours` timer so a forgotten experiment can't drain the balance. CUDA + cuDNN are preinstalled. Iceland runs on 100% renewable geothermal/hydro power — the lowest-carbon offshore AI compute on the market.

## Install & run

The server speaks MCP over **stdio**, so any MCP client launches it as a subprocess. The simplest path uses [`uv`](https://docs.astral.sh/uv/) (no manual virtualenv):

```bash
uvx servprivacy-mcp
```

Or install it into your environment with pip / pipx:

```bash
pip install servprivacy-mcp
# the console script is then on your PATH:
servprivacy-mcp
```

> Want the latest unreleased code? Install straight from source instead:
> `uvx --from git+https://github.com/ServPrivacy/servprivacy-mcp servprivacy-mcp`

### Configuration

| Variable | Required | Default | Purpose |
| --- | --- | --- | --- |
| `SERVPRIVACY_TOKEN` | for authenticated tools | — | Your account token (`AAAA-BBBB-CCCC-DDDD`), auto-issued on your first `create_topup` and shown **once** — store it. |
| `SERVPRIVACY_BASE_URL` | no | `https://servprivacy.com` | Override the API base URL (testing/self-host). |

Discovery tools — `agent_help`, `list_catalog`, `list_locations`, `quote`, `topup_bonus`, `check_domains` — and `create_topup` / `create_account` work with **no token at all** (the token is minted for you on the first top-up).

### Claude Desktop

Add to `claude_desktop_config.json` (see [`examples/`](examples/)):

```json
{
  "mcpServers": {
    "servprivacy": {
      "command": "uvx",
      "args": ["servprivacy-mcp"],
      "env": { "SERVPRIVACY_TOKEN": "AAAA-BBBB-CCCC-DDDD" }
    }
  }
}
```

### Cursor

Add to `~/.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "servprivacy": {
      "command": "uvx",
      "args": ["servprivacy-mcp"],
      "env": { "SERVPRIVACY_TOKEN": "AAAA-BBBB-CCCC-DDDD" }
    }
  }
}
```

## Try it

Once connected, ask your assistant things like:

- *"Compare ServPrivacy's [VPS](https://servprivacy.com/vps) tiers and tell me the cheapest one with 16 GB RAM in Iceland."*
- *"Rent an [H100](https://servprivacy.com/gpu) in Iceland with vLLM and Llama-3.3-70B pre-installed, expose an HTTPS endpoint, and auto-shutdown after 24h."*
- *"Top up $250 of Monero (grab the bonus tier) and wait for it to confirm."*
- *"Deploy a [Windows RDP](https://servprivacy.com/rdp) box in the Netherlands and read me the Administrator password."*
- *"Is `mybrand.com` available, and how much vs Namecheap?"* (the [.com loss leader](https://servprivacy.com/com-domain) is $4.99/yr).

There's also a built-in **`onboard_to_servprivacy`** prompt that drives the full top-up → deploy flow, and a **`dry_run`** flag on `create_topup`/`order_server` to validate everything without spending a cent.

## The payment model (balance-only)

ServPrivacy is **balance-only** — there is no direct crypto-to-server purchase:

1. `create_topup` — fund USD credit with crypto (min **$30**, max **$2000**). Bonus is applied automatically on confirmation (e.g. **$500 → $700 credited, +40%**; **$2000 → $4000, +100%**). See `topup_bonus`.
2. `get_topup` — poll until `status: "confirmed"`.
3. `order_server` — deploy from the credit; the server is `active` immediately. If the balance is short it returns **HTTP 402** with a `topup_required` block whose `suggested_usd` already covers the deficit and the $30 minimum — feed it back into `create_topup` and retry.

## Tools

13 tools, mapped onto the REST API. Tools marked _public_ need no token.

| Group | Tools |
| --- | --- |
| **Discovery** _(public)_ | `agent_help`, `list_catalog`, `list_locations`, `quote`, `topup_bonus`, `check_domains` |
| **Account** | `create_account` _(public)_, `get_account` |
| **Billing** | `create_topup` _(public)_, `get_topup` |
| **Servers** | `order_server` _(public; auto-creates account)_, `get_server`, `server_action` |

`order_server` carries the **GPU AI** deploy-time fields — `ai_stacks`, `pretrained_models`, `hf_token`, `ssh_public_key`, `public_endpoint`, `auto_shutdown_hours` — alongside the standard `type` / `plan` / `location` / `os` / `billing`.

### Resources

- `servprivacy://catalog` — full VPS/dedicated/RDP/GPU price-spec matrix (JSON)
- `servprivacy://locations` — the 7 jurisdictions and their legal posture (JSON)
- `servprivacy://bonus` — top-up bonus tiers (JSON)
- `servprivacy://doctrine` — the operating principles (text)

## How it works

```
AI agent ──MCP/stdio──▶ servprivacy-mcp ──HTTPS──▶ https://servprivacy.com/api/v1
```

The registry in [`tools.py`](src/servprivacy_mcp/tools.py) mirrors ServPrivacy's own [Agent API](https://servprivacy.com/agents) and binds each tool to its REST endpoint, so the surface stays in lock-step with the upstream [OpenAPI spec](https://servprivacy.com/openapi.json). Authentication is a single bearer token; nothing is cached to disk.

## Security & privacy

- Your token lives only in the client's environment — never written to disk by this server.
- **No KYC, no email, no logs:** the token *is* the account. Lose it and you lose access to the balance and every server bought with it — store it in a password manager.
- `order_server` and `create_topup` move real money/balance. Use `dry_run: true` to rehearse, and review your agent's confirmations before granting it the token.
- See the [warrant canary](https://servprivacy.com/canary) and the [no-KYC](https://servprivacy.com/no-kyc-hosting) / [anonymous hosting](https://servprivacy.com/anonymous-hosting) policy for what is (and isn't) collected.

## Development

```bash
git clone https://github.com/ServPrivacy/servprivacy-mcp
cd servprivacy-mcp
uv venv && uv pip install -e . ruff
python -m servprivacy_mcp   # starts the stdio server
ruff check .
```

## Links

- 🌐 Website — 
- ⚡ GPU AI hosting (H100 / RTX) — 
- 🧭 Agent docs — 
- 📜 OpenAPI 3.1 spec — 
- 🗺️ Jurisdictions — 
- 🔒 Warrant canary — 

## License

[MIT](LICENSE) © ServPrivacy. This is an open-source client for the ServPrivacy API.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ServPrivacy](https://github.com/ServPrivacy)
- **Source:** [ServPrivacy/servprivacy-mcp](https://github.com/ServPrivacy/servprivacy-mcp)
- **License:** MIT
- **Homepage:** https://servprivacy.com

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** yes
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-servprivacy-servprivacy-mcp
- Seller: https://agentstack.voostack.com/s/servprivacy
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.