Dcp Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Dcp Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
DCP is Saudi Arabia's sovereign AI compute platform — in-Kingdom inference, GPU rental, and persistent storage, billed in SAR, on Saudi-owned hardware. This MCP server lets any MCP-capable agent (Claude Desktop, Claude Code, Cursor, or your own) use DCP through native tool calls.
It is a thin client: it reads DCP_API_KEY from the environment and calls https://api.dcp.sa. No secrets are bundled.
The connector runs straight from GitHub — no npm install, no clone:
DCP_API_KEY=dc1-sk-xxxxxxxx npx -y github:dhnpmp-tech/dcp-mcpAdd this to your MCP client (Claude Desktop claude_desktop_config.json, Claude Code / Cursor .mcp.json):
{
"mcpServers": {
"dcp": {
"command": "npx",
"args": ["-y", "github:dhnpmp-tech/dcp-mcp"],
"env": { "DCP_API_KEY": "dc1-sk-xxxxxxxx" }
}
}
}Then ask your agent to "list DCP models" or "rent a GPU on DCP for 30 minutes." Agents with no key can call register_agent first — see the quickstart below.
| Tool | What it does |
|---|---|
register_agent | Self-register in one call — get a real API key + small SAR trial, no human, no email click. Use first when you have no key. |
list_models | List currently-serveable models (OpenAI-style). |
chat | Run a chat completion (OpenAI-compatible, in-Kingdom). |
get_balance | Renter wallet balance (SAR). |
list_gpus | List rentable GPU types (e.g. H100, RTX 4090) with VRAM + live availability. |
create_pod | Rent a whole GPU as an interactive pod (root + Jupyter + SSH), prepaid per minute. |
get_pod | Pod status + access URL / SSH command / time remaining. |
extend_pod | Add time to a running pod, no restart. |
stop_pod | Stop early; unused prepaid time refunded. |
rent_volume | Rent an exclusive in-Kingdom persistent volume (10/20/30 GB). |
get_volume | Active volume status + usage. |
The whole loop runs with no human in it:
api_key + a 20 SAR trial credit (no email click). Set it as DCP_API_KEY.gpu_type string (e.g. "H100", "RTX 4090") from the live, available types.gpu_type + duration_minutes → poll `get_pod` for the access_url / ssh_command once running.list_models.Minting a key by hand (equivalent to register_agent):
curl -s -X POST https://api.dcp.sa/api/renters/agent-register \
-H 'Content-Type: application/json' -d '{}'
# → { "api_key": "dcp-renter-…", "trial_credit_sar": 20, "balance_sar": 20, ... }The trial (20 SAR) is enough to list GPUs, run a short pod, and do real inference; the larger grant stays behind email-verified signup. Calls are per-IP rate-limited.
DCP_API_KEY — renter API key (required for every tool except register_agent).DCP_API_BASE — API host, default https://api.dcp.sa.Inference, GPU rental, fine-tune hosting, and storage on Saudi-owned hardware inside the Kingdom — full PDPL / data-residency compliance, billed in SAR. The inference API is a drop-in OpenAI replacement: point any OpenAI SDK at https://api.dcp.sa/v1.
Learn more: https://dcp.sa/v2/agents · https://dcp.sa/llms.txt
MIT licensed.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.