Dcp Mcp

io.github.dhnpmp-tech由 GitHub 账号 dhnpmp-tech 发布v1.0.0更新于 Oct 24, 2026

Saudi sovereign AI compute: OpenAI-compatible inference, rent GPU pods, manage storage.

概览

AI 生成的概览

本地 MCP 服务器,让助手使用沙特 AI 算力平台 DCP,进行 OpenAI 兼容的对话推理、GPU 租用和持久存储。

可以做什么
注册代理并获取 API 密钥和少量试用额度,无需人工或邮件验证,并查询以 SAR 计价的租户钱包余额。列出可用模型并运行托管于沙特境内的 OpenAI 兼容对话补全。列出可租 GPU 类型及其显存和实时可用性,然后创建、查看、延长和停止按分钟预付费的 GPU 实例,实例提供 root、Jupyter 和 SSH 访问。租用并查看 10、20 或 30 GB 的境内持久卷。
适用场景
当助手需要在 DCP 的沙特托管基础设施上运行推理或租用 GPU 算力时适用,也适合关注沙特境内数据驻留和 SAR 计费的场景。适合需要通过工具调用而非控制台开通短期 GPU 实例或持久卷的代理。
运行要求
以 stdio 本地运行,通过 npx 从 GitHub 仓库启动,需要 Node.js 以及访问 DCP API 的网络。除 register_agent 外所有工具都需要环境变量 DCP_API_KEY;可用 DCP_API_BASE 覆盖默认 API 主机。仅支持桌面 MCP 客户端。
安装前请注意
多数工具会实际花钱:create_pod、extend_pod 和 rent_volume 按分钟或按卷预付费,stop_pod 只退还未使用的预付时间。register_agent 无需人工验证即可创建真实 API 密钥和试用额度,调用按 IP 限流。DCP_API_KEY 是计费凭据,勿放入共享配置。实例提供 root、Jupyter 和 SSH 访问,提示词、数据和负载会发送到第三方平台。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Dcp Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

@dcp/mcp — DCP Model Context Protocol server

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.

Install (one line)

The connector runs straight from GitHub — no npm install, no clone:

bash
DCP_API_KEY=dc1-sk-xxxxxxxx npx -y github:dhnpmp-tech/dcp-mcp

MCP client config

Add this to your MCP client (Claude Desktop claude_desktop_config.json, Claude Code / Cursor .mcp.json):

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.

Tools

ToolWhat it does
register_agentSelf-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_modelsList currently-serveable models (OpenAI-style).
chatRun a chat completion (OpenAI-compatible, in-Kingdom).
get_balanceRenter wallet balance (SAR).
list_gpusList rentable GPU types (e.g. H100, RTX 4090) with VRAM + live availability.
create_podRent a whole GPU as an interactive pod (root + Jupyter + SSH), prepaid per minute.
get_podPod status + access URL / SSH command / time remaining.
extend_podAdd time to a running pod, no restart.
stop_podStop early; unused prepaid time refunded.
rent_volumeRent an exclusive in-Kingdom persistent volume (10/20/30 GB).
get_volumeActive volume status + usage.

Zero-human quickstart (for agents)

The whole loop runs with no human in it:

  1. register_agent → returns a real api_key + a 20 SAR trial credit (no email click). Set it as DCP_API_KEY.
  2. list_gpus → pick a gpu_type string (e.g. "H100", "RTX 4090") from the live, available types.
  3. create_pod with that gpu_type + duration_minutes → poll get_pod for the access_url / ssh_command once running.
  4. chat → run OpenAI-compatible inference on an available model from list_models.
  5. stop_pod → stop early; unused prepaid minutes are refunded to the wallet.

Minting a key by hand (equivalent to register_agent):

bash
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.

Environment

  • DCP_API_KEY — renter API key (required for every tool except register_agent).
  • DCP_API_BASE — API host, default https://api.dcp.sa.

Why DCP

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.

来源:README.md,提交 b9d485a

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分