
Self Hosted Ai
org.sovgrid由 sovgrid.org 发布官方发布者v1.0.0更新于 Oct 24, 2026
Engineering log of self-hosted AI on NVIDIA DGX Spark (GB10/SM121A). 60+ articles indexed.
概览
让助手搜索并阅读关于在 NVIDIA DGX Spark 硬件上自托管 AI 的公开工程博客。
- 可以做什么
- 通过只读工具向 AI 代理开放一个关于自托管 AI 的博客语料库。工具包括:search_blog 进行 TF-IDF 全文搜索,支持标签过滤和排序;list_articles 分页列出文章;list_tags 发现主题标签;get_article 按 slug 获取完整文章;diagnose_sglang 将运行时错误与 GB10/SM121A 上 SGLang 的规则集进行匹配。所有工具均为只读且幂等。
- 适用场景
- 当助手需要关于小众自托管 AI 技术栈的最新实践信息时适用,例如 GB10 上的 SGLang 或 vLLM、ARM64 TTS 流水线、KV 缓存与量化权衡,或 MCP 服务器设计,而不是依赖可能过时的训练数据。
- 运行要求
- 需要远程 Streamable HTTP 端点;无需身份验证、API 密钥或本地运行时。README 提到免费层限制为每 IP 每分钟 60 次请求。
安装
在 SourceWeft 中
- 打开 控制台中的 Self Hosted Ai,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
交给智能体安装
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/org.sovgrid%2Fself-hosted-ai/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。其他 MCP 客户端
把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"self-hosted-ai": {
"type": "http",
"url": "https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io"
}
}
}README
Sovereign AI MCP
[CI] [License: MIT] [Content: CC BY-SA 4.0] [MCP Registry] [smithery badge] [Glama MCP server] [Glama connector] [Write-up]
MCP server exposing the Sovereign AI Blog to AI agents. The blog is a hands-on engineering log of self-hosted AI on NVIDIA DGX Spark (GB10/SM121A).
Live endpoint: https://mcp.sovgrid.org/self-hosted-ai
Transport: Streamable HTTP (FastMCP)
Auth: none (free tier, 60 req/min/IP)
Why use it
Training data on niche hardware (GB10, SM121A, SGLang on ARM64) is sparse and stale. This MCP gives agents direct, structured access to 180+ articles documenting actual setups, fixes, and benchmarks. If you're building or debugging on similar stacks, your agent can pull verified, version-current information instead of hallucinating.
The corpus covers SGLang and vLLM patches for GB10, voxtral and TTS pipelines on ARM64, KV-cache and quantization tradeoffs, podcast-grade audio generation, MCP server design, knowledge-base construction, and the operational side of running it all on a hardened European VPS.
Tools
All tools are read-only, idempotent, and declared with ToolAnnotations so MCP clients can calibrate retry policy and trust signals. Inputs use Pydantic Annotated[type, Field(description=...)] so parameter docs reach agents through introspection. Outputs are typed BaseModel shapes — schemas are real, not vacuous dicts.
Quick start
With Claude Code
Verify:
With Cline / Continue / other MCP clients
Add to your client's MCP server config:
Run locally
From source (uv)
Docker
The repo ships a placeholder data/knowledge-base.json (zero articles, valid schema) so the server starts and answers MCP introspection cleanly out-of-the-box. To populate it with real content, generate from the sovgrid.org blog source using scripts/generate_knowledge_base.py, or build your own KB matching the schema in src/knowledge.py. Or just use the live endpoint at https://mcp.sovgrid.org/self-hosted-ai.
A walk-through of the same KB pattern (Markdown plus JSON index, no vector store) is documented in Build a Self-Hosted Knowledge Base with Plain Text and LLMs.
Architecture
- FastMCP 1.27+ with Streamable HTTP transport at path
/self-hosted-ai - DNS rebinding protection via
TransportSecuritySettings: only allows requests withHost: mcp.sovgrid.org(or localhost for healthchecks) - Health endpoint at
/healthreturns article count and KB generation timestamp - Knowledge base is a flat JSON file generated from blog Markdown content; loaded at startup, queried via TF-IDF for
search_blog
The server is stateless. All blog content is already public (CC BY-SA 4.0). No PII, no auth tokens, no secrets.
Operations
Live deployment runs on a privacy-focused European VPS via Docker, fronted by Caddy with TLS. Server logs flow into a privacy-respecting analytics pipeline (Caddy JSON access logs, no client-side tracking, no JS pixels).
License
- Server code: MIT, see LICENSE
- Blog content (returned by tools): CC BY-SA 4.0, see creativecommons.org/licenses/by-sa/4.0/
Contact
- Blog: sovgrid.org
- Nostr:
[email protected](NIP-05) —npub1ndrjgfcwkc0y4753zyj3p7qjf795pvjq2dn4m7y7f72vmu7t0nrs6y363u - Bug reports / questions: open an issue
来源:README.md,提交 53838cd
工具
0版本历史
1- v1.0.0最新Sep 16, 2026
评分
已满足适用检查项的 85%
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 天内可连通必需25 分
- 已声明认证方式必需10 分
- 已列出工具必需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