Skip to content

org.sovgrid/self-hosted-ai

by sovgrid.org · remote · no sign-in to list tools · v1.0.0 · published by org.sovgrid

Engineering log of self-hosted AI on NVIDIA DGX Spark (GB10/SM121A). 60+ articles indexed.

Read only
CompareRegistry entry

5 tools: 5 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http self-hosted-ai https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Only reads 5Claude Code: allow
  • diagnose_sglangValidate an SGLang configuration for NVIDIA DGX Spark (GB10/SM121A).No findings

    Why it is in this group

    • The description's first verb is "validate": a word for reading.
    Description, as the server wrote it
    Validate an SGLang configuration for NVIDIA DGX Spark (GB10/SM121A). Pure pattern-matching against known failure modes documented in the Sovereign AI Blog. No inference, no external calls. Returns critical issues, non-fatal warnings, and a recommended baseline config. All parameters are optional; supply only what you have. With no inputs you get the recommended config and a 'unknown' verdict.

    Annotations the server declares

    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Diagnose SGLang Config
  • get_articleRetrieve the full content of a blog article by its slug.No findings

    Why it is in this group

    • The name "get_article" says "get": a word for reading.
    Description, as the server wrote it
    Retrieve the full content of a blog article by its slug. Returns the article body (Markdown) plus metadata. If the slug does not match any article, returns an Article with `error='article_not_found'` and other fields at their defaults.

    Annotations the server declares

    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Get Article
  • list_articlesList all blog articles.No findings

    Why it is in this group

    • The name "list_articles" says "list": a word for reading.
    Description, as the server wrote it
    List all blog articles. No TF-IDF computation — pure database listing. Use to browse the full corpus, paginate through articles, or filter by tag. For full-text semantic search use search_blog instead.

    Annotations the server declares

    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List Articles
  • list_tagsList all topic tags used across the Sovereign AI Blog corpus, with article counts.No findings

    Why it is in this group

    • The name "list_tags" says "list": a word for reading.
    Description, as the server wrote it
    List all topic tags used across the Sovereign AI Blog corpus, with article counts. Use this to browse the topic space before calling search_blog with a tag filter.

    Annotations the server declares

    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List Tags
  • search_blogSearch the Sovereign AI Blog for articles matching a natural language query, optionally filtered by tag and sorted by relevance or date.No findings

    Why it is in this group

    • The name "search_blog" says "search": a word for reading.
    Description, as the server wrote it
    Search the Sovereign AI Blog for articles matching a natural language query, optionally filtered by tag and sorted by relevance or date. Behaviour matrix: - query='', sort=* -> list newest-first, optionally tag-filtered - query!='', sort=relevance -> TF-IDF ranked, optionally tag-filtered - query!='', sort=date_desc -> TF-IDF filtered (score > 0.001), then sorted by date Pure read-only, deterministic for a given KB snapshot.

    Annotations the server declares

    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Search Blog

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 15:12 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
no
HTTP status of an anonymous initialize
none
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
none
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: The operation was aborted due to timeout

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http self-hosted-ai https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__self-hosted-ai__search_blog",
      "mcp__self-hosted-ai__list_articles",
      "mcp__self-hosted-ai__get_article",
      "mcp__self-hosted-ai__diagnose_sglang",
      "mcp__self-hosted-ai__list_tags"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as self-hosted-ai. Review it before you use it.