Self Hosted AI MCP Server

by sovgrid Your server? Claim it

answering

Self Hosted AI is answering right now. Last checked 2 min ago. It exposes 5 tools. Last commit 21 Sep 2026.

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

Uptime history 52 days of history · worst day 88%

52 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

212 ms

Response time

average over 24h

Stars

last commit 21 Sep 2026

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 21 September 2026. No other catalogue keeps this.

21 Sep a tool appeared list_articles

Nothing serious here today

Today is the operative word: we check Self Hosted AI every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "self-hosted-ai": {
      "url": "https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io"
    }
  }
}

~/.codex/config.toml

[mcp_servers.self-hosted-ai]
url = "https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io"

.cursor/mcp.json

{
  "mcpServers": {
    "self-hosted-ai": {
      "url": "https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "self-hosted-ai": {
      "url": "https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

article

get_article

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.

articles

list_articles

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.

blog

search_blog

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.

diagnose

diagnose_sglang

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.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.sovgrid.org/self-hosted-ai?ref=mcp-io	streamable-http	answering	160 ms	2 min ago

Alternatives to Self Hosted AI

same job, measured the same way

Rankrat

by psyb0t

Self-hosted MCP for owned-site SEO, search analytics, indexing, monitoring, and safe remediation.

local only

ShotPulled

by shotpulled

Espresso dialing: log a shot, say how it tasted, get one change in your grinder's own clicks.

41 tools answering

P2Predict

by ahmed-khalil-hafsi

Local MCP server for parametric price benchmarking in procurement and engineering.

local only

Cortex RMCP

by dinglebear

Self-hosted homelab log intelligence over MCP, CLI, and REST with SQLite/FTS.

59 installs/wk local only

GCP Platform Engineer

by debilla

Read-only GCP tools for debugging incidents and finding cost savings

562 installs/wk local only

Sparkforensics MCP

by shuffle-works

MCP server for diagnosing Apache Spark event-log performance issues and comparing runs.

183 installs/wk local only

Myco Brain

by thegoodguysla

Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.

34 installs/wk local only

Agent Incident Reporter MCP

by csoai-org

Signed, hash-chained, tamper-evident AI incident records. EU AI Act Article 73 serious-incident repo

251 installs/wk local only

Self Hosted AI — questions

Answers built from our own checks of this server.

What can Self Hosted AI do?

It exposes 5 tools, read directly from the server on our last check. Among them: diagnose_sglang, get_article, list_articles, list_tags, search_blog. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Self Hosted AI working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 212 ms. The bar chart above shows every period we have measured.

How do I connect Self Hosted AI?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Self Hosted AI need an API key?

No. Self Hosted AI completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Self Hosted AI?

It answers our handshake in 212 ms on average, which is faster than 75% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Self Hosted AI open source?

Yes — it is published under the MIT licence, written in Python and 3 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.