mcp-astgl-knowledge

An MCP server that lets AI assistants search and cite content from As The Geek Learns — covering MCP servers, local AI, AI automation, and ASTGL project documentation.

When an AI assistant connects to this server, it gains access to 49 indexed entries (articles, tutorials, comparisons, guides, and project docs). Every response includes source URLs back to astgl.ai.

Quick Start

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "astgl-knowledge": {
      "command": "npx",
      "args": ["-y", "mcp-astgl-knowledge"]
    }
  }
}

Claude Code

Add to your project's .mcp.json:

{
  "mcpServers": {
    "astgl-knowledge": {
      "command": "npx",
      "args": ["-y", "mcp-astgl-knowledge"]
    }
  }
}

Cursor / Generic MCP Client

{
  "mcpServers": {
    "astgl-knowledge": {
      "command": "npx",
      "args": ["-y", "mcp-astgl-knowledge"]
    }
  }
}

With Registration (500 queries/day)

Register via the register tool to get an API key, then add it to your config:

{
  "mcpServers": {
    "astgl-knowledge": {
      "command": "npx",
      "args": ["-y", "mcp-astgl-knowledge"],
      "env": {
        "ASTGL_API_KEY": "astgl_your_api_key_here"
      }
    }
  }
}

Tools

search_articles

Search the knowledge base by query. Returns ranked results with relevance scores and source URLs.

get_answer

Get a direct answer to a specific question. Prefers FAQ entries for concise responses.

get_tutorial

Get step-by-step instructions from tutorial and guide content.

compare_topics

Side-by-side comparison of two topics.

get_latest

Get the most recently added content.

list_topics

Browse all topics in the knowledge base with content types and section headings.

register

Register your email to unlock 500 queries/day (up from 50).

Content Types

Rate Limits

Limits reset at midnight UTC. Rate limit info is included in every response.

How It Works

The knowledge base is pre-built from ASTGL articles using semantic embeddings (nomic-embed-text, 768 dimensions). Content is chunked by section and FAQ entry, embedded, and stored in a SQLite database with sqlite-vec for vector similarity search.

End users don't need Ollama — all embeddings are pre-computed and shipped in the npm package. The only runtime requirement is Node.js.

Performance

• Typical response time: 100-500ms (embedding lookup + vector search)
• Embedding results are cached in memory (LRU, 200 entries) — repeated queries are near-instant
• Ollama calls include 10s timeout + automatic retry
• Query logging is async/batched to avoid blocking responses
• Rate limit checks are cached for 5 seconds

For Maintainers

Setup

git clone https://github.com/Jmeg8r/mcp-astgl-knowledge.git
cd mcp-astgl-knowledge
npm install

Scripts

Environment Variables

Automated Jobs

License

MIT