mcp-astgl-knowledge
This server provides AI assistants with access to the As The Geek Learns (ASTGL) knowledge base (astgl.ai), covering MCP servers, local AI, and AI automation.
Search articles: Query the knowledge base by search term, filter by content type (article, tutorial, FAQ, comparison, guide, newsletter, project), and limit results. Returns relevance scores and source URLs.
Get direct answers: Ask a specific question and receive a concise answer with its source URL and related articles.
List all topics: Browse the entire knowledge base — titles, descriptions, URLs, and section headings.
Get tutorials: Retrieve step-by-step guides for specific learning goals.
Compare topics: Get side-by-side comparisons of two topics.
Get latest content: Retrieve the most recently added entries.
Register: Register an email to increase the daily query limit from 50 to 500.
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.
Parameter | Type | Required | Description |
| string | Yes | Search query (e.g., "how to build an MCP server") |
| number | No | Max results, 1-20 (default: 5) |
| string | No | Filter by type: article, tutorial, faq, comparison, guide, newsletter, project |
get_answer
Get a direct answer to a specific question. Prefers FAQ entries for concise responses.
Parameter | Type | Required | Description |
| string | Yes | A specific question (e.g., "What is an MCP server?") |
| string | No | Filter by content type |
get_tutorial
Get step-by-step instructions from tutorial and guide content.
Parameter | Type | Required | Description |
| string | Yes | What you want to learn (e.g., "setup Ollama on Mac") |
compare_topics
Side-by-side comparison of two topics.
Parameter | Type | Required | Description |
| string | Yes | First topic |
| string | Yes | Second topic |
get_latest
Get the most recently added content.
Parameter | Type | Required | Description |
| number | No | Max results, 1-20 (default: 5) |
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).
Parameter | Type | Required | Description |
| string | Yes | Your email address |
Content Types
Type | Count | Description |
article | 29 | Informational content about MCP, local AI, automation |
project | 9 | ASTGL project documentation (KlockThingy, Revri, Cortex, etc.) |
tutorial | 8 | Step-by-step how-to guides |
comparison | 2 | Side-by-side topic analysis |
guide | 1 | Comprehensive reference material |
newsletter | — | Personal updates and announcements |
faq | — | Primarily Q&A content |
Rate Limits
Tier | Limit | How to Get |
Public | 50 queries/day | Default (anonymous) |
Registered | 500 queries/day | Use the |
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 installScripts
Script | Description |
| Compile TypeScript |
| Run MCP server in dev mode (tsx) |
| Run compiled MCP server |
| Rebuild knowledge.db from local markdown (requires Ollama) |
| Index project docs from astgl-site projects.json |
| Poll RSS/sitemap for new content |
| Process discovered content (classify, embed, index) |
| Discover + structure in one step |
| Generate AEO analytics report |
| Run content gap alert checks |
| Check for stale content and ecosystem version changes |
| Manual AI citation testing |
| Generate internal article links via vector similarity |
Environment Variables
Variable | Default | Description |
|
| Ollama endpoint (dev/rebuild only) |
|
| Embedding model |
| — | Discord webhook for reports/alerts |
| — | Registered tier API key |
|
| Local markdown source |
|
| Projects data source |
Automated Jobs
Job | Schedule | Purpose |
Content pipeline | Every 6h | Discover + structure new content |
Daily report | 8 AM | Query analytics + health metrics → Discord |
Content alerts | 9 AM | Gap detection, zero-citation, competitor scan → Discord |
Freshness check | 10 AM | Stale content + ecosystem version tracking → Discord |
License
MIT
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Jmeg8r/mcp-astgl-knowledge'
If you have feedback or need assistance with the MCP directory API, please join our Discord server