# io.github.karandaid/karandeepsingh-blog (remote · karandeepsingh.ca)

Search and read Karandeep Singh's DevOps and AWS blog: articles and cheatsheets.

- Trust score: 76/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-14

## Components

- remote · `karandeepsingh.ca`: 76/100 (this document), [markdown](https://verifymcp.io/servers/karandaid-karandeepsingh-blog/karandeepsingh.md), [page](https://verifymcp.io/servers/karandaid-karandeepsingh-blog/karandeepsingh)

## Channel facts

- Endpoint: `https://karandeepsingh.ca/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `3.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-14.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 87/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 6338 tokens (~52/item across 121 items; 11 tools + 110 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 87% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http karandaid-karandeepsingh-blog https://karandeepsingh.ca/mcp
```

### Codex

```toml
[mcp_servers.karandaid-karandeepsingh-blog]
url = "https://karandeepsingh.ca/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "karandaid-karandeepsingh-blog": {
      "type": "remote",
      "url": "https://karandeepsingh.ca/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add karandaid-karandeepsingh-blog --url https://karandeepsingh.ca/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  karandaid-karandeepsingh-blog:
    url: "https://karandeepsingh.ca/mcp"
```

### Other

```json
{
  "mcpServers": {
    "karandaid-karandeepsingh-blog": {
      "type": "http",
      "url": "https://karandeepsingh.ca/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-13 (score 76, +1)

- [functional] New resource “atuin-shell-history-search”

### 2026-08-12 (score 75, +1)

- [functional] New resource “lambda-cost-tuning-memory-graviton”
- [functional] New resource “atuin”

### 2026-08-11 (score 74, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-10 (score 74)

First indexed and scored.

## MCP tools (11)

### `search_posts` (~103 tokens)

Search the blog

Search Karandeep Singh's blog (DevOps/AWS articles and cheatsheets). Returns ranked cards with title, URL, tags, date, reading time, and summary.

Input parameters:

- `limit` (number): Max results (default 8, cap 20).
- `query` (string, required): Search terms, e.g. 'aurora failover' or 'lambda cold start'.
- `section` (string): Optional: restrict to 'posts' or 'cheatsheets'.

### `read_post` (~77 tokens)

Read an article

Read a post's full text by URL, paginated. Returns a window of characters; call again with the returned next offset to continue.

Input parameters:

- `offset` (number): Character offset to start from (default 0).
- `url` (string, required): Post URL or path, e.g. /posts/aurora-postgresql-setup-guide/.

### `list_recent` (~29 tokens)

Recent posts

List the most recently published posts.

Input parameters:

- `limit` (number): Default 8, cap 20.

### `browse_by_tag` (~53 tokens)

Browse by tag

List posts with a given tag (e.g. aws, lambda, cost, aurora). Use list_topics to see all tags.

Input parameters:

- `limit` (number)
- `tag` (string, required): A tag name.

### `list_topics` (~24 tokens)

List topics

List every tag on the blog with a post count, for discovering what's covered.

### `related_posts` (~42 tokens)

Related posts

Given a post URL, find other posts that share the most tags with it.

Input parameters:

- `limit` (number)
- `url` (string, required): Post URL or path.

### `random_post` (~20 tokens)

Random post

Return a random post from the blog — a surprise pick.

### `get_cheatsheet` (~53 tokens)

Get a cheatsheet

Jump straight to a cheatsheet by topic (docker, cloudformation, cost, aurora, kubernetes, …) and get its full text.

Input parameters:

- `topic` (string, required): Cheatsheet topic or name.

### `list_cheatsheets` (~23 tokens)

List cheatsheets

List all cheatsheets (quick-reference guides) on the blog.

### `quiz_me` (~95 tokens)

Quiz me

Test the user's knowledge with real multiple-choice questions written for the blog's articles. Returns questions, options, and an answers section with explanations. Ask the questions first, then reveal the answers.

Input parameters:

- `count` (number): How many questions (default 3, max 10).
- `topic` (string): Topic to be quizzed on, e.g. aurora, lambda, docker. Omit for a random quiz.

### `get_commands` (~84 tokens)

Just the commands

Return just the runnable commands and code blocks from the best-matching article or cheatsheet — no prose. Use when the user wants the command, not the explanation.

Input parameters:

- `limit` (number): Max code blocks to return (default 6, max 12).
- `topic` (string, required): Topic or tool, e.g. docker, kubectl, terraform, psql.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/karandaid-karandeepsingh-blog/karandeepsingh#diagnostics

## Score history

- 2026-08-14: 76
- 2026-08-13: 76
- 2026-08-12: 75
- 2026-08-11: 74
- 2026-08-10: 74

## Links

- Remote endpoint: https://karandeepsingh.ca/mcp
- Repository: https://github.com/karandaid/hugov2.karandeepsingh.ca
- Website: https://karandeepsingh.ca/mcp-server/
- Changelog RSS feed: https://verifymcp.io/servers/karandaid-karandeepsingh-blog/karandeepsingh.xml
- Changelog JSON feed: https://verifymcp.io/servers/karandaid-karandeepsingh-blog/karandeepsingh.json
- HTML version of this page: https://verifymcp.io/servers/karandaid-karandeepsingh-blog/karandeepsingh