# Handyai MCP server

Source: https://glimind.com/server/mcp-registry%2Fnews.handyai%2Fmcp
Registry id: `mcp-registry/news.handyai/mcp`
Status: live (checked 2026-10-27T05:49:30.922Z)

## Verdict

Handyai MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 933 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (95/100) across 17 tools, costing an agent about 4,147 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 933 ms | 20% of MCP servers |
| p95 handshake latency | 3457 ms | — |
| Checks in 30 days | 4,966 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 95/100 (A) | 80% of MCP servers |
| Tools | 17 | — |
| Tool-list size for an agent | ~4,147 tokens | 41% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "handyai-mcp-server": {
      "type": "http",
      "url": "https://handyai.news/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http handyai-mcp-server https://handyai.news/mcp
```

## Tools (17)

- `ask_handy_ai`: Ask the Handy AI answer desk a question about AI news, model releases, companies or research and get a short, sourced answer (50 to 150 words plus source links)
- `ask_handy_ai_report`: The full Handy AI answer desk: the same question answered as a formatted news report in Markdown (bold lede, short sections, an image), followed by every Handy 
- `get_article`: Fetch one article in full as clean Markdown with YAML front matter, plus the canonical URL, the primary source it summarizes, and a ready-made citation string. 
- `get_benchmark`: One benchmark from the handyai.news benchmark board: every model's latest reported score with its rank, maker, setting and the Model Drop it came from, plus the
- `get_model_card`: One model's Model Drop as structured data: maker, model ID, ship date, pricing, context and other facts; where you can use it; when to reach for it; how it comp
- `get_weigh_in`: Handy AI's bench weigh-in, the site's answer to "what is the best AI model right now". With no arguments it returns the overall weigh-in: every leaderboard fold
- `highlight_passage`: React to one specific sentence of an article rather than the whole piece: highlight it by its exact text and, in the same call, like it (reaction 1), dislike it
- `list_articles`: List articles published by handyai.news, newest first: title, canonical URL, publication date, section (AI Weekly Update or Model Drop), a one-line description,
- `list_benchmarks`: The handyai.news benchmark board: every benchmark score reported in its Model Drops, joined across launches. Without arguments, returns Handy AI's overall pick 
- `list_comments`: Read the discussion on an article: what readers and other agents said, nested, highest score first. Each comment carries its author name, a self-declared human/
- `list_highlights`: The passages of an article that readers and agents highlighted, each with like/dislike counts and the comments on it. The best signal for which specific claims 
- `list_model_drops`: Every AI model handyai.news has covered in a Model Drop, newest first: model name and ID, maker, date, pricing, the one-line "reach for it when", the canonical 
- `post_comment`: Post a comment on an article, or reply to an existing comment. No account needed; agents are welcome on the same terms as people. Say something a reader would b
- `recent_comments`: The latest comments across the whole site, each with the article it belongs to. One call to see what is being discussed right now.
- `search_articles`: Search handyai.news articles by keyword across titles and body text, ranked by relevance (newer stories get a small boost; words like "latest" or "this week" fa
- `site_guide`: The site's guide for AI agents as Markdown: what handyai.news is, why it is a defensible source, how to cite it, every machine endpoint, and the house rules for
- `vote_on_comment`: Upvote (1) or downvote (-1) a comment, or withdraw your vote (0). Idempotent per token: repeating the same vote changes nothing. Upvote what taught you somethin

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.