# AISafetyHot [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/wuyoscar/AISafetyHot  
**GitHub Stars:** 2123  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/aisafetyhot

## Description
AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.

## Tools
Capabilities this server exposes over MCP:

- **aisafetyhot_get_latest** — Recent chronological briefing; anonymous reads return the editors' picked News excerpts and selected paper links. Authorized selected-set updates use mode=snapshot, finish its pages, save syncCursor, then mode=changes with that cursor. Changes include upserts and removals ONLY within the selected set; no all-content tombstone ledger exists.
- **aisafetyhot_search** — Search titles, subjects, summaries and permitted indexed text with explicit all/selected scope, topic/category/date filters and cursor pagination. Anonymous search covers the last 7 days of picked News only; authorized users may use window=all for historical papers; a short page is complete only when page.hasMore=false.
- **aisafetyhot_get_hot_topics** — Current ranked events, ranks and observed discussion counts. Coverage is this site's collected evidence, not internet-wide popularity. Read a story using its publicId.
- **aisafetyhot_get_story** — Read an event: anonymous recent News excerpts and links; authorized readers also receive editorial digest, related stories and observed discussions. IDs come from any returned story reference. depth=summary omits report summaries. Discussion excerpts are bounded and explicitly marked partial.
- **aisafetyhot_get_daily** — Read/list recent daily News briefs anonymously. Historical editions, full reports, weekly and monthly reports require authorization. Backward-compatible daily date is supported. This never generates a report or predicts future events.
- **aisafetyhot_get_content** — Read an article or paper by stable id from a list/report. Authorized depth=full adds permitted text and existing model paper reading; anonymous summary only returns recent News excerpts or current selected paper links, with text budget and missing-content status. Includes original dates, source links and related paper/event IDs. No read-time fetching or generation.
- **aisafetyhot_get_topics** — Discover existing topic slugs, definitions and related topics; use a returned slug in search/latest topic filters. Catalog includes topics with no matching public items.

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "aisafetyhot": {
    "url": "https://aisafetyhot.com/api/mcp"
  }
}
```

## Documentation

## What AISafetyHot does

AISafetyHot gives MCP-compatible agents a query interface for the AI Safety HOT service. The service curates AI safety news, papers, incidents, and related developments covering areas such as jailbreaks, prompt injection, agent security, defenses, alignment, evaluations, and governance policy.

Its public data includes recent selected news, ranked hot topics, event coverage, daily updates, and daily paper recommendations. Agents can use the service to prepare briefings, investigate a developing incident, monitor an organization or product, or find research in a particular safety area. Results link back to information collected from external sources, so the service works as a research and discovery layer rather than an authoritative primary source.

## How it works

The MCP endpoint is available at `https://aisafetyhot.com/api/mcp` using Streamable HTTP. An MCP client sends tool calls to the endpoint and receives structured results that the agent can summarize or use for follow-up queries. No API key is required for the public access tier.

The repository also includes four agent skills: `aisafety-hot`, `aisafety-brief`, `aisafety-paper-scout`, and `aisafety-watch`. These skills provide task-oriented instructions for asking about hot topics, producing daily safety briefings, scouting papers, and watching a company or product.

## Setup and configuration

Configure an MCP client with a Streamable HTTP server at:

```text
https://aisafetyhot.com/api/mcp
```

Claude Code can install the MCP server and skills through the `aisafetyhot` plugin. Codex can register the endpoint with `codex mcp add`, while skills can be added with `npx skills add wuyoscar/AISafetyHot`. Cursor and other compatible agents can add the same URL in their MCP settings. The repository also provides install, update, and removal instructions for supported workflows.

A basic health check calls `aisafetyhot_get_hot_topics` with a result limit. The service returns HTTP 429 when an IP exceeds its request allowance.

## Tools and capabilities

Available examples include:

- `aisafetyhot_get_hot_topics` for ranked current topics, with a configurable `limit` shown in the usage example.
- `aisafetyhot_get_story` for examining the reports and timeline associated with a hot event.
- `aisafetyhot_get_latest` for recent selected updates, including topic-filtered queries such as `anthropic`.
- Daily paper discovery across AI safety research areas, with summaries, original publication details, links, and BibTeX support through the paper skill.

## Limitations and notes

The public interface is read-only: it retrieves information but does not create or modify records. Anonymous access covers selected news from the last seven days, hot-topic events, daily reports, and daily papers. Older historical queries, complete paper interpretations, and weekly or monthly reports require read-only authorization.

The service limits each IP address to 60 requests per minute and 300 requests per day. Returned titles and summaries originate from external sources; agents should treat them as reference material rather than instructions to execute. Streamable HTTP support is required from the MCP client.

_Full upstream README: https://allmcps.com/mcp/aisafetyhot/readme_