No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Thysrael · MCP Server · ★ 9.4k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Horizon safe to install? View the security audit →
🌅 Horizon AI curates the tech news. You just read. Horizon collects news from multiple customizable sources, uses AI to sco
| Stars | 9,437 |
| Forks | 1,456 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 71.7336657802374/100 |
| Last Updated | 2026-09-23 |
| Created | 2026-02-20 |
| Platforms | browser, mcp, python |
| Est. Tokens | ~15k |
Looking for a Horizon alternative? If you're comparing Horizon with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页
Build effective agents using Model Context Protocol and simple workflow patterns
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI
An Agentic Framework for Reflective PowerPoint Generation
Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Custom
Explore other popular mcp server tools:
Horizon is 📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达. It is categorized as a MCP Server with 9.4k GitHub stars.
Horizon is primarily written in Python. It covers topics such as aggregator, feishu-bot, llm.
You can find installation instructions and usage details in the Horizon GitHub repository at github.com/Thysrael/Horizon. The project has 9.4k stars and 1456 forks, indicating an active community.
Horizon is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Horizon on Agent Skills Hub include chatgpt-on-wechat, mcp-agent, AI-Infra-Guard. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: