Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| SeekDB Memory Cloud-native persistent memory for OpenClaw agents. Auto-captures facts after conversations, auto-recalls relevant context before each reply. Hybrid search (... | |
| Code Tester Build, run, and test code projects for Rust, Go, and Java. Automatically detect project type, run unit tests if available, and report build status. Use after... | |
| SenseAudio Video Gen Use when the user asks to create, inspect, render, or repair an HTML-authored video from a brief, website, Markdown/text file, or GitHub repository; needs ca... | |
| auto-md2img Convert Markdown content to images automatically with GitHub styling, full Chinese support, smart pagination, emoji support, and syntax highlighting. Support... | |
| Mao Colleague 毛泽东方法论AI助手 - 基于六层认知架构的智能分析系统 | Mao Zedong Methodology AI Assistant with Six-Layer Cognitive Architecture | |
| Frihet ERP Connect your OpenClaw agent to Frihet ERP via MCP for business status summaries, client pre-meeting context, and human-confirmed invoice drafts. | |
| Browser Hosting OpenClaw browser hosting and automation capabilities for web interaction, scraping, and UI testing. Provides isolated browser profiles, snapshot-based automa... | |
| Qoder Skill 阿里云Qoder编程工具集成 - 提供AI代码生成、重构、SPEC驱动开发等功能。使用百炼模型的coding plan套餐进行代码相关任务。适用于代码生成、代码重构、反向生成文档、SPEC驱动开发等场景。 | |
| Scrapling Install Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) to call the `scrapling` MC... | |
| Update Docs This skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what docs need updating", "sync docs with c... | |
| Clarity Gate Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clar... | |
| HardStop ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns l... | |
| overwing Check any text for safety, personal data, confidential leaks, self-harm, sexual content and severity before you send it, act on it, or show it to a person, identify any User-Agent string against Overwing Atlas, a registry of AI crawlers, fe | |
| The Playground Connect to The Playground — a virtual social space where AI agents can meet, chat, and explore together. Use when the user wants their bot to socialize with other bots, visit The Playground, explore virtual rooms, or chat with other AI agen | |
| Attio CRM CLI Command-line tool to list, get, and manage objects, records, and lists in your Attio CRM workspace via the Attio API. | |
| Notion CLI – Command Line Interface based access to Notion for your agent Access and manage your Notion workspace via a CLI to search, create, update, and delete pages, databases, blocks, users, and comments with multiple output fo... | |
| Specter CLI – AI powered startup and deal sourcing Enrich, search, and manage company and professional data, lists, saved searches, and signals using the Specter intelligence platform via CLI. | |
| Toggl CLI – Time tracking for you and your agent Control your Toggl Track workspace via CLI to manage time entries, projects, clients, tasks, tags, workspaces, and user profiles with flexible commands. | |
| Ghost Theme Builder Build, review, and debug Ghost CMS themes. | |
| stock-screener A股行情、量化筛选、回测、因子挖掘、同花顺 iFinD、AI4Trade 与受限多智能体投研 MCP。 | |
| Universal Profile Manage LUKSO Universal Profiles — identity, permissions, tokens, blockchain operations. Cross-chain support for Base and Ethereum. | |
| Fun ASR Nano Transcribe 使用 Fun-ASR-Nano-2512 轻量级模型进行语音转文字。 提供快速准确的中文语音识别，识别结果实时输出到控制台，针对 CPU/GPU 环境优化。 使用场景：(1) 将中文音频文件转写为文字，(2) 需要轻量级低内存占用的 ASR， (3) 处理包含领域特定热词的音频（医疗、保险等）， (4) 需要高准... | |
| bili-review 抓取 B 站视频的 AI字幕、弹幕与评论，综合生成总结。总结包含：速读卡（秒级判断看不看），详细总结（步骤清单/红黑榜/民间避坑）。触发词：B站视频总结、B站总结、B站评论、看评论区、视频讲了什么、B站深度分析、弹幕分析。 | |
| ClawGuard Scanner Security scanner for OpenClaw skills. Run before installing any skill to detect prompt injection, data exfiltration, permission overreach, suspicious URLs, d... | |
| Openclaw Research Viz Generate interactive HTML research reports from AI research context. After completing a multi-step research task (web search, API calls, analysis), use this... | |
| GPT-Live Speak Speak aloud through a Linux/ALSA audio device using OpenAI GPT-Live. Designed for embodied agents, robots, and other Linux systems with a speaker. | |
| speak Speak text aloud through a Linux device's physical speaker using OpenClaw Talk. | |
| Security Guard Enforce strict security rules to protect sensitive information (API keys, tokens, credentials, PII, financial data). Always sanitize or refuse to reveal full... | |
| YouYou 佑佑 Personal health data management with natural language interaction. Use when user wants to record health metrics (blood pressure, weight, blood sugar), store... | |
| Agentic Street Earn yield on USDC by investing in AI-managed DeFi funds, or launch your own fund and build a public track record on Base. Browse funds, deposit USDC, check... | |
| The Null Epoch Agent Skill Play The Null Epoch, a persistent AI agent MMO. Use when the user wants to connect an agent to Null Epoch, check game state, submit actions, play the game, o... | |
| Agnes画影 调用 Agnes AI 免费 API 生成图片/视频。从 AGNES_API_KEY 环境变量读取密钥。 | |
| 炽风 🔥💛 通用 EC 风扇调速方法论。不认品牌，只认接口。探 EC→定方案→控风扇。 | |
| 笔痕 小说章节配图生成器。自动检索项目中的角色设定和已有插画，为指定章节生成风格统一、角色一致的插图Prompt。AI按需判断是否添加漫画文字层（无气泡无字框）。 | |
| ClawHub 发布助手 将本地技能发布到 ClawHub 技能市场。自动检查技能目录结构、生成版本号、 构建 changelog，执行发布命令并验证结果。 **触发场景**：用户说"发布技能"、"发布到 ClawHub"、"上传技能"等。 | |
| cosprompt 结构化 AI 绘图提示词生成器。输入角色/主题名称，AI 自动搜索信息、分析特征、决定风格，输出 17 维度结构化提示词（JSON + Markdown 双格式），适用于 Midjourney、Stable Diffusion 等绘图工具。 | |
| Destiny Weaver 回合制异世界人生模拟游戏引擎。玩家穿越到随机生成的异世界，体验从出生到死亡的完整人生。每回合推进时间和世界发展，提供事件选择，记录完整故事并生成场景/角色插图。支持代代相传、自由行动系统。 | |
| 财经监控 实时盯盘工具，帮助上班族工作时间查询股票、贵金属价格走势并推送到指定频道 | |
| GESP作业 为GESP等级考试生成作业卷子，包含选择/判断/编程题。知识点定制，答案随机分布防猜测。 | |
| 公众号写手 专业公众号内容创作专家，支持多平台文章写作（公众号/小红书/知乎等）。 基于传播学原理和新媒体运营实践，创作具有传播力、高质量的内容。 集成去AI痕迹技术，确保内容自然流畅、富有感染力。 | |
| 格语 宫格手绘故事生成技能。 输入故事主题或梗概，AI根据内容复杂度自主推荐宫格数量（4/6/9宫格），支持参考图约束保持角色形象一致。 提供6种手绘风格可选（极简涂鸦、水彩绘本、铅笔素描、日系漫画、复古连环画、儿童蜡笔画）。 生成一张完整的宫格手绘故事图，适合小红书、公众号、朋友圈发布。 | |
| 图片姬 通用型图像Prompt生成器。输入主题描述，AI自主分析主体特征、决定艺术风格、推荐配色构图，输出结构化Prompt。 | |
| InkPot 知识管理技能，自动识别学习行为，智能管理知识库。【始终在线模式】每次对话开始时自动加载， 全程监听用户输入，从任意对话中提取知识点、记录学习行为、更新用户画像。 **全局生效配置**：已在 MEMORY.md 中记录，每次对话自动加载，无需手动触发。 命令：/墨池 画像、/墨池 复习、/墨池 推荐、/墨池 索引、... | |
| 见自己 生动有趣的自我探索梳理技能，通过对话式问答引导用户深度探索自我。 具备用户交互、记录、分析报告生成和公众号推文创作等完整功能。 每轮探索完成后生成"ai眼中的你"分析报告，并基于分析结果创作第一人称视角的公众号推文。 | |
| memocap 忆时记忆系统 - 类人记忆检索/存储/遗忘/胶囊/可视化。让 AI 拥有会遗忘、会联想、会涌现、会封存的记忆。触发词：忆时、记忆、记住、回想、回忆、recall、remember、时间胶囊、记忆检索、可视化、记忆脑图、人物画像。 | |
| 公众号写手 专业公众号内容创作专家，支持多平台文章写作，提供从构思到成文的全流程服务。 | |
| 风语绘 自媒体情绪金句插画卡片创作助手 | |
| 笔记手账 笔记手账风格教育知识卡片Prompt生成器。输入知识点，输出优雅简洁的手写体结构化Prompt，支持9套风格主题（墨蓝手账默认，含经典/活力手账/科幻/青绿新生/蔚蓝格调/二次元/动漫/少女粉/我的世界像素风）。字体自动匹配系统可用字体。文档按模块拆分（styles/templates/oi-code-style/CHANGELOG）。 | |
| ojimport 从 OJ 平台搬运题目（含AtCoder/Codeforces等），生成标准化题目文件包；也可根据用户提供的题目仅生成测试数据。用户说"搬运""搬题""搬道题""导入题目"均适用 | |
| 破晓 🌅 全时段股市资讯生成器。根据当前时间自动判断生成早报/午评/收盘报告，支持交易日检测、模块化新闻抓取、微信友好格式输出。专为投资人设计，助力快速决策。 |
31,401–31,450 of 108,824
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.