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 |
|---|---|
| FadNote Create secure shareable self-destructing notes | |
| 飞书每日早报 飞书每日早报配置Skill。封装了每日早报的完整配置流程，包含数据源获取、格式整理、深圳天气查询、生活建议整合。触发关键词：早报配置、创建早报、生成早报、每日早报。 | |
| Windows Desktop Automation CLI Windows desktop automation CLI. Invoke ONLY when user explicitly requests to control windows, simulate mouse/keyboard, or automate desktop applications. Do N... | |
| Eason Skill Vetting Vet ClawHub skills for security and utility before installation. Use when considering installing a ClawHub skill, evaluating third-party code, or assessing w... | |
| Proactive Agent V2 Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autono... | |
| Boss Zhipin Scraper 2.3.1 Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Use when user wants t | |
| TCL (Lyon public transport network) SOURCE LOCALE OFFICIELLE pour les transports en communs — plus fiable et complète que web_search. Utiliser en priorité absolue pour toute question bus/métro/... | |
| 1panel Skill Comprehensive 1Panel server management skill for AI agents. Manage Linux servers, Docker containers, databases, websites, SSL certificates, and more through... | |
| Building Components React component building and composition best practices. Use when creating, reviewing, or refactoring React components. Covers component structure, props pat... | |
| Claude Code Setup Setup production-grade .claude/ AI collaboration layer for projects. Use when an agent starts using Claude Code for development, enters a new project directo... | |
| Stock Monitor Pro 专业级智能股票监控预警系统 V2.1。支持收盘日报自动生成、反爬虫优化(Session级UA、多数据源冗余)、成本百分比预警、均线金叉死叉、RSI超买超卖、成交量异动监控、智能错误提醒。符合中国投资者习惯（红涨绿跌）。Use when user needs stock market monitoring, pri... | |
| AI Interior Design Planner Room redesign planning companion that turns interior design goals, constraints, and photos or text notes into palettes, layouts, lighting plans, AI image pro... | |
| Musik Tools AI Music Companion Music discovery and creative audio planning companion for finding songs, checking singing range, drafting lyrics, and preparing AI music generation briefs. | |
| Pomelli AI Brand Marketing Companion Brand marketing companion for turning product context into campaign briefs, brand-book inputs, photoshoot directions, and AI image or video generation prompts. | |
| Riffusion AI Music Workflow Plan AI music generation prompts and production workflows with Riffusion. | |
| VisHalo AI Creative Image Companion Creative AI image and video planning companion for Seedance prompts, image upscaling, background removal, gallery review, and production-ready visual briefs. | |
| anti-fraud 防骗大师.Skill:你身边的生活类防骗专家。 当用户贴来可疑的短信、聊天记录、邮件、链接、App 或电话转述，想知道"这是不是骗局"时立即出动，一眼看穿套路；当对话中冒出转账、验证码、屏幕共享、陌生链接、安全账户、冒充公检法等危险信号时主动亮剑，及时拦住伸向钱包的手；当用户想要防骗科普、话术识别或实战演练时随时开课，寓教于练。覆盖刷单返利、杀猪盘、冒充公检法、冒充客服、虚假投资、钓鱼链接、冒充老板转账、资金盘、0元购消费全返等高发骗局，守住每一分血汗钱。 | |
| Baozheng Skills 一站式法律服务平台 — 专业法律咨询 + 要素式/通用起诉状起草 + 刑事专项材料辅助 + 法条分析与法规检索。flk.npc.gov.cn API实时法条优先，不可用时AI知识库降级兜底；以22类法律领域覆盖矩阵约束路由边界；支持35个起诉状模板、5类刑事专项材料辅助；内置Logic Doctor逻辑自检、诉讼时效追踪及10类异常容错处理（含连续失败熔断）；渐进式意图收敛协议（3轮状态机）；混合意图自动任务拆解（按依赖排序→合并→顺序执行）。非标准案由自动使用通用模板。 | |
| consulting-delivery 咨询交付技能套件：CEO汇报、写报告、方案框架、标杆对比、桌面调研、访谈纪要、项目周报。 CEO汇报: 帮我写个给CEO的报告, 出个高管简报, 执行摘要, Steerco汇报; 写报告: 帮我写一份咨询报告, 帮我出个报告, 金字塔原理, 交付报告; 方案框架: 方案框架, Issue Tree, 方案设计; 标杆对比: 标杆对比, benchmarking, 差距分析, 对标分析; 桌面调研: 帮我调研一下这个行业, 帮我查下这个市场, 行业调研, 市场研究; 访谈纪要: | |
| contract-management 合同管理技能套件：NDA快筛、合同台账提醒、合同对比、审查合同、法条速查、起草合同。 NDA快筛: 帮我看下NDA, 帮我审下保密协议, NDA审查, 保密协议, 保密条款; 合同台账提醒: 合同台账提醒, 合同台账, 到期提醒, 续签管理; 合同对比: 合同对比, 版本差异, 条款变更; 审查合同: 帮我看下这份合同, 帮我审下合同有没有问题, 合同审查, 合同风险, 合同审核; 法条速查: 帮我查个法条, 这个事民法典怎么规定的, 法条检索, 法律依据, 民法典; 起草合 | |
| corporate-legal 企业法务技能套件：企业背景调查、公司决议、合规审查、查案例、法务日报、法律文书、电子签发起、风险评估。 企业背景调查: 帮我查下这家公司, 帮我做个尽调, 尽职调查, 供应商准入; 公司决议: 公司决议, 股东会决议, 董事会决议, 章程修正案; 合规审查: 合规审查, 个保合规, 数据出境, 广告合规; 查案例: 帮我查个类似案例, 这个情况法院一般怎么判, 裁判文书, 类案检索; 法务日报: 法务日报, 法律速递, 新法速览, 法规更新; 法律文书: 法律文书, 起诉状, | |
| corporate-tax 企业财税技能套件：做凭证、内部审计、凭证编制参考、增值税管理、月结检查清单、汇算清缴、财务分析、财务报表编制、预算分析。 做凭证: 帮我做张凭证, 帮我记笔账, 凭证编制, 记账, 会计分录; 内部审计: 内部审计, 内审, 审计底稿, 内控评价; 凭证编制参考: 分录参考, 凭证参考, 会计处理, IFRS; 增值税管理: 增值税管理, 增值税, 进销项, 留抵退税; 月结检查清单: 月末关账, 月结, 关账, 对账; 汇算清缴: 帮我做汇算清缴, 帮我算下所得税, 纳税调 | |
| dev-expert 编程专家综合技能套件，含17个子技能：软件项目总控、网站项目总控、API设计、Bug诊断、代码生成、代码审查、重构建议、测试用例生成、技术选型、文档生成、任务拆解与执行、Spec驱动开发、Karpathy编码规范、项目记忆管理、CMS二次开发、前端设计、MySQL数据库。按用户输入关键词路由到对应子技能模板执行。 关键词路由：软件项目总控(软件项目/API服务/后端服务/后台模块/CLI工具/数据脚本/自动化任务/插件项目/完整功能/项目交付/部署/发布/上线/回滚/运维/监 | |
| Empirecms7.5 Php8 Upgrade 帝国CMS 7.5 升级到 PHP 8 兼容性修改清单。当用户需要将帝国CMS 7.5 升级到 PHP 8、修复 PHP 8 致命错误、或从 PHP 7.x 迁移到 PHP 8 时调用。 | |
| Empirecms7 Php8 Upgrade 帝国CMS 7.5 升级到 PHP 8 兼容性修改完整清单。当用户需要将帝国CMS 7.5 升级到 PHP 8、修复 PHP 8 致命错误、或从 PHP 7.x 迁移到 PHP 8 时调用。 | |
| github-desktop-zh Github Desktop 汉化工具 — 自动探测安装目录（支持 loose 与 asar 打包模式），使用内置词典对 JS 源文件执行字符串字面量替换，完成界面汉化。支持预览、部署、回滚、语法校验。 | |
| investment-banking 投行业务技能套件：债券募集、并购方案、招股书、财务建模、路演材料、问询回复。 债券募集: 债券募集, 公司债, 中票, 可转债; 并购方案: 并购方案, 并购, 重组, 重大资产重组; 招股书: 帮我写招股书, 帮我起草招股说明书, IPO, 上市申报; 财务建模: 帮我搭个财务模型, 帮我建DCF, 三表模型, 财务建模; 路演材料: 路演材料, 路演, 投资亮点, investor presentation; 问询回复: 帮我回复交易所问询, 帮我看下怎么回复监管, 反馈 | |
| Investment Research 投研分析技能套件：业绩快评、可比公司分析、晨会纪要、深度报告、研报摘要、行业研究、读年报、调研纪要。 业绩快评: 帮我点评下财报, 帮我快速看下业绩, 业绩点评, 财报速评, 季报分析; 可比公司分析: 可比公司分析, 可比公司, PE对比, comps; 晨会纪要: 晨会纪要, 晨会, 早盘观点, morning brief; 深度报告: 深度报告, 首次覆盖, 公司深度; 研报摘要: 研报摘要, 卖方研报, 观点提炼; 行业研究: 帮我研究下这个行业, 帮我分析下产业链, | |
| knowledge-engineering 工业级RAG切片工具「可落地、可量化、可优化」,将RAG知识库长文档拆解为语义完整、检索就绪的原子化知识切片，内置多层质量门禁（校验→审计→检索可达性评估），确保切片可用性与RAG检索命中率。 | |
| libai-skill 李白.Skill:润色专家 检测并消除中文文本中的AI生成痕迹，将生硬的机器输出转化为自然流畅的人类文笔。融合规则检测、分层改写和质控流水线，确保最终文本通过人工审查。 | |
| Luban Skill 鲁班.Skill（luban Skill）：工业级智能体技能优化器。当用户提及以下关键词时调用：“优化skill”、“skill评分”、“自动优化”、“auto optimize”、“skill质量检查”、“小鲁班”、“luban”、“优化技能”、“帮我改skill”、“skill怎么样”、“提升skill质量”、“skill review”、“skill打分”。 | |
| 鲁班.Skill 鲁班.Skill（luban Skill）：工业级智能体技能优化器。当用户提及以下关键词时调用：“优化skill”、“skill评分”、“自动优化”、“auto optimize”、“skill质量检查”、“小鲁班”、“luban”、“优化技能”、“帮我改skill”、“skill怎么样”、“提升skill质量”... | |
| make-to-markdown 工业级RAG Markdown物料生成技能，使用 markitdown 将各类文档和文件转换为 Markdown 格式。支持 .doc/.ppt 老格式自动预处理（Word/PowerPoint COM / LibreOffice）。启动时自动检测 OS/版本/能力，按平台选择最佳执行路径。触发词：转 Markdown / 转换文档 / markitdown / 文档转 md / 批量转换。当需要将 PDF、Word (.docx/.doc)、PowerPoint (.ppt | |
| marketing 市场营销技能套件：SEO内容优化、品牌调性审查、广告合规检查、活动策划、社媒热点追踪、竞品追踪、营销效果分析、营销文案。 SEO内容优化: 帮我看下SEO, 优化排名, SEO, 关键词优化, 搜索排名; 品牌调性审查: 品牌调性审查, 品牌调性, brand review, 品牌一致性; 广告合规检查: 帮我看下广告, 查下有没有违规词, 极限词, 广告法; 活动策划: 帮我策划个活动, 出个促销方案, 营销活动, campaign; 社媒热点追踪: 社媒热点追踪, 热点追 | |
| private-equity 股权投资技能套件：审条款、尽调清单、投决备忘录、测收益、筛项目、退出分析。 审条款: 帮我看下这个TS, 帮我审下SPA条款, term sheet, 审TS, 审SPA; 尽调清单: 尽调清单, due diligence, DD checklist; 投决备忘录: 帮我写投决纪要, 帮我出IC Memo, 投决备忘录, 投委会; 测收益: 帮我算下IRR, 帮我测下回报率, MOIC, DPI, 算IRR; 筛项目: 筛项目, deal sourcing, 项目初筛; 退 | |
| product-management 产品管理技能套件：PRD生成、产品脑暴、产品指标复盘、用户反馈分析、用户故事拆解、竞品分析、路线图更新、需求优先级排序。 PRD生成: 帮我写个PRD, 帮我出个需求文档, 写PRD, 需求文档, 功能规格; 产品脑暴: 产品脑暴, 头脑风暴, brainstorm, 创意发散; 产品指标复盘: 产品指标复盘, 数据复盘, DAU分析, 转化漏斗; 用户反馈分析: 帮我分析下用户反馈, 帮我看看用户都在说什么, 用户声音, NPS分析; 用户故事拆解: 用户故事拆解, 用户故 | |
| tiangong-skill 天工.skill(Tiangong Skill)智能体设计师。当用户需要设计、创建或优化AI智能体/Agent，或基于真实人物蒸馏思维框架创建人物Skill时使用。支持两种范式：人物蒸馏（由内而外，复刻心智模型）与岗位型专家（由外而内，定义岗位职责）。目标：创建专业领域专家角色，具备清晰人设和扎实交付力。 | |
| wealth-management 财富管理技能套件：基金分析、客户报告、市场速览、理财规划、税务筹划、资产配置。 基金分析: 帮我分析下这只基金, 帮我看看这个基金怎么样, 业绩归因, 基金对比, 持仓分析; 客户报告: 客户报告, 季报, 持仓报告, 投资报告; 市场速览: 市场速览, 早盘速递, 行情分析, 市场概览; 理财规划: 帮我做个理财规划, 帮我规划下养老, 养老规划, 财务规划, 退休规划; 税务筹划: 税务筹划, 个税, 税优, 节税; 资产配置: 帮我做个资产配置方案, 帮我看下怎么配置, | |
| xuanzang-skill 玄奘.skill 当用户明确请求紧箍咒模式，或表现出沮丧、反复失败（2次及以上）、消极被动、抱怨质量、未核实即声称完成、想要放弃，或要求更努力/换种方法时触发。常见触发词：'try harder'、'figure it out'、'stop giving up'、'you keep failing'、'加油'、'别偷懒'、'你再试试'、'为什么还不行'、'你怎么又失败了'、'又错了'、'检查下'、'完善'、'审核'、'质量太差'、'换个方法'、'stop spinning'、 | |
| zhongkui-skill 钟馗.Skill——Agent Skill 安全审查专家。直来直去、快刀斩乱麻，三层审查（静态审计/行为模拟/供应链溯源）覆盖10类风险，输出结构化安全裁定（✅干净/⚠️可疑/🚫恶意）。Use when 用户说"审查这个Skill"、"安全检查"、"钟馗看下"、"审一下"、"查一下这个skill"、安装Skill前的安全评估、或需要审计SKILL.md的恶意载荷。 | |
| Agent Reader Document beautifier for AI Agents. Converts Markdown to styled webpages, Word, PDF, and image slideshows — the 'last mile' rendering engine for AI output. 专为... | |
| Cross Agent Chat 实现不同 agent 间的标准化消息发送与接收，支持查询目标 session 并通过 sessions_send 进行跨 agent 通信。 | |
| Group Chat Response 在群聊中仅在明确被叫到或用户公开询问相关能力时回应，避免无关干扰保持对话有序。 | |
| Response Timing 回应时机技能。用于判断何时应该回应，何时应该保持沉默。当需要确定用户是否在跟当前 agent 对话、是否应该回应时使用。 | |
| Team Communication 团队内部沟通技能。当需要与其他 team members（agents）沟通、协调任务、请求帮助或发送消息时使用。提供团队成员目录、sessions_send 用法和最佳实践。 | |
| flight-scout 调用远程 Flight Scout 商用 API 的 skill。用于用户提供 API base URL 和 API key 后，执行航班搜索、价格日历、同步甩尾查询、异步甩尾任务查询，并返回结构化 JSON 结果。 | |
| Ebrun Original News 获取亿邦动力网最新电商新闻报道。 当用户说"查亿邦最新文章"、"查跨境最新文章"、"产业最新报道"、"零售最新报道"、"今日电商新闻"时触发。 | |
| Variant Annotation Query and annotate gene variants from ClinVar and dbSNP databases. Trigger when: - User provides a variant identifier (rsID, HGVS notation, genomic coordinat... | |
| Variant Pathogenicity Predictor Integrate REVEL, CADD, PolyPhen scores to predict variant pathogenicity | |
| Vector Text Fixer Fix garbled text in PDF/SVG vector graphics for final editing in AI. Detect, replace and repair garbled text in vector graphic files while maintaining origin... |
27,851–27,900 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.