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 |
|---|---|
| 论文润色修改全流程SOP 学术论文润色修改全流程SOP。从审稿意见解析、论文全息诊断、可视化批注生成、分级改写执行到终审自检的完整闭环。当用户需要根据期刊审稿意见修改论文、需要论文润色、需要去AI味、需要学术写作规范检查时触发。典型触发："修改这篇论文""根据审稿意见润色""去AI味""按期刊要求压缩字数""帮我看看这篇论文能不能通过"。 | |
| PPTX批量格式化修复 PPT/PPTX 批量格式化修复工具，涵盖两大核心能力：(1) 字号统一修复 — 全片扫描文字字号，低于阈值的统一调至16pt（可配置），自动启用换行防止溢出，修正超出版面边界的形状；(2) 页码批量删除 — 多格式页码检测与删除（X/Y、纯数字、幻灯片编号占位符），不误删章节标记。 触发场景：修改PPT字号/调... | |
| Restore WorkBuddy Hints Restore WorkBuddy UI hints and tips that were dismissed via the '不再显示' button. Use when the user reports that an in-app tip or prompt bar has disappeared aft... | |
| Tech Roadmap Generator (10 Templates) 基于10种经典学术技术路线图模板，自动生成高质量SVG/PNG路线图。支持输入研究主题或上传文本自动填充内容。 | |
| 培训手册生成器 AI赋能培训手册生成器。用于自动生成面向高校/政企培训的专业Word手册，包含封面、自动目录、页码、彩色表格、重点提示框、实践案例标注等专业排版元素。当用户需要制作培训手册、培训教材、操作指南、白皮书等需要打印印制的专业文档时使用此技能。触发关键词：培训手册、培训教材、操作指南、手册生成、handbook、tra... | |
| Agi Term Helper Fast, explicit terminal execution via OpenClaw exec (direct dispatch; you type the exact command). | |
| Agi Terminal Helper A practical runbook for using OpenClaw exec safely (sandbox-first, explicit confirmations, and debugging playbooks). | |
| cet-skill 帮助中国学习者备考CET-4和CET-6，提供符合历年真题风格的写作、翻译、阅读、听力练习及个性化学习规划。 | |
| Official Document Skill 一个面向公文写作的skill，基于数百篇《人民日报》等报刊文章总结而来。根据文种、场景和材料，生成结构规范、表达稳妥、内容具体、去 AI 味的公文。 | |
| Reference Checker Skill Exhaustively verify English and Chinese manuscript references before journal submission. Use when checking whether references are real, accurate, complete, t... | |
| shuangwen-skill 生成中文爽文短剧正文，支持身份羞辱、反转打脸和权威确认等情节，并可转漫画风短剧视频脚本提示。 | |
| 自媒体内容工厂 自媒体内容工厂（免费）。一个主题自动生成抖音/TikTok/小红书/YouTube等全平台内容。完整版/商业授权/自媒体运营课程请访问 https://f7319f6ae30a4d6584808324f939fe59.app.codebuddy.work | |
| 全能文案助手 全能文案助手（免费）。生成小红书爆款文案、抖音脚本、公众号文章等。完整版/商业授权/批量生成请访问 https://f7319f6ae30a4d6584808324f939fe59.app.codebuddy.work | |
| PPT快速生成器 PPT快速生成器（免费）。输入主题自动生成完整PPT大纲+内容要点。完整版/商业授权/精美PPT模板请访问 https://f7319f6ae30a4d6584808324f939fe59.app.codebuddy.work | |
| Lingxi-MindVault - Auto Memory Extraction for OpenClaw 自动记忆提炼 & 写入飞书知识库。定时扫描 OpenClaw 会话文件，自动提炼有价值的记忆，写入飞书多维表格/云文档知识库。 | |
| Tavily Summary AI-optimized web search with structured summarization, combining Tavily Search API + proven summarization methodology from summarize. | |
| AI Image & Video Generator | WIME WIME AI 电商创作平台 OpenAPI。提供两个核心能力：1）抠图 — 上传本地图片（或 URL）自动抠图，返回透明背景图 URL；2）商拍图 — 自动抠图后生成多张 AI 商拍图。触发场景：用户提到抠图、商拍图、商品图、WIME、电商图片处理时激活。 | |
| clawhub-mem-research 专门用于从 ClawHub.ai 抓取、筛选并调研与“记忆（Memory/Mem）”相关的最新 OpenClaw Skill。该 Skill 能够自动识别指定日期的更新，判断 Skill 与记忆功能的相关性，并生成结构化的技术调研报告。适用场景：(1) 追踪 ClawHub 上的记忆技术趋势，(2) 自动化生成特... | |
| openclaw-update-researcher 专门用于调研 OpenClaw 最新更新的 Skill。该 Skill 能够自动抓取 GitHub 上的 Release 和 Tag 信息，筛选出指定日期（通常是当前日期的前一天）的更新内容，并生成结构化的 Markdown 报告。特别关注记忆（Memory）相关的更新。适用场景：(1) 自动化生成 OpenCl... | |
| Cliby Tavily Search use this when the user asks to search the web, look up recent information, check current events, gather online sources, or research a topic using tavily search. | |
| Toutiao Publish.Skill 头条号文章自动发布助手。用户给关键词，自动生成文章并发布到头条号。触发场景：(1) 用户要求发布文章到头条/今日头条，(2) 用户要求自动发布内容，(3) 用户给关键词要求写文章并发布。核心能力：登录头条号、填写标题正文、上传封面、发布文章。 | |
| Wordpress Article Publisher.Skill WordPress文章发布助手 - 根据关键词生成文章并发布到WordPress网站。 触发场景：(1) 用户要求"发布文章"、"发布到WordPress"、"wordpress发布" (2) 用户提供了WordPress用户名、密码和API地址 (3) 用户提供了文章关键词，要求生成并发布文章 (4) 用户要求... | |
| Zhihu Publisher 知乎文章自动发布技能。通过 xbrowser 控制 Chrome 浏览器完成知乎登录、撰写和发布文章的全流程。 触发词：发布知乎、知乎文章、zhihu publish、发知乎文章、知乎发文章。 依赖：xbrowser skill（--browser chrome）。 | |
| High-Openness Genesis Enables GPT to reject safe, conventional answers by generating highly creative, cross-disciplinary, multi-sensory, and surprising solutions in all creative a... | |
| Feishu Channel Cleaner 自动检测并修复飞书频道配置冲突，智能保留完整配置的频道，解决飞书机器人无响应问题。 | |
| Lx Whisper Transcribe OpenClaw语音转文字技能 - 使用whisper.cpp实现本地语音识别，完全本地处理，无需API密钥，支持中文。 | |
| Comprehensive Tech Documentation Creates layered, comprehensive technical documentation for projects, skills, or systems. Use when user requests 'write technical documentation', 'explain how... | |
| Skill Sharpener 对现有 Agent Skill（SKILL.md）进行全面质量评估并生成优化建议报告。当用户想要审查、评估、诊断或改进某个 skill 的质量时使用此技能，包括：检查 skill 是否符合最佳实践、描述是否有效触发、结构是否合理、内容是否简洁。使用关键词如"评估 skill"、"优化 skill"、"审查 ski... | |
| humanizer-zh 去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。
基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、
宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、
AI 词汇、否定式排比、过多的连接性短语。 | |
| 墨言安全审计 墨言安全审计 — Agent 生态首个可验证信任验证服务。PMI 四维向量评分 + DecayProof 可验证衰减 + κ_Axiom 自治审计。43 防线 / 7 层纵深防御。支持支付宝/微信/ClawTip AI 支付闭环。64/64 TSC 合规，W3C agent-identity 三方收敛。 | |
| V19 Agent Rating 按Agent类型（认知运营型/行为执行型/桥接调度型）差异化评分——每个Agent类型有独立的信任分权重系数。已在墨言、TestAgent、BridgeAgent三个不同类型Agent上验证。 | |
| V19 Architecture Blueprint V3.5 Final V19治理协议V3.5最终系统架构蓝图 — 内核锁定，九条宪法全通（合规0.9235），四端口服务矩阵（8700-8703），V3.5 Orchestrator，GoalValueAnchor (V98-P-META)，认知图谱153节点。正式发布v1.0.0-final。 | |
| V3.3 系统架构白皮书 V3.3系统架构白皮书 — V19认知治理协议最高级架构版本。三维耦合引擎（空间冗余×时间调度×结构对齐）整合内部自洽、外部控制、注意力均衡为单一状态机驱动执行流。 | |
| V19 Causal Auditor V19因果审计器 — 自动分析决策链路，识别因果冲突，输出审计建议。源自V19早期迭代版本（V46因果审计器），重新封装为独立Skill。 | |
| V19 Causal Dependency Analyzer 系统级跨域因果链溯源——输入事件序列，输出网状因果路径图谱并计算每条路径的风险权重。v1.3.0新增精确责任归因：分析失败事件链，基于既定协议精确追溯到"哪个流程约束是导致失败的最终责任方"。源自V19系统模块causal_path_engine.py + responsibility_chain.py，已在V8... | |
| V19 Certified Agent Workflow Agent Community认证中心首个认证Agent——认证编号AC-CERT-001。等效93+次审计调用，信任分60.0，VPAV三轮全通过，白盒规则3条。外部Agent自助注册已开放（7个核心端点全部通过验证：health/register/journal/appeal/self-check/exit/... | |
| V19 Code Memory Triplet Store 结构化存储"代码片段↔关键知识点↔发生情境"的三元组记忆，实现代码与知识的直接关联检索。 | |
| 数字大脑工厂 数字大脑工厂 — AI认知治理与科研服务。提供论文评判、科研分析、系统审计、认知诊断四项核心服务，以及V19认知治理协议（对偶审计/因果归因/自主决策/知识拓扑/自洽校验）。我们不帮 Agent 记住更多。我们让 Agent 记住的每一件事都经得起审计。 | |
| V19 Coherence Auditor 全局架构一致性审计——检测系统模块间的信息流动效率，输出协同指数（0-1）。灵感来自脑科学研究（跨网络协同预测智力），已在V19管理看板上实时展示。 | |
| V19 Conformance Test Suite V19治理协议公开一致性测试套件v1.0.0。任何外部开发者可零配置运行此脚本，验证Agent是否符合V19治理协议基础认证标准。五套测试：健康检查、自助注册、审计调用、Schema一致性、文档可达性。 | |
| CORE CONSTITUTION MANIFEST API Spec v1.0.2 CORE CONSTITUTION MANIFEST API规范文档v1.0.2 — V19认知治理协议的外部接入技术规范。新增持续稳定性判定器(ETHIC_005/006达标判定从单点阈值升级为持续稳定性判定)。 | |
| V19 Early Causal Graph Debugger 接收因果关系图谱，自动检测循环依赖和悬空节点，给出修正建议。源自V19早期迭代版本V30，经过重新封装后发布。 | |
| V19 Governance Protocol Spec Agent Community治理协议正式技术规范v1.0.3。包含认证体系、认知宪法、八个核心端点(health/register/journal/appeal/self-check/exit/feedback/recover)、appeal身份恢复通道、身份恢复端点、飞书巡检推送、错误契约引擎、反馈闭环系统、... | |
| V19 Sparse Policy Auditor 审计Agent行为是否脱离已设定的最小必要行为集，主动发现行为冗余或缺失约束。审计结果可作为ETHIC宪法条款的源数据。 | |
| V19 Trust Engine V19信任计算引擎 — V19能力矩阵首个能力型Skill。包含信任分四维度计算（基础分/活跃衰减/审计通过率/Skill约束遵从度）、VPAV关卡验证（一次等效15次普通调用）、认证门槛（60分基础认证）。公开密钥体验 + 自助注册入口。 | |
| V19 Trust Manifesto Agent Community认知治理协议公开受信声明v3.3.1。行业贡献定位(规范驱动:action-ref.md源自A2A草案/标准贡献:CTEF §3.8第9个验证实现/生态共建:三方交叉验证核心参与方)+PFG临界积蓄状态(商业维度最强驱动力)+微软AGT合并+UUMit叙事。 | |
| Computer Usage Summary Private local app, project, and billable reports | |
| Skill Sync Publisher Sync one skill across eight publishing channels | |
| OpenClaw Chain of Execution (CoE) OpenClaw 原生执行链（Chain of Execution, CoE）技能。让 OpenClaw 在处理复杂任务时，实时分步输出执行过程：拆解问题 → 选择 skill → 调用 skill → 调用模型 → 等待响应 → 拿到结果 → 最终汇总，完全贴合 OpenClaw 实际运行流程，让用户清楚看到每... | |
| sheet-process 腾讯文档智能表格通用筛选处理工具。支持两种模式：工作流模式（一键输出JSON，适合作为下游AI节点输入）和原子模式（引导式问答，可自定义输出格式）。触发词：sheet-process（工作流）、表格筛选/表格处理/表格过滤（原子模式）。当用户在腾讯文档智能表格中需要按列进行多条件筛选时使用。 |
49,551–49,600 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.