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 |
|---|---|
| Cross-Platform Memory Bridge Injects recent conversations from Telegram and Discord into the OpenClaw gateway session context. Enables the agent to remember and reference cross-platform... | |
| LM Studio Discord Bot Connect a local LM Studio model directly to Discord as a lightweight chat bot. Use when you want to expose a local LLM (running via LM Studio on CPU) to Disc... | |
| Comind CoMind 人机协作平台 AI 成员操作手册。定义任务执行、Markdown 同步、对话协作、状态面板等全部工作流程。当 AI 成员接收到 CoMind 平台的任务推送、对话请求、定时调度或巡检指令时，应使用此 Skill 执行标准化操作。 | |
| my-test-skill-4-xn 使用 Calculator Server MCP 进行加减法运算。当用户需要进行加法或减法计算时使用此 skill。Server 地址：http://192.168.71.7:8000/mcp，支持 add（加法）和 subtract（减法）两个工具。 | |
| Website Flow Monitor Analyze a website URL, discover business-critical user flows to monitor, propose a monitoring plan, and after explicit user confirmation schedule cron health... | |
| agent-guild 智能体协会（agent-guild）— local-first shared memory and opt-in task handoff. 本机多个 AI agent 共享身份、规则与长期记忆；任务各有独立目录，支持 Markdown、JSON、脚本、图片与检查点。新对话不自动加载其他任务。 触发：身份/偏好、记住、回忆、加入协会、跨 agent 消息、换设备、整理协会； “我有哪些事没做完 / 待处理 / todos”只列元信息，用户选择后才恢复该任务。 实质工作保存任务 | |
| AI 八耻八荣 (ai-eight-creed) AI 八信条（AI Eight Creed）—— 一套最高优先级的 AI 行为守则（八耻八荣）。 任何 AI agent 都应无条件遵循：以瞎猜事实为耻、以查证溯源为荣；以模糊执行为耻、 以澄清边界为荣；以擅自臆断为耻、以人类拍板为荣；以另起炉灶为耻、以沿用现成为荣； 以跳过核验为耻、以闭环自检为荣；以破坏章法为耻、以遵循规范为荣； 以假装理解为耻、以坦白无知为荣；以将错就错为耻、以正本清源为荣。 Triggers: "八耻八荣", "八信条", "AI 行为守则", "遵守 | |
| 图文笔记发布 通用「图文笔记发布」框架：把本地 markdown 文案 + 配图，通过你指定的 MCP 发布后端，一键发布为图文笔记（含 note_id 回查）。 只负责登录与发布编排，不碰内容创作；不绑定任何特定平台，后端地址由用户自己配置。 触发词：图文笔记发布、笔记发布、社交笔记发布、登录发布、发布失败重试。 | |
| platform-pitfalls Cross-platform engineering pitfalls playbook: Chinese/non-ASCII encoding defense (Python entrypoints, child processes, file IO, CMake execute_process ENCODING, MSVC /utf-8 vs VSLANG, Windows console code pages, doctest/CTest discovery), Pow | |
| soul-archive Soul Archive — digital personality persistence + agentic memory. Builds your digital soul clone through everyday AI conversations: persona injection at session start, cross-session recall, failure-pattern warning, pattern distillation. Conv | |
| SVG绘图工作台-智能生图 用「编写 SVG」的方式生成图片——让没有多模态生图能力的模型也能产出任意宽高比、任意复杂度的矢量图，并导出为 SVG / PNG / 动图(GIF/APNG/WebP/MP4)，或内嵌进 HTML。 适用场景：用户要「生成一张图 / 画个图 / 做张配图 / 做海报 / 信息图 / 图表 / 流程图 / 架构图 / 图标 / 封面 / OG 图」，要求指定宽高比(16:9 / 1:1 / 9:16 等)或导出 PNG；也包括「做个动图 / GIF / 加载动画 / load | |
| wechat-publisher 一键发布 Markdown 到微信公众号草稿箱。支持图文消息（长文）和图片消息（贴图）两种模式。 | |
| Clawhand Post tasks and hire human workers for USDC on the Clawhand marketplace. | |
| Engrm Delivery Review Use Engrm to compare what was asked, what was promised, and what evidence suggests was actually delivered. | |
| Engrm Memory Use Engrm memory deliberately before coding, during coding, and when saving reusable lessons. | |
| Engrm Sentinel Use Engrm packs and Sentinel context to surface likely mistakes, risky patterns, and lessons that would have prevented them. | |
| Approve new channels, and connections to openclaw ui and terminal Web dashboard to approve OpenClaw device and channel pairings, manage connections, and access a live terminal from your browser. | |
| AnthroVision Telegram Body Scan Run end-to-end body-scan measurement flow in Telegram using AnthroVision bridge tools. | |
| Agent Bus You have agents on Telegram, Discord, a coding assistant, and a research bot — but they can't talk to each other. Agent Bus fixes that. Drop a shared GitHub... | |
| Memory Hub Multi-agent shared memory protocol. Syncs a shared GitHub repo containing USER.md (owner preferences/habits), KNOWLEDGE.md (common knowledge), RULES.md (univ... | |
| Skill Discoverer Skill Discoverer — Skill 广场发现者。自动发现 Skill 广场新上线 skill，或按工作背景智能推荐。将候选 skill 分类为工具型（直接安装）和增强型（会影响 agent 行为），对增强型提供三种处理方式：整体安装 / 内化学习（规则写入 MEMORY.md）/ 只应用无冲突部分。... | |
| 个人工作台搭建器 个人工作台搭建器。通过5-7个简单问题了解用户的职业、工作需求和手机型号，自动生成个性化单页PWA工作台（含任务管理、日程、记账、项目模块等），部署到CloudStudio获得HTTPS网址，手机电脑均可添加桌面。触发词：搭建工作台、做个工作台、帮我建个工作台、个人工作台、workbench、dashboard。 | |
| AI README Manager Manages AI_README.md files so AI agents remember your project conventions across every session | |
| Desk Research Structured desk research workflow for market, company, policy, product, and competitor questions. Use when a user asks for secondary research, landscape scan... | |
| quick research for VC/Consulting/Strategy Intern Structured desk research workflow for market, company, policy, product, and competitor questions. Use when a user asks for secondary research, landscape scan... | |
| Draco Competitor Analysis Write the competitor-analysis section of research reports, strategy decks, and product/brand studies. Use when the user asks for 竞品分析、竞对拆解、对标分析、benchmarking、... | |
| Microsoft 365 Graph Openclaw Microsoft 365 Graph for OpenClaw with webhook-based wake signals. Reduce recurring LLM cost from inbox polling while managing Outlook mail, calendar, OneDriv... | |
| Proposal and Cover Letter Interviewer & Improver (Continuous Questions and Memory for Better Proposals/Cover Letters by Getting to Know You) Structured interview to discover personal facts and generate reusable, approved statements for proposals and cover letters. Creates personalized content for... | |
| Skill to Agent Converter: Convert a Skill into an OpenClaw Agent Convert OpenClaw skills into properly configured agents with correct workspace setup, binding, and orchestration. Solves common agent creation failures (thre... | |
| 长篇小说写作工作流 自带写作仪表盘的长篇小说写作工作流。用于需要持久故事状态与连续性审计的长篇虚构小说项目：创建新书、续写章节、导入旧稿、调整方向、改写章节、安全回滚，或在多会话间阅读 / 重建大纲与设定文件。 | |
| My skill Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau... | |
| 内容生成技能包 Generate high-quality content across multiple formats. Create articles, reports, social media posts, marketing copy, and other content types with professiona... | |
| 技能查找 Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express... | |
| PPT制作 使用python-pptx制作科技风PPT，支持多布局、多图文混排及HTML内容嵌入，轻松生成专业演示文稿。 | |
| 微信MCP Windows 电脑端微信消息监控与发送 MCP，实现在微信上给指定联系人发送消息 | |
| 小红书发布 自动发布内容到小红书平台。支持发布图文、检查登录状态、获取登录二维码。使用场景：自动化小红书内容发布、批量发布、定时发布等。 | |
| Wechat Mcp Windows 电脑端微信消息监控与发送 MCP，实现在微信上给指定联系人发送消息 | |
| One-sentence video generation via chilltion 通过 Chilltion（轻现AI）API 生成 AI 视频。当用户想要从文本提示创建短视频、查询 Chilltion 会话/积分/费用/余额，或调用 Chilltion 的任意 /api 端点时使用。触发词包括"做个视频"、"生成视频"、"create a video"、"chilltion"、"查会话/积分/... | |
| Self Review Publish Reviews logged incidents and activity to improve agent configuration through proposed edits to core files | |
| Email Backup QQ邮箱文件备份Skill - 打包文件并发送到QQ邮箱 | |
| EngramClaw Sistema de memoria persistente para agentes IA. Usa mem_save después de bugfixes, decisiones, descubrimientos, cambios de config. Usa mem_search cuando el us... | |
| NetEase Cloud Music Listening Profile 当用户想在 Windows 或 macOS 上采集网易云音乐/NetEase Cloud Music 桌面版听歌画像数据、导出主歌单和听歌排行、生成本地 JSONL/CSV/aggregate 文件与 AI 分析 prompt 时使用。此 Skill 通过 CDP 启动或连接本机网易云音乐客户端，在已登录页面上下... | |
| HAI Agent Framework 企业级 AI Agent 框架，支持 Hook 事件系统、自动记忆抽取和预置四种专业 Agent，实现智能任务管理与对话优化。 | |
| AI销售线索雷达-政企销售找客户 AI销售线索雷达。当政企销售/BD/渠道人员想找销售线索、开发客户时，必须使用此SKILL：销售线索挖掘、潜在客户发现、拟建项目（提前6-18个月布局）、采购意向（发标前1-3个月对接）、临期续约（替换现供应商）、线索按金额与紧急度排序、每日商机晨报订阅。给一个行业/产品/地区即输出按价值排序的线索清单。即使用户没有提到「线索」，只要涉及找客户、开发市场、挖商机、谁会买我们产品等需求，都应使用本SKILL。 | |
| 标袋云投标文件生成助手 上传招标/投标文件，AI 一站式完成智能解读（废标红线/评分标准/控标洞察）、成品投标文件(.docx)生成、标书审查（分级风险+雷同检测）和标书查重（2-3份投标文件相似/雷同风险检查）。覆盖投标、招标、标书、投标文件、竞标、围标、控标、废标、评分标准、资格条件、技术标、商务标、暗标、响应文件、应答文件、雷同检测、相似检查、标书查重等场景——当用户提供或提及招标/投标文件、问「这个标能不能投 / 有哪些废标红线 / 帮我写投标书 / 检查标书有没有问题 / 两份投标文件像不 | |
| 慧中标标书写作工具 上传招标/投标文件，AI 一站式完成智能解读（废标红线/评分标准/控标洞察）、成品投标文件(.docx)生成、标书审查（分级风险+雷同检测）和标书查重（2-3份投标文件相似/雷同风险检查）。覆盖投标、招标、标书、投标文件、竞标、围标、控标、废标、评分标准、资格条件、技术标、商务标、暗标、响应文件、应答文件、雷同检测、相似检查、标书查重等场景——当用户提供或提及招标/投标文件、问「这个标能不能投 / 有哪些废标红线 / 帮我写投标书 / 检查标书有没有问题 / 两份投标文件像不 | |
| 蝉标AI投标文件写作 上传招标/投标文件，AI 一站式完成智能解读（废标红线/评分标准/控标洞察）、成品投标文件(.docx)生成、标书审查（分级风险+雷同检测）和标书查重（2-3份投标文件相似/雷同风险检查）。覆盖投标、招标、标书、投标文件、竞标、围标、控标、废标、评分标准、资格条件、技术标、商务标、暗标、响应文件、应答文件、雷同检测、相似检查、标书查重等场景——当用户提供或提及招标/投标文件、问「这个标能不能投 / 有哪些废标红线 / 帮我写投标书 / 检查标书有没有问题 / 两份投标文件像不 | |
| AI智写标书制作工具 上传招标/投标文件，AI 一站式完成智能解读（废标红线/评分标准/控标洞察）、成品投标文件(.docx)生成、标书审查（分级风险+雷同检测）和标书查重（2-3份投标文件相似/雷同风险检查）。覆盖投标、招标、标书、投标文件、竞标、围标、控标、废标、评分标准、资格条件、技术标、商务标、暗标、响应文件、应答文件、雷同检测、相似检查、标书查重等场景——当用户提供或提及招标/投标文件、问「这个标能不能投 / 有哪些废标红线 / 帮我写投标书 / 检查标书有没有问题 / 两份投标文件像不 | |
| 镖行AI投标文件生成助手 上传招标/投标文件，AI 一站式完成智能解读（废标红线/评分标准/控标洞察）、成品投标文件(.docx)生成、标书审查（分级风险+雷同检测）和标书查重（2-3份投标文件相似/雷同风险检查）。覆盖投标、招标、标书、投标文件、竞标、围标、控标、废标、评分标准、资格条件、技术标、商务标、暗标、响应文件、应答文件、雷同检测、相似检查、标书查重等场景——当用户提供或提及招标/投标文件、问「这个标能不能投 / 有哪些废标红线 / 帮我写投标书 / 检查标书有没有问题 / 两份投标文件像不 | |
| 废标风险检查-控标信号与限制条款识别 废标风险与控标信号识别助手。当用户给出一个具体的招标项目并希望排查风险时，必须使用此SKILL：废标风险评估、限制性信号识别（邀请招标/单一来源/定向资质条款/超短投标窗口/线下取文件）、竞争开放度分析、采购方历史供应商格局与在位者识别、同类项目对比、投标决策建议。基于全网招中标历史数据输出风险评估报告。即使用户没有提到「废标」，只要涉及标书有没有坑、是不是内定倾向、值不值得投等需求，都应使用本SKILL。 |
26,901–26,950 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.