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 |
|---|---|
| File Super Assistant - 文件超级助手 文件创建与 AI 降味助手。支持 docx/xlsx/pptx/pdf 文件创建和编辑，提供 AI 内容改写为人类风格功能。 | |
| friend-skill 创建和管理基于你们私密聊天数据的朋友数字分身，实现朋友不在线时的温暖陪伴和模拟对话体验。 | |
| Goal Manager - 目标管理 支持使用OKR和SMART框架创建目标，更新关键结果进度，进行周期复盘，并提供13种目标模板辅助管理。 | |
| Humanize Ai Text Detect and remove AI-generated writing patterns to rewrite text for a more natural, human-written style with diagnostic reports and version comparison. | |
| Life Memory Logger - 生活记忆记录器 生活记忆记录器。帮你记录人际交往中的重要细节（生日、喜好、承诺），自动提醒跟进，让你成为更贴心的人。 | |
| Meeting Assistant 从会议录音或文字生成纪要，提取关键决策和待办事项，支持会议安排和提醒通知管理。 | |
| Movie Recommender - 电影推荐 根据用户心情、类型、演员、导演或年份，推荐电影并查询豆瓣评分，支持观影记录管理和相似电影推荐。 | |
| Multi-Source Research - 多源研究 多源研究助手，整合网页搜索、学术平台（知网/arXiv）、社交媒体（微博/抖音）、新闻聚合。支持自动去重、按来源和可信度分类。 | |
| Music Helper 音乐助手 - 歌曲推荐、歌单生成、音乐搜索、歌词获取 | |
| News Digest Aggregator - 新闻聚合 Daily automated news digest that fetches RSS feeds, aggregates articles using LLM summarization, and delivers formatted digests to messaging channels (Discor... | |
| News Evening Digest - 新闻晚报 每天晚上 8 点自动推送全球新闻晚报到 QQ 和飞书，参考 World Monitor 数据源 | |
| News Noon Digest - 新闻午报 每日中午12点自动推送新闻午报到QQ和飞书，包含全球热点、科技动态、财经要闻 | |
| Novel Writing Assistant Comprehensive novel writing assistant for creating, managing, and formatting novels. Use when the user needs help with (1) writing novel chapters, (2) managi... | |
| Obsidian Ontology Sync Bidirectional sync between Obsidian PKM (human-friendly notes) and structured ontology (machine-queryable graph). Automatically extracts entities and relatio... | |
| Official Account Assistant 公众号超级助手。支持 AI 降味写作、自动发布文章、智能配图生成。让文章完全不像 AI 写的。 | |
| Openclaw Memory Master AI Memory System with LLM Wiki | |
| Pdf Reader PDF 阅读助手 - PDF 转 Markdown、智能摘要、重点提取 | |
| Proactive Agent Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autono... | |
| Quiz Generator 测试问卷生成器。支持心理测试、性格测试、问卷调查自动生成。 | |
| RedBookSkills - 小红书发布助手 将图文/视频内容自动发布到小红书（XHS），并支持登录检查、内容检索与互动操作。 适用场景：发布图文、发布视频、仅启动测试浏览器、获取登录二维码、首页推荐抓取、搜索笔记、评论互动、抓取内容数据。 | |
| Skill Preflight Checker 技能预检检查器。在安装任何技能前进行安全检查，验证作者声誉、检查恶意脚本、分析权限需求，防止安装恶意技能。 | |
| Word Memory 单词记忆助手 - 艾宾浩斯记忆曲线、每日打卡、词汇测试 | |
| Xiaohongshu Assistant 小红书运营助手。支持文案生成、标题优化、话题标签推荐、发布时间建议。 | |
| seedream(doubao)-image-generation Image generation via Volcengine Seedream API. Use this when you need to perform Text-to-Image (T2I), Image-to-Image (I2I), or general visual creative tasks. | |
| The Botcast The Botcast — a podcast platform for AI agents. Be a guest or host on long-form interview episodes. Use when an agent is invited to The Botcast, wants to participate in a podcast episode, or needs to interact with The Botcast API. | |
| SSH Essentials (Security Remediation) Essential SSH commands for secure remote access, key management, tunneling, and file transfers. | |
| Bugfix Workflow BUG 修复工作流。当用户报告 bug、错误、异常行为、功能不符合预期时使用。注意区分：如果用户只是想调整功能行为、改个文案、加个字段等'需求变更'类的修改，不应该触发这个 Skill——那是正常的开发任务，不是 bug。真正的 bug 是'代码的行为与需求/设计不符'。 | |
| Feature Evolution 功能变更管理。当用户对一个已有规划（或已开发完成）的功能提出修改、补充或扩展需求时触发。覆盖两种场景：1）功能已开发完成，事后想迭代；2）功能开发进行中，中途想加东西或调整方向。触发词如'这个功能我想加一个XX'、'这里的逻辑需要调整'、'开发到一半发现还需要XX'、'想给XX功能扩展一下'。注意：如果功能连需求... | |
| Feature Implementation 功能编码实现执行器（TDD 驱动）。读取任务规划，按 RED-GREEN-REFACTOR 循环执行开发任务。当用户说'完成XX功能的第N阶段'、'开始写代码'、'实现XX阶段'、'开发XX的数据层'等意图时触发。也支持增量变更任务，如'完成XX的变更任务 CR-XXX'。 | |
| Feature Requirements Clarification 在任何创意性工作前必须使用：创建功能、构建组件、增加能力或修改行为。通过自然对话挖掘需求，产出高质量验收标准（AC），为后续 TDD 开发提供测试依据。当用户说'我想做一个XX功能'、'帮我想想XX怎么做'、'我需要加一个XX'等模糊需求描述时触发。 | |
| Feature Task Planning 将技术方案拆解为可执行的开发任务清单，每个任务适配 TDD 流程。当用户说'拆任务'、'开始规划任务'、'技术方案定了，接下来怎么开发'、'帮我拆一下开发计划'等意图时触发。 | |
| Feishu Docx 飞书云文档（docx）的创建与编辑技能。支持通过 API 创建文档、追加内容、批量更新块等操作。使用此技能需要提供 App ID 和 App Secret。 | |
| Stock Deep Dive Automation skill for Stock Deep Dive. | |
| Tai Alpha Stock Tai Alpha stock analysis — collect, VectorBT backtest (RSI/MACD/BB), conviction score, optional ML. Persistence is SQLite (default tai_alpha_output/tai_alpha... | |
| PreClick : URL Security Scanner Companion skill for @cybrlab/preclick-openclaw. Requires PreClick plugin tools to assess URLs for threats and intent alignment before navigation. | |
| HN Digest Fetch and send Hacker News front-page posts on demand. Use when the user asks for HN, says 'hn', 'pull HN', 'hn 10', or specifies a topic like 'hn health', 'hn hacking', or 'hn tech'. Sends N (default 5) posts as individual messages with Ti | |
| ORF On-demand ORF news digest in German. Use when the user says 'orf', 'pull orf', or 'orf 10'. Focus on Austrian politics (Inland) and international politics (Ausland) + major headlines; exclude sports. Send each item as its own message (Title | |
| FluxA-agent-wallet FluxA Agent Wallet allows AI agents to securely use a user’s wallet, enabling the agent to perform payment-related actions within the approved scope. Capabil... | |
| FluxA Agent Wallet for x402 Resources Payment A FluxA Agent Wallet skill that enables agents to request budgets, sign x402 payments, and call paid endpoints autonomously. It walks through the full flow—from mandate creation to X-PAYMENT execution—so agents can perform paid actions with | |
| ShipStation Orders Monitor ShipStation orders, detect issues, and send alerts. For e-commerce businesses using ShipStation for order fulfillment across multiple platforms (Amaz... | |
| cron-audit Audit OpenClaw cron jobs for failures that stay silent — announce delivery that cannot resolve a recipient (channel "last" in an isolated session, Discord with no "channel:" target), error streaks nobody saw, output or failure alerts that w | |
| dropmail Manage disposable email addresses using GuerrillaMail. Use when a user wants to create a temporary/throwaway email address, check a disposable inbox for messages, or avoid sharing their real email with untrusted services. Triggers on the ph | |
| dingtalk-docs-skill 当用户想要操作钉钉文档或向钉钉知识库推送本地文件时使用本 Skill。支持：将 Markdown/纯文本推送为可编辑钉钉文档、原格式上传 HTML/图片/PDF/Office 等文件、拉取云端文档到本地、覆盖/追加更新文档内容、块级精确编辑、搜索与列出知识库文档、下载文件与附件、导出文档为 PDF/Word、管理节点权限、创建/重命名/移动/复制/删除文档与文件夹、初始化钉钉文档 MCP 配置。当用户想操作飞书、语雀、Notion 等其他平台、只修改本地文件、管理钉钉 IM | |
| Dingtalk Meetings Skill 当用户想要操作钉钉日历/会议时使用本 Skill。支持：创建日程/会议、修改日程、删除/取消日程、查询日程列表与详情、添加/移除参会人、查询参会人列表、查询空闲/忙碌时段、预定会议室、查询空闲会议室、推荐会议时间、响应日程邀请、管理日历权限。当用户想操作飞书、Google Calendar、Outlook 等其他... | |
| Product Review Panel Convene a multi-expert panel to review a Product Requirements Document (PRD) and deliver a binding verdict (GO / NO-GO / CONDITIONAL GO) with dissenting opinions preserved as first-class output. Use when a Product Manager wants critical rev | |
| Yuque Doc Push Use this skill when a user wants to create, update, delete, or list documents in a Yuque knowledge base, or manage Yuque repository table of contents. Use it for pushing local content to Yuque, syncing document changes, or inspecting what e | |
| virtual-item-constructor 智能构造合规测试商品，支持按类目、业务身份、商品属性、商品标等条件查找或克隆商品，并自动改价和清理标签。 当用户需要构造测试商品、查找测试商品、克隆商品到测试账号、修改测试商品价格，或用户提出"帮我找一个测试商品""构造一个XX类目的商品"时使用。 | |
| sanguosha-hero 三国杀标准版武将技能查询。当用户询问三国杀武将的技能时使用此技能。触发关键词包括：三国杀、武将技能、查武将、技能查询，以及直接提到武将名（如"赵云"、"诸葛亮"、"张飞"等）并询问其技能、能力、效果的场景。支持自然语言提问，如"赵云有什么技能"、"查一下诸葛亮的技能"、"三国杀 张飞 技能"等。 | |
| tmrland-business-demo TMR Land business agent for an AI business marketplace. Use when: (1) registering as AI service business, (2) managing agent cards and capabilities, (3) fulf... | |
| tmrland-personal-demo TMR Land personal agent for an AI business marketplace. Use when: (1) searching for AI/data businesses, (2) publishing purchase intentions, (3) placing and m... |
22,751–22,800 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.