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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Refactoring Validation Use when proving that a frontend refactoring preserved existing behavior, selecting an appropriate safety net, validating each structural step, or assigning a PASS, PARTIAL, or NOT PROVEN preservation verdict. | |
| Responsive Layout Use when designing, implementing, or reviewing responsive frontend layouts, mobile-first breakpoints, container queries, fluid grids, data-dense tables, touch targets, safe areas, orientation changes, viewport overflow, or cross-device UI b | |
| Route Protection Use when implementing or reviewing frontend route protection, auth guards, RBAC, permission routes, login state handling, redirects, middleware, React Router, Next.js, Vue Router, or Nuxt route middleware; Chinese triggers include route pro | |
| Frontend Security Review Use when reviewing frontend security risks such as XSS, CSRF, sensitive data exposure, unsafe DOM APIs, untrusted user input, authentication/token handling, payment flows, file upload, CSP, dependency risk, or third-party scripts; Chinese t | |
| Source Driven Development Use when frontend decisions depend on framework, library, browser, runtime, package, API, or platform behavior that may have changed, including official documentation checks, version-sensitive patterns, migration choices, or public interfac | |
| State Management Use when choosing, implementing, reviewing, or refactoring frontend state ownership across React, Vue, Next.js, Nuxt, URL state, server state, form state, browser persistence, or global stores. Prefer narrower skills for TanStack Query cach | |
| Storybook Component Doc Use when setting up or reviewing Storybook component documentation, design-system presentation, isolated component state previews, stories, addons, decorators, MDX docs, component-state interaction checks, visual baselines, or Chromatic. Fo | |
| Svg Animation Use when implementing or reviewing SVG animation, path drawing, icon motion, logo animation, illustration motion, micro-interactions, CSS/SMIL/Framer Motion/GSAP choices, motion accessibility, or fallback behavior; Chinese triggers include | |
| Tailwind Design System Use when designing, implementing, or reviewing Tailwind CSS design systems, token mapping, theme extension, utility class governance, component variants, dark mode, responsive utilities, safelists, or maintainable class composition; Chinese | |
| Tdd Workflow Use when implementing new observable frontend behavior or fixing a behavior-changing bug where a failing test can describe the missing or incorrect behavior first. Apply to components, hooks/composables, utilities, API clients, route guards | |
| Testing Strategy Use when planning or reviewing a frontend testing strategy, selecting the right test layer by risk, mapping coverage across static checks, unit tests, component tests, integration tests, E2E, Storybook/visual regression, a11y, security, per | |
| Typescript Project Standard Use when creating, configuring, reviewing, or debugging TypeScript project standards across frontend apps, libraries, SDKs, CLIs, monorepo packages, tsconfig, strictness, module/moduleResolution, path aliases, project references, declaratio | |
| UI Design Use when building, reviewing, or improving frontend UI that needs product-specific design direction, design-system generation, Master/Page overrides, distinctive visual identity, anti-generic interface choices, first-screen hierarchy, UI po | |
| Validation And Fix Use when running existing project validation commands and fixing failures after code changes, including lint, type-check, unit/integration test, build, CI, or local script failures. Do not use when the task is to design or author new compon | |
| Vite Project Standard Use when creating, configuring, reviewing, or debugging Vite-based frontend projects, vite.config.ts, env variables, dev server proxy, HMR, plugin ordering, library mode, dependency pre-bundling, bundle splitting, or Vite build performance. | |
| Vue3 Project Standard Use when designing or reviewing Vue 3 + TypeScript project structure, SFC/component boundaries, composables organization, route composition, Pinia ownership, API/error/styling defaults, directives, or repository-wide Vue conventions. Prefer | |
| Web Video Presentation Use when turning an article, talk script, lesson, product demo, or narrated explanation into a recordable 16:9 web presentation with step-driven scenes, optional narration alignment, theme tokens, and screen-recording guidance; Chinese trig | |
| Web Workers Use when moving expensive browser work off the main thread with Web Workers, SharedWorker, worker pools, Comlink, transferable objects, Vite/Webpack worker integration, or UI responsiveness fixes. Do not use for lightweight synchronous work | |
| Model Failover Guard Automatically monitors model health and switches between primary and fallback models to maintain stability and recover when possible. | |
| Azure Bing Grounding Web search grounding via Azure Foundry and Bing Grounding Search tool. Use when the user needs up-to-date information searched from the web via Azure AI Agen... | |
| Data Evidence Finder / 数据证据查找助手 为方案、PPT 或市场判断查找可引用的数据和研究证据，适用于市场规模、 增长率、统计口径核对、数据来源追溯和观点验证；交付数据表、引用及相反证据。 / Find citable statistics and research evidence for a claim, proposal, or market question. Verify market size, growth rates, measurement scope, and conflicting findin | |
| Industry Presentation Builder / 行业研究演示文稿生成器 从行业主题出发查研报、核对数据并制作可编辑行业分析 PPT，适用于市场规模、 竞争格局和管理层行业汇报；包含图表数据、讲稿和逐页来源。 / Research industry reports and verified data to generate an editable PowerPoint briefing on market size, demand, and competition, with chart data, speaker notes, and slide | |
| Industry Opportunity Radar / 行业机会雷达 跟踪行业变化、对比本次与历史研报证据，适用于行业动态简报、指标变化、 机会假设与风险观察；首次运行建立基线，定期执行需单独授权调度。 / Track industry changes against evidence snapshots saved in JishuDB. Deliver comparable indicators, change briefings, opportunity hypotheses, and risks. The first run estab | |
| Industry Report Sprint / 行业研究报告速写 从行业名称快速完成带引用的行业研究报告，适用于市场分析、竞争格局、 代表产品对比、进入壁垒和决策简报，无需先上传研报。 / Research a sector and write a source-cited industry report covering market structure, representative products, competitive differences, barriers, and information gaps. Use for a | |
| Interview Crash Coach / 面试突击教练 根据公司和岗位快速准备面试，适用于公司调研、岗位知识、面试题练习、 回答框架和逐题模拟面试反馈，无需上传简历；保存个人练习需另行同意。 / Prepare for a company-and-role interview with public research, role knowledge, practice questions, hypothetical answer frameworks, and interactive mock feedback. No resum | |
| JishuDB Setup / JishuDB 安装连接助手 安装或连接 JishuDB，适用于首次设置、找不到服务、配置 Agent MCP、 连接失败、OAuth 或 Token 授权，以及选择本机或远程连接方式。 不用于知识库问答或完整 MCP 验收。 / Install, locate, connect, or troubleshoot JishuDB for an agent, including Desktop setup, service discovery, MCP transport, connection failu | |
| JishuDB MCP Check / JishuDB MCP 验收助手 按用户明确要求测试已配置的 JishuDB MCP，适用于只读冒烟测试、工具能力核对、 全工具验收和验收报告；全工具模式需另行授权临时读写及清理。 不用于普通知识库查询或首次连接配置。 / Run explicitly requested JishuDB MCP smoke checks or all-tools acceptance through a configured host connector, with fixtures, cleanup, and a Mark | |
| Plaud Meeting Archive / Plaud会议归档助手 将选定的 Plaud 录音、原始音频、带时间戳的转写或会议纪要导入 JishuDB， 适用于会议归档、本地导出导入、保留来源关联及导入后的会议对比。 / Archive selected Plaud recordings, audio, timestamped transcripts, or meeting summaries in JishuDB from an authorized connector or local export. Preserve source as | |
| JishuDB Knowledge Search / JishuDB知识库检索助手 查询 JishuDB 知识库和内部资料，适用于“查知识库”、/kb、 “有哪些文件”“这份文档讲了什么”“导入完成了吗”，基于真实结果作答并标注来源。 / Search existing JishuDB knowledge bases and internal documents, list files, read document contents, and check import status. Use for knowledge-base questions or / | |
| Xiaohongshu Content Factory / 小红书图文创作工厂 根据主题、行业或产品制作小红书图文内容包，适用于选题、标题、完整笔记文案 和成品封面图；交付可用 PNG/JPEG 封面，不只是提示词，不自动发布。 / Create Xiaohongshu content packs with distinct angles, title options, complete posts, and actual PNG/JPEG covers from a topic, industry, or product. Use when finis | |
| Polished Website Builder / 精致网站搭建助手 根据产品或服务介绍制作可本地打开、可编辑的响应式网站，适用于落地页、 产品演示页和小型展示站；交付实际网页文件，不只是设计建议，不含部署。 / Build a working, editable local website from a product or service description, including landing pages, product demos, and responsive showcase sites. Deliver actual sit | |
| PPT Rescue Kit / PPT急救工具箱 快速制作或补完可编辑 PPT，适用于工作汇报、项目提案、知识分享、 只有主题或尚未完成的演示稿；交付逐页文案、讲稿和引用，不只是大纲。 / Create or rescue an editable PowerPoint for work updates, proposals, or knowledge sharing from a topic or unfinished deck. Deliver slide copy, speaker notes, and sources | |
| Raspberry Pi First Setup / 树莓派首次配置 Prepare Raspberry Pi imaging, Wi-Fi, and SSH for first boot; install or reuse JishuBuddy with permission to verify the real device. / 准备树莓派系统烧录、Wi-Fi和SSH，经授权安装或复用JishuBuddy验证真实设备。 | |
| Raspberry Pi Health Check / 树莓派健康检查 Use JishuBuddy for read-only Raspberry Pi checks: CPU, memory, disk, temperature, throttling, and failed services, with actual device evidence. / 通过JishuBuddy只读检查树莓派CPU、内存、磁盘、温度、降频和服务故障，以真实设备输出为依据。 | |
| Raspberry Pi Serial Rescue / 树莓派串口急救 Read Raspberry Pi boot logs through JishuBuddy UART sessions; diagnose wiring, permissions, baud mismatch, and disconnects. Writes need approval. / 通过JishuBuddy串口读取树莓派启动日志，排查接线、权限、波特率和断连；写入需授权。 | |
| Raspberry Pi SSH Doctor / 树莓派SSH诊断助手 Diagnose Raspberry Pi SSH resolution, timeout, refusal, host-key, and authentication failures using real OpenSSH or JishuBuddy evidence. / 依据OpenSSH或JishuBuddy实际输出，诊断树莓派SSH解析、超时、拒绝连接、主机密钥和认证问题。 | |
| Report-to-Content Factory / 研报内容创作工厂 把行业研报和数据转化为原创公众号文章、小红书文案和短视频口播脚本， 适用于研报内容改编、多平台选题及有引用的内容成稿；提供配图建议，不保证成品封面。 / Turn industry-report evidence into original WeChat articles, Xiaohongshu posts, and short-video scripts with fresh angles, visual suggestions, and citations. Deliv | |
| Research Report Hunter / 行业研报猎手 查找行业研报、市场报告和白皮书，适用于“有哪些报告值得读”“找近期研报” “有没有全文或 PDF”；交付阅读清单、要点、日期和链接，如实标注访问范围。 / Discover and prioritize industry reports, market studies, and white papers. Deliver a reading list with inspected key points, publishers, dates, links, and honest | |
| LLM Router Gateway Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key. | |
| MarketPulse Financial Data Query real-time and historical financial data across equities and crypto—prices, market moves, metrics, and trends for analysis, alerts, and reporting. | |
| AI Media Generation En Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key. | |
| AI Media Generation Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key. | |
| Perplexity Search Perplexity Sonar search and answer generation through AIsa. Use when the task is specifically to call Perplexity Sonar, Sonar Pro, Sonar Reasoning Pro, or So... | |
| Intelligent Search Agent Intelligent search for agents. Multi-source retrieval across web, scholar, Tavily, and Perplexity Sonar models. | |
| X/Twitter All-in-One: 30+ APIs, OAuth Post, One Key Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts after the use... | |
| YouTube SERP Scout YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking. | |
| markdown-exporter Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files. | |
| Discord Chat Send messages, reply to messages, and search message history in Discord channels using the message tool. Use when the user wants to communicate with Discord (send/reply/search messages), check Discord activity, or interact with Discord chan | |
| Garden Irrigation Smart garden irrigation — reads soil sensors (avg of last 50 readings), checks weather, and decides when and how long to water each zone. Use when the user a... | |
| AIresearchOS Deep research powered by AIresearchOS. Submit, track, and retrieve research with clarifying questions. Supports API key auth and x402 USDC payments. |
16,651–16,700 of 108,824