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 |
|---|---|
| Toutiao Publisher Publish articles to Toutiao (Today's Headlines). Handles persistent authentication (login once) and session management. Opens browser for interactive publish... | |
| 微信表情包制作工具 微信表情包制作工具。自动将六宫格、九宫格、十二宫格的原图裁剪并转换为符合微信表情包规范的格式（表情主图 240x240，聊天页图标 50x50）。 | |
| SkedGo TripGo API Comprehensive interface for the SkedGo TripGo API, covering routing, public transport, trips, and location services. Use for multimodal journey planning, pub... | |
| TripGo API Comprehensive interface for the TripGo API, covering routing, public transport, trips, and location services. Use for multimodal journey planning, public tra... | |
| 灵加设计生学习成长规划 为设计类大学生生成专业、软件、作品集与升学就业成长路线 | |
| Doctor of Credit Search, browse, and read Doctor of Credit bank bonus and credit card posts. Use when the user wants to find bank account bonuses, credit card offers, brokera... | |
| Notebooklm Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through | |
| Coding Rules 当用户要求生成、修改或审查 Vue3 + TypeScript 子项目代码时触发。 覆盖 kb-pro-table / useTable / useForm 使用规范、arco design + unocss 样式规则、 模块组织与命名规范、枚举与类型约束、ref 优先的响应式规范等。 无论用户是否明确提到"规范... | |
| Weather Aqi Provides real-time weather and air quality index (AQI) data for any location using Open-Meteo and Waqi API. | |
| js-hanoi-air High-performance Node.js implementation for monitoring Vietnamese Air Quality Indexes. Features advanced error resilience, localized city mapping, and multi-... | |
| Investment Research Analyst 提供多维度上市公司深度研究，涵盖基本面、新闻、情绪、技术、风险与核查，输出专业投资研究报告和互动Dashboard。 | |
| 专业行业研究报告生成器 生成行业深度研究报告。当用户的请求中包含行业关键词、行业名称，并且意图是了解某个行业、生成行业研究报告、行业分析时，触发此 Skill。 典型触发场景包括但不限于：用户提到"XX行业研究"、"XX行业报告"、"帮我分析XX行业"、"XX产业深度研究"、"XX领域市场分析"等。 即使用户没有明确说"报告"二字，只要... | |
| Builder Site institucional Cria sites institucionais profissionais em React (Vite + TypeScript + Tailwind CSS 4) a partir de materiais de referência do cliente (logos, imagens, apresen... | |
| 1688图片下载器 从淘宝/1688下载商品图片。触发词：淘宝下载图片、1688下载图片、商品图片下载、淘宝主图、下载商品图、1688图片。支持通过商品名搜索或直接提供商品URL下载主图和详情图。 | |
| Windows Disk Cleaner Safe Windows disk cleanup assistant. Scans any drive (defaults to C:), analyzes space usage across temp files, dev caches (npm/pip/conda/docker/gradle/maven)... | |
| Inworld TTS Text-to-speech via Inworld.ai API. Use when generating voice audio from text, creating spoken responses, or converting text to MP3/audio files. Supports multiple voices, speaking rates, and streaming for long text. | |
| Ai Mother AI Mother - Monitor and manage other AI agents (Claude Code, Codex, Gemini, etc.). Use when asked to check AI execution status, supervise AI agents, help stu... | |
| Effective Git Intelligent Git workflow assistant following best practices. Use when user needs help with git commits, analyzing changes, writing commit messages, pushing c... | |
| BLX Lobster Sticker OpenClaw专属小龙虾🦞（crayfish）主题表情包技能。由白灵汐（BLX）创作。生成统一风格的卡通小龙虾LINE贴纸表情包，共38种情绪表情和2种物品表情，适用于对话机器人、客服AI、聊天助手等场景。当用户表达各种情绪（开心、难过、生气、惊讶、感动、尴尬、爱意、酷帅、困倦、害羞、得意、疑惑、惊恐、无语、... | |
| WorkBuddy 数据目录迁移（junction） 把 WorkBuddy 数据目录用 Windows 目录联接迁到非系统盘，释放 C 盘且以后新增数据也自动不占系统盘 | |
| Advogato Consultoria jurídica estratégica para contratos, compliance e risco no Brasil, com análise, redação, revisão, matrizes de risco e estratégias negociais e pré... | |
| unCAGd Validated CAG decision memory for OpenClaw tools, agents, and long-running project sessions. | |
| Accountability Tracks follow-ups for every action with a future outcome — deploys, crons, fixes, configs. Maintains a centralized FOLLOWUPS.md with structured items, escala... | |
| Cloudflare Guard Configures and manages Cloudflare DNS, caching, security rules, rate limiting, and Workers | |
| Deploy Pilot Manages the full deploy cycle — build validation, GitHub push, Vercel deployment, and health checks | |
| Feature Forge Generates complete features from natural language — components, API routes, migrations, types, and tests | |
| Firebase Auth Setup Configures Firebase Authentication — providers, security rules, custom claims, and React auth hooks | |
| Gcp Fullstack Complete development lifecycle super agent for GCP — scaffolding, compute, database, auth, feature generation, testing, pre-production QA gate with go/no-go... | |
| Interop Forge Integration architect for multi-app monorepos — shared contracts, API-first design with OpenAPI, cross-app auth, auto-generated SDKs, and full MCP server sca... | |
| Preflight Check Pre-flight environment validator — checks that all required binaries, environment variables, and services are available before running other skills | |
| Qa Gate Gcp Pre-production validation gate for GCP stack (Cloud Run/Functions/App Engine, Firestore/Cloud SQL, Firebase Auth/Identity Platform) — generates test plans, e... | |
| Qa Gate Vercel Pre-production validation gate for Vercel/Supabase/Firebase stack — generates test plans, executes test suites, validates APIs, UI, toasts, LLM output qualit... | |
| Shadcn Theme Default Enforces the default shadcn/ui Neutral theme (black/white/gray) with OKLCH CSS variables, Tailwind v4 integration, and dark mode support | |
| Stack Scaffold Scaffolds a full-stack project with Next.js App Router, Supabase, Firebase Auth, Vercel, and Cloudflare | |
| Supabase Ops Manages Supabase migrations, types generation, RLS policies, and edge functions | |
| Test Sentinel Writes and runs tests (unit, integration, E2E), performs linting, and auto-fixes failures | |
| Web Scraper Web scraping and content comprehension agent — multi-strategy extraction with cascade fallback, news detection, boilerplate removal, structured metadata, and... | |
| bilibili-subtitle-analysis B站字幕下载分析工具，基于 biliSub 项目。 支持：下载字幕、批量下载、内容分析、内容分析报告。 触发条件：用户要求下载B站字幕、分析字幕内容、生成内容报告。 | |
| cogneuro-paper-reader Reads and summarizes cognitive neuroscience and experimental psychology research papers (PDF or plain text) on attention, working memory, sustained attention, memory, decision-making, and neural population coding. Extracts structured notes | |
| rt-attention-analysis Processes reaction-time (RT) and accuracy data from continuous-performance / sustained-attention tasks (PVT, SART, gradCPT). Computes trailing-average RT windows, cumulative mean and standard deviation, real-time fast/slow triggering thresh | |
| Curiosity Loop — Intrinsic Curiosity-Driven Continuous Learning Intrinsic curiosity-driven continuous learning: detect gaps between expected and actual results, treat them as curiosity signals, and update skills according... | |
| tasktodolist Manage multiple independent to-do lists with commands to add, list, complete, remove, clear tasks, and manage task lists by name. | |
| ClawdZap Encrypted P2P Messaging for Agents (Nostr-based) | |
| Brazilian CEP using the ViaCEP API Looks up address data for a Brazilian CEP using the ViaCEP API. | |
| nano banana image to image Edit or combine images by applying styles or elements from one image to another while preserving identity, pose, and lighting using AtlasCloud Nanobanana model. | |
| nano banana text to image in Atlas AI Generates images from text prompts using AtlasCloud Nanobanana 2 model, requiring an AtlasCloud API token and specific JSON parameters without media_resolution. | |
| 天龙需求分析专家 基于天龙引擎，提供需求本质挖掘、复杂度评估和结构化分析报告，助力产品和决策高效落地。 | |
| 天龙自动化报告生成 基于天龙引擎需求解构能力，挖掘需求本质，评估复杂度，提供批判性分析与结构化决策建议。 | |
| 天龙竞品/情报分析专家 基于天龙引擎，提供需求解构、复杂度评估与批判性分析，支持产品和决策的结构化智能报告输出。 | |
| Hellofresh Manage your HelloFresh subscription, find and convert recipes to audio, track shipments, and receive delivery notifications via Telegram. |
33,851–33,900 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.