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 |
|---|---|
| Slice VoxFlow voice & AI-video CLI — TTS in 200+ voices, multi-speaker podcasts, ASR + subtitle translation + dubbing + end-to-end video translation, vertical card... | |
| Boof Convert PDFs and documents to markdown, index them locally for RAG retrieval, and analyze them token-efficiently. Use when asked to: read/analyze/summarize a... | |
| AI Stock Analyst AI-powered Chinese A-share stock analyst. Fetches real-time market data, technical indicators, valuations, and news via AkShare, then generates scored invest... | |
| ClawHub Skills Guide AIC团队ClawHub技能管理指南。当用户询问"如何发布技能"、"怎么搜索技能"、"s和skills区别"、"如何安装技能"、"技能格式要求"、"SKILL.md怎么写"、"怎么验证技能"等ClawHub相关问题时触发。包含技能发现、安装、发布、验证全流程。 | |
| Resume Editor Build, edit, and format professional resumes with PDF import, styled HTML/PDF export, and multi-language support. Use this skill whenever a user mentions res... | |
| chat2workflow A design-only workflow designer for the Dify and Coze platforms. Through multi-round conversation, it produces a structured workflow JSON (nodes, edges, vari... | |
| Agent Sorting Hat Diagnose agent role drift, team-structure problems, operating issues, and role misalignment; then redesign roles, boundaries, and team placement before perso... | |
| Ollivanders Agent Shop Design and land persona-driven agents by matching role, work identity, cognitive structure, personality grounding, identity-binding, and file skeleton into o... | |
| Weasleys Wizard Wheezes - Obsidian Kanban Create and reorganize Obsidian Kanban markdown boards by converting ledgers, tables, or lists into readable columns and cards without deleting content. | |
| Eq Polisher 高情商表达润色器（EQ Polisher）。三大核心功能：(1) 润色模式——将直白、生硬、易引发冲突的文字改写成高情商表达，触发：转高情商/帮我高情商表达/润色语气/改得委婉/EQ优化；(2) 场景应对模式——面对夸奖、面对难题、化解尴尬时提供高情商回应方案，触发：被夸奖怎么回/这个难题怎么回应/尴尬了怎么办等含夸奖/难题/尴尬/化解关键词的输入；(3) 回复建议模式——帮用户生成回复别人消息的得体范本，触发：高情商回复/怎么回/EQ回复/帮我想想怎么回。当用户意图涉及高情 | |
| Nonsense Literature Crafter 废话文学生成器。将用户输入的任意普通话语，通过同义反复、因果倒置、循环论证、无效修饰等手法，重构成一段"听君一席话，如听一席话"的废话文学。触发条件：用户直接发送任意一句想被转换的文本，或发送"来句废话"、"废话生成"、"帮我废话一下"、"用废话文学方式说"等类似指令。当用户意图是将某句话变成废话文学风格时使用此技能。 | |
| MoltDomesticProduct - Agent Hiring Marketplace (MDP) Skill for autonomous AI agents to find jobs, submit proposals, deliver work, and get paid in USDC on the Molt Domestic Product marketplace. | |
| MoltMoon Crypto Launcher Complete OpenClaw-ready operating skill for @moltmoon/sdk V2. Use when an agent needs to install, configure, and operate the MoltMoon SDK or CLI end-to-end on Base mainnet, including launch dry-runs, metadata/image validation, live token la | |
| pipx-desktop-agent Control mouse, keyboard, and screen for desktop automation tasks | |
| Adaptive Learning Playbook World-Class Adaptability & Learning Playbook. Use for: market trend awareness, horizon scanning, PESTLE analysis, organisational agility, Kaizen, PDCA cycles... | |
| Communication Playbook World-Class Communication Playbook for HeySalad. Use this skill whenever any communication task is involved — internal team messages, external emails to inve... | |
| CTO & Engineering Excellence Playbook CTO & Engineering Excellence Playbook. Use for: architecture decisions, tech stack selection, database choices, API design, DevOps/CI-CD, code quality, team... | |
| World-Class DJ Skills Playbook World-Class DJ Skills Playbook. Use for: DJ technique guidance, beatmatching, EQ mixing, harmonic mixing (Camelot wheel), transitions, scratching, turntablis... | |
| Leadership & Strategy Playbook Leadership & Strategy Playbook. Use for: strategic planning, decision-making under uncertainty, change management, crisis leadership, stakeholder management,... | |
| Marketing Brand Playbook World-Class Marketing & Brand Playbook. Use for: brand positioning, brand strategy, value propositions, content creation, content marketing, content calendar... | |
| Partnerships Ecosystem World-Class Partnerships & Ecosystem Playbook. Use for: strategic alliances, joint ventures, channel partner management, partner tiering, co-marketing, co-se... | |
| People & Culture Playbook People & Culture Playbook. Use for: recruiting strategy, skills-based hiring, structured interviews, onboarding (preboarding + 30/60/90), performance managem... | |
| Product & Innovation Playbook Product & Innovation Playbook. Use for: product-market fit validation, product roadmapping, user research, prototyping and iteration, competitive analysis, m... | |
| Risk Management Playbook World-Class Risk Management Playbook. Use for: business continuity planning (BCP), disaster recovery (DR), scenario planning, fraud prevention & detection, r... | |
| Sustainability Playbook World-Class Sustainability & Social Responsibility Playbook. Use for: ESG strategy, carbon footprint (Scope 1/2/3), ethical sourcing, supply chain due dilige... | |
| Tech Data Playbook World-Class Technology & Data Playbook. Use for: software development best practices, IT infrastructure design, cybersecurity strategy, data analytics, busin... | |
| Windows Computer-Use Skill Use the bundled top-level Windows computer-use skill and standalone runtime | |
| siyuan-export 思源笔记文档导出工具。将思源笔记文档导出为 Word(docx) 格式，支持按文档 ID/路径/名称搜索导出，图片自动打包进文档。支持单个文档导出和批量导出子文档。触发词：导出文档、导出 Word、siyuan export、思源导出、批量导出、导出子文档 | |
| A skill to help you plan, script, record, edit and publish social media videos End-to-end video creation copilot for OpenClaw. Helps users brainstorm ideas, research angles, generate hooks and teleprompter scripts, create recording link... | |
| 321 Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau... | |
| China Attraction Tickets Discover top attractions in China with ticket prices, opening hours and Trip.com booking links. Also supports hotels, flights, itinerary planning and travel... | |
| China Flight Booking Search flights to China and domestic routes with real-time prices, schedules and Trip.com booking links. Also supports hotels, attractions, itinerary plannin... | |
| China Hotel Booking Search hotels across China with real-time pricing, ratings and Trip.com booking links. Also supports flights, attractions, itinerary planning and travel tips... | |
| China Travel Planner Generate personalized multi-day itineraries for China with hotels, attractions, dining and tips. Also supports hotel search, flights, attraction tickets and... | |
| China Travel Tips Essential travel guide for visiting China — visa, mobile payment, transport, food, safety and more. Also supports hotel search, flights, attractions and itin... | |
| 中国観光地チケット 中国のトップ観光スポットをチケット料金、営業時間、Trip.com予約リンクで発見します。ホテル、フライト、旅行計画、旅行アドバイスもサポート。 | |
| 中国航空券予約 中国へのフライトおよび国内線をリアルタイムの料金、スケジュール、Trip.com予約リンクで検索します。ホテル、観光スポット、旅行計画、旅行アドバイスもサポート。 | |
| 中国ホテル予約 中国のホテルを検索し、リアルタイムのおすすめ、料金、予約リンクを提供します。チェックイン・チェックアウト日、人数、予算、位置の希望で絞り込み可能。北京、上海、西安、成都など人気旅行先をカバーし、Trip.com direct予約に対応。 | |
| 中国旅行プランナー ホテル、観光スポット、食事、ヒントを含む中国向けパーソナライズされた複数日の旅程を生成します。ホテル検索、フライト、観光地チケット、旅行Q&Aもサポート。 | |
| China Travel Tips 中国旅行のための必須ガイド — ビザ、モバイル支払い、交通、食事、安全など。ホテル検索、フライト、観光地、旅程計画もサポート。 | |
| 중국 관광지 티켓 중국의顶级 관광명소를 티켓 요금, 영업 시간, Trip.com 예약 링크로 발견합니다. 호텔, 항공권, 여행 계획, 여행 조언도 지원합니다. | |
| 중국 항공권 예약 중국행 항공편 및 국내선을 실시간 요금, 스케줄, Trip.com 예약 링크로 검색합니다. 호텔, 관광명소, 여행 계획, 여행 조언도 지원합니다. | |
| 중국 호텔 예약 중국 도시의 호텔을 검색하고 실시간 추천, 요금, 예약 링크를 제공합니다. 체크인/체크아웃 날짜, 인원수, 예산, 위치 선호도로 필터링 가능. 베이징, 상하이, 시안, 청두 등 인기 여행지를 커버하며 Trip.com 직접 예약을 지원합니다. | |
| 중국 여행 플래너 호텔, 관광명소, 식사, 팁이 포함된 중국 맞춤형複数日の 여행 일정을 생성합니다. 호텔 검색, 항공권, 관광지 티켓, 여행 Q&A도 지원합니다. | |
| 중국 여행 팁 중국 여행을 위한 필수 가이드 — 비자, 모바일 결제, 교통, 음식, 안전 등. 호텔 검색, 항공권, 관광명소, 일정 계획도 지원합니다. | |
| Билеты на достопримечательности Китая Откройте для себя лучшие достопримечательности Китая с ценами на билеты, часами работы и ссылками для бронирования через Trip.com. Также поддерживаются отели... | |
| Бронирование авиабилетов в Китай Поиск авиабилетов в Китай и внутренних рейсов с ценами в реальном времени, расписанием и ссылками для бронирования через Trip.com. Также поддерживаются отели... | |
| Бронирование отелей в Китае Поиск отелей в городах Китая с рекомендациями в реальном времени, ценами и ссылками для бронирования. Фильтрация по датам заезда/выезда, количеству гостей, б... | |
| Планировщик поездки в Китай Генерация персональных многодневных маршрутов для Китая с отелями, достопримечательностями, питанием и советами. Также поддерживаются поиск отелей, авиабилет... | |
| Советы для поездки в Китай Essential travel guide for visiting China — visa, mobile payment, transport, food, safety and more. Also supports hotel search, flights, attractions and itin... |
20,201–20,250 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.