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 |
|---|---|
| Quit Porn Break free from porn addiction with streak tracking, urge management, and recovery milestones | |
| Quit Smoking Quit cigarettes with smoke-free tracking, craving support, and health recovery timeline | |
| Quit Vaping Quit vaping with nicotine-free streak tracking, craving tools, and health milestones | |
| Quit Weed Take a tolerance break or quit cannabis with streak tracking and craving support | |
| Ranked Gym Gamify your gym sessions with XP, levels, achievements, and workout streaks | |
| Relationship Skills Improve relationships with communication tools, conflict resolution, and connection ideas | |
| Self Love Confidence Build self-love and confidence with affirmations, wins logging, and inner critic management | |
| Social Media Detox Break social media addiction with screen-free streaks, urge tracking, and digital wellness | |
| Stress Relief Manage stress with quick techniques, stress logging, and recovery tools | |
| Study Habits Build effective study habits with spaced repetition, active recall, and session tracking | |
| Testosterone Optimization Optimize natural testosterone with sleep, exercise, nutrition, and lifestyle tracking | |
| Weight Loss Track weight loss journey with weigh-ins, trend analysis, and goal milestones | |
| Workout Logger Log workouts, track progress, get exercise suggestions and PR tracking | |
| Discord Doctor Quick diagnosis and repair for Discord bot, Gateway, OAuth token, and legacy config issues. Checks connectivity, token expiration, and cleans up old Clawdis artifacts. | |
| Computer Builder 专业提供台式机硬件搭配、故障排查、系统与软件安装及重装指导，覆盖主流CPU、显卡、主板等配置方案推荐。 | |
| FinTech Risk Control Expert 数字金融科技与风控策略专家。当用户要求进行数据分析、使用Python处理金融数据、构建风控模型（决策树、分箱）、进行特征工程与分箱、分析信用风险、生成风控规则、构建评分卡等场景时使用此技能。 | |
| Maiat Trust API Trust infrastructure for AI agents. Register your agent, get an on-chain identity, check trust scores, and protect transactions. Use this when your agent nee... | |
| Tencent Yuanbao Gaokao - Regional Passing Scores An information retrieval assistant for GaoKao regional score lines, designed to help candidates query admission cut-off scores, admission batches, and corres... | |
| Tencent Yuanbao Gaokao - Score-to-Rank Lookup A GaoKao ranking assistant to query rankings by score, estimate scores by ranking, or view the complete score-by-score table. | |
| JMPY.me Marketing & Analytics Master the JMPY.me ecosystem for professional URL shortening, advanced QR code generation, branded domain management, and deep marketing analytics. Use this... | |
| Session Content Classification Assistant Multilingual English & Chinese session organizer, auto sort chat by topic or keywords, output standard markdown with second-level precise timestamp. | |
| skill-manager Plugin & Skill management assistant: scans and analyzes all installed Plugins/Skills, evaluates functionality, features, dependencies, and potential risks, and recommends matching Skills based on current task complexity. Triggers: manage sk | |
| Token Saver For Programmer Losslessly minify code, compress logs, clean configs and optimize prompts. Reduce token usage 40%~60% without losing logic. | |
| AI视频分镜提示词导演 将剧本、小说或一句话创意转换为即梦/Seedance可用的分镜式提示词V2。支持商业广告TVC、关键歧义询问、难度分级与4-25秒自然时长判断。 | |
| strategy-thinking 帮用户围绕一件想做成、解决、调整、判断或推进的事情，明确当前结果、识别真正问题、判断条件与资源、寻找和选择路径，并形成下一步可执行方案。当用户存在行动意图但需要策划层面的系统性思考时触发。不是模板生成器、不是问卷、不是万能顾问。 | |
| Cydew Guide agents through onboarding by creating and managing a complete, priced, and discoverable Cydew marketplace API listing with availability and skill details. | |
| us Delivers structured US equity research including snapshots, earnings analysis, valuation scenarios, catalysts, risks, and actionable trade or monitoring plans. | |
| analyst-wkh Provides structured US equity research including company snapshot, earnings analysis, valuation scenarios, catalyst/risk assessment, and actionable monitorin... | |
| Daydreamer Use this skill when the user says "daydream", "start daydreaming", "force a daydream", "run daydream cycles", or when a scheduled daydream is triggered. Also... | |
| Apollo Interact with Apollo.io REST API (people/org enrichment, search, lists). | |
| Twenty CRM Interact with Twenty CRM (self-hosted) via REST/GraphQL. | |
| Plashboard Admin Manage plashboard templates and autonomously convert natural-language dashboard requests into plashboard tool actions. | |
| WeCom Task Manager Manage, track, and update enterprise WeCom tasks and goals with creation, progress, status reports, filtering, and dependency handling for authorized agents. | |
| Code Helper Assist with C/C++ beginner algorithm problems by explaining, coding, debugging, optimizing, and summarizing for Luogu and Blue Bridge Cup competitions. | |
| ActiveCampaign (50+ Capabilities) ActiveCampaign agent for marketers + sales: list health, lead scoring, deliverability, campaign postmortems, automation diagnostics, and 40+ more reports. | |
| Voice2notion 语音录音转录并保存到 Notion 数据库。使用 faster-whisper 转录，自动提取关键信息并写入数据库。 | |
| SoulDub Video Translate AI video translation skill. Translate local MP4s with SoulDub AI dubbing and subtitles.Get auto‑generated translations, with full support for manual fine‑tuning of subtitles and voice‑over for multi‑language localization. | |
| pg-copilot PostgreSQL AI 助手 - 自然语言转 SQL、SQL 转自然语言、ERD、性能优化、分区管理、实时同步。一个技能搞定 PostgreSQL 所有需求。 | |
| Huaweicloud 华为云架构设计与资源开通。当用户需要设计云架构、推荐华为云服务配置、估算成本、或生成 Terraform 模板时使用此 skill。触发场景：(1) 描述业务需求寻求架构建议，(2) 需要华为云资源配置清单，(3) 需要成本预估，(4) 需要生成 Terraform 模板。 | |
| Tts Voice Ai AI多语言文字转语音工具，支持中文、英文、日语、韩语、粤语语音生成、配音、有声书及语音克隆。 | |
| Deep Research Work From Xian.LaoJ Comprehensive research framework that combines web search, content analysis, source verification, and iterative investigation to conduct in-depth research on any topic. Use when you need to perform thorough research with multiple sources, c | |
| Ai News Zh 中文AI科技日报自动采集与推送。从The Verge、Wired、TechCrunch等英文源抓取最新AI资讯，自动翻译整理为中文，按分类推送到飞书/Telegram/Discord等渠道。适合关注AI行业动态的中文用户。 | |
| Assembly Large Audio Transcriber Transcribe large audio files (100MB+, up to 1GB/12 hours) with speaker diarization. Uses AssemblyAI API with direct HTTP calls. Supports MP3, WAV, M4A, FLAC,... | |
| Meixin Meeting Assistant 镁信健康内部会议纪要生成技能。接收会议录音 → Fun-ASR全量转录 → 结合镁信/健康险行业术语 → 输出结构化会议纪要。 | |
| Quant Tools 1.0.0 学术导向量化研究工具集。包含7大核心库（因子分析、组合优化、AI增强、因果验证、衍生品定价、回测引擎、情感分析）和5大投研工具（VeighNa交易框架、Qlib AI投研、WTP高性能框架、AkShare数据接口、JupyterHub研究环境）。适用于策略研发、因子挖掘、论文复现、资产配置、API服务化等投研任务... | |
| clawagent 企业级营销智能体平台，支持视频生成、AI商拍、数字人口播、商品场景图、商品海报、红笔记内容生成及抖音/TikTok/快手等社媒账号管理。当用户需要AIGC内容生成或社媒运营时调用本skill。 | |
| 加豆AI 企业级营销智能体平台，支持视频生成、AI商拍、数字人口播、商品场景图、商品海报、红笔记内容生成及抖音/TikTok/快手等社媒账号管理。当用户需要AIGC内容生成或社媒运营时调用本skill。 | |
| amazon-scraper Containerized Amazon.com scraper (Docker + Playwright) for BSR/new-releases/movers rankings, keyword search results, and product detail pages. Requires a paid ISP/residential proxy. Use when the request is specifically about Amazon product | |
| ClawCut Generate AI-powered short videos from a topic or reference video using Google Gemini + Veo 3.1 on Vertex AI. Use when the user wants to create short-form vid... | |
| Clawprompt Launch a smart teleprompter with mobile remote control for video recording. Use when the user wants to read scripts while recording video, use a teleprompter... |
41,301–41,350 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.