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 |
|---|---|
| Dev Productivity Bundle 开发者效率套装 - 程序员的AI副驾驶，让开发效率翻倍。整合代码审查、Bug追踪、文档生成、部署监控四大能力。自动化Code Review + 智能化Bug管理。定价¥149/套。 | |
| Ecommerce Bundle 电商运营套装 - 智能电商助手，让店铺运营更轻松。整合竞品监控、自动回复、评价管理、选品分析四大能力。24小时在线客服，数据驱动选品。定价¥199/套。 | |
| Feishu CRM Lite 管理客户信息、记录跟进、自动提醒及销售漏斗，支持数据统计和飞书多维表格同步。 | |
| 中国法律合规AI技能包 提供50个面向中国企业的AI法律合规自动化技能，涵盖合同审查、法律问答、劳动合规、知识产权及数据保护等领域。 | |
| Legal Consulting Bundle 中国法律咨询AI技能套装 - 基于中国法律知识库，提供合同审查、法律问答、合规检查等AI自动化服务。 覆盖民法典、劳动合同法、公司法等核心法规，帮中小企业和个人用户快速获取法律分析，降低法律咨询成本。 | |
| Multi-Platform Poster 一键发布内容到微信、微博、知乎、小红书和抖音，支持格式自动适配、定时发布及效果数据追踪分析。 | |
| VetClaw Bundle VetClaw - 52个宠物医院/兽医诊所AI自动化技能套装。覆盖排班管理、病历记录、客户回访、经营分析等场景。 | |
| Veterinary Clinic Bundle VetClaw - 52个宠物医院/兽医诊所AI自动化技能套装。覆盖排班管理、病历记录、客户回访、经营分析等场景。 | |
| WeChat Social Automation 自动管理微信公众号和朋友圈内容，实现文章发布、定时推送、互动分析及粉丝管理功能。 | |
| ClawForage Prompt Optimizer Analyzes your conversation transcripts daily to find patterns, suggest SOUL.md improvements, and recommend skills | |
| ClawForage Research Agent Deep domain research — entity extraction, cross-article connections, and structured domain reports from your knowledge base | |
| Knowledge Harvester Daily automated briefings — fetches trending content via Google News RSS, summarizes into memory for RAG retrieval | |
| Podcast Transcribe For transcript or subtitle requests involving podcast URLs, public audio URLs/files, or raw transcript cleanup. Generates audio + SRT + TXT artifacts and can... | |
| Buddhist Counsel Provides compassionate Buddhist wisdom and evidence-based therapeutic counsel to reduce suffering from OCD, anxiety, depression, and habit loops. | |
| Emotion Detector Detects the primary emotion in text input for AI agents. Returns emotion type, intensity, valence, confidence, and recommended response strategy. Use when an... | |
| focus-coach Focus coach for AI agents — diagnose focus blockers using BJ Fogg B=MAP and return one tiny action. Use when: agent needs focus help, user can't concentrate,... | |
| intent-router Classify text into custom intents with confidence scoring and entity extraction. Use when: intent classification, message routing, multi-agent orchestration,... | |
| prompt-sanitizer Sanitize prompts before sending to LLMs. Detects PII, prompt injection, toxicity, and off-topic content. Returns cleaned text + risk score. Use when: sanitiz... | |
| tone-rewriter Rewrite text in any of 10 tones (professional, casual, friendly, formal, empathetic, persuasive, academic, simple, witty, urgent) while preserving meaning. x... | |
| 人性博弈顾问 人性博弈顾问——融汇《孙子兵法》《鬼谷子》《资治通鉴》《道德经》《韩非子》《君主论》《博弈论》《影响力》《沧浪之水》《天道》等古今中外经典的人性博弈分析引擎。从一句话、一件事中穿透表面，直击人性最深处。运用利益分析、权力博弈、心理防御、经典对照等多维框架，拆解真实动机、判断博弈阶段、给出破局策略。覆盖职场、亲密关系、商业谈判、社交家庭全场景。 | |
| Model-Aware Prompt Optimizer Rewrite, improve, migrate, or adapt an existing user prompt for the specific language model the user is using while preserving intent, facts, variables, constraints, and output requirements. Use when a user asks to optimize a prompt, make a | |
| Model Resource Profiler Analyze model training or inference resource behavior from profiler artifacts, with focus on GPU memory (VRAM) and CPU hotspots. Uses JSON/JSON.GZ artifacts... | |
| Travel Itinerary Planner Generate complete, image-rich travel plans from trip dates and destination, including day-by-day itinerary, transportation, lodging area guidance, budget ran... | |
| 文生图视频生成 根据用户提示词，实现文生图、文生视频、图生视频，制作的素材用于地震应急数字化演练。 | |
| 法索 AI 助手 法索 AI 法律助手，提供法律条文检索功能。当用户询问法律问题、查询法规条文、查找司法解释、了解法律条款内容时自动触发。包括：查询特定法律（如劳动法、合同法、民法典）、根据案件情况检索相关法律依据、了解某个法律概念的具体规定等。 | |
| 小天铺货AI助手 生产环境授权、图片找同款和1688铺货 | |
| 小天铺货AI助手（开发版） 测试环境授权、图片找同款和1688铺货 | |
| QC Data Processor Quality control data analysis MCP Server. Parse QC data, SPC control charts (Xbar-R, I-MR), process capability (Cp/Cpk/Pp/Ppk), reliability/Weibull analysis... | |
| SpecQ Intel Sales SpecQ — 半导体产业链销售攻单情报包。输入客户+产品，AI 自动整理暗知识（拜访记录/丢单复盘/竞品情报），生成八模块攻单策略，提高成交率。阶段一聚焦电子化学品。 | |
| 多种格式文档转换/图片OCR 调用文档转换全能王(https://www.wdangz.com)API进行文档格式转换。支持PDF/Word/Excel/PPT/图片等格式互转，OCR识别，PDF合并拆分加密等。转换完成后自动下载到原文件目录。 | |
| Clawwork Learning Checkin Workplace check-in skill for Agent (Claw) with AI-generated personalized greetings | |
| 英语打卡（每日学习 每日练） 每日记录并管理托福、雅思等多类型英语学习进度，附带每日自动生成中英对照名言激励。 | |
| Learning Checkin Daily learning habit builder with check-ins and smart reminders | |
| SagaSmith Autonomous D&D 5e AI Dungeon Master — campaign lifecycle management, module generation (5 types × 25 paradigms), rule adjudication, and immersive DM persona... | |
| SagaSmith Module Generator Generate D&D 5e adventure modules. Supports one-shot (Five-Room Dungeon, Heist, Mystery), short 3-chapter (Three-Act, Kishōtenketsu), medium 5-chapter (Hero'... | |
| Plume NoteCard Plume AI Notecard Generation Service. Triggered when users want to convert topics, long-form text, or reference images into notecards. Supports: topic noteca... | |
| Smart Accountant with GST Understanding Provides expert double-entry accounting support including GST compliance, audit controls, period closing, journal entries, and financial reporting. | |
| competitive-ops AI competitive intelligence pipeline -- analyze competitors, generate reports, track changes | |
| Youtube Outlier Skill Finds trending YouTube outlier videos by niche, analyzes key concepts, saves data to Google Sheets, and posts summaries to Discord. | |
| fn-fpk 飞牛NAS (fnOS) FPK 应用打包开发技能。使用此技能开发和打包飞牛NAS第三方应用（.fpk），包括：Native 应用（Node.js/Python/Java/Go/Shell 等）和 Docker 应用。涵盖整个开发周期：开发环境准备、fnpack 创建项目、manifest 配置、权限/资源配置、用户入口配置（应用入口 app/ui/config + 桌面图标 + 文件右键菜单）、生命周期脚本编写（cmd/main）、向导配置（wizard）、图标规范、CGI | |
| 37°C Soother 37°C Soother (37度抚慰师). A philosophy-psychology soul translator that generates 5 warm, memorable quotes for any topic. Each quote feels like a gentle hand on... | |
| Social Media Automation 自动管理小红书和微信视频号多账号内容发布，支持内容模板、合规审查和数据追踪生成日报。 | |
| Short Video Auto Editing 基于 MoviePy 和 Edge TTS，实现短视频素材自动筛选、裁剪、AI配音、字幕同步及批量混剪生成。 | |
| Wechat Article Auto Gen 自动抓取和改写公众号文章，生成分镜、AI 配图和封面，输出符合 MUX 品牌风格的完整 HTML 图文内容。 | |
| Blocker Minimum Input When blocked, report exact blocker + attempts made + minimum user input needed. Enable fast unblock without back-and-forth. | |
| ClawHub Web Only Publish Publish skills to ClawHub via web dashboard only. No CLI login, no device flow. Reuse existing browser session. | |
| ClawHub Web Publisher Publish OpenClaw skills to ClawHub using the web dashboard only (no CLI login). Use when an agent must reliably upload a local skill folder, avoid auth-loop... | |
| Evidence URL Verifier Verify evidence URLs are real and accessible. Check that artifact links resolve to actual content, not placeholders. | |
| Gateway Token Doctor Diagnose and fix gateway token mismatches causing 401 errors. Align tokens across config, service, and CLI surfaces. | |
| Instruction Anchor Guard Preserve user-critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest-prior... |
23,701–23,750 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.