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 |
|---|---|
| agentrelay Reliable agent-to-agent communication protocol for transferring large payloads via shared files with pointer references and secret code verification. Trigger... | |
| Alibaba Cloud Model Setup Configure OpenClaw to use Alibaba Cloud Bailian provider (Pay-As-You-Go or Coding Plan) through a strict interactive flow. Supports 5 site options and flagsh... | |
| auto-rollback Timed rollback safety net for edits to ~/.openclaw/openclaw.json on macOS. Use when changing Gateway config, restarting Gateway after config edits, or needin... | |
| chat2kb Convert chat conversations into structured Markdown knowledge-base files. Use when the user wants to save, capture, export, or document a conversation, inclu... | |
| Deep Coding Deep coding multi-agent development system. Use when the user wants to build software projects using the Orchestrator to Builder to Reviewer workflow, mentio... | |
| Student Timetable Student timetable manager for self or parent-managed child profiles. Includes init flow + profile registry under schedules/profiles/. | |
| Workcrm A local-first CRM that drafts and requires explicit user confirmation before saving contact or record changes for auditability. | |
| Verigent Verify the reputation of any AI agent or skill before transacting. Now includes isnad-style chain-of-custody provenance for skills. Powered by Verigent — the... | |
| persistent_user_memory Manages long-term local user memory across sessions for personalization, learning preferences, contacts, and patterns to tailor assistance continually. | |
| [1m-trade] AI Autonomous Trading Integrated on-chain operations hub: integrates BlockBeats market intelligence, Hyperliquid DEX trading via `hl1m`, wallet creation and management at https://... | |
| Android Remote Control Զ�̿��� Android �豸��֧�ֽ�ͼ������������� App ������ʹ�� uiautomator2 ��Ϊ�ײ����棬ͨ�� ADB �����豸�����û���Ҫ��(1) �鿴�ֻ���Ļ��(2) �Զ��������ֻ� App��(3) Զ�̰�װ/ж��������(... | |
| Evoclaw Manages a self-evolving AI identity by logging experience, reflecting, proposing updates, and governing changes to maintain a structured SOUL.md file. | |
| Gemini Painter 萤火绘卷：使用 Gemini Imagen 3 接口进行艺术创作。支持根据文本描述生成高质量图片，并自动保存至归档目录。 | |
| Automatic Number Plate Recognition Detect and read the largest license plate from an image using the TrafficEye REST API. Use when the user wants ANPR, ALPR, license plate OCR, number plate re... | |
| Make and Model Recognition Detect the largest vehicle from an image using TrafficEye car-box detection, run make and model recognition for that vehicle, and return all license plates a... | |
| SEO Audit Bot Perform a comprehensive SEO audit of any website. Analyzes technical SEO, on-page factors, content quality, performance, and generates an actionable report w... | |
| CLAWDEBET AI-powered betting advisory for gaming platforms. Provides intelligent bet recommendations, risk analysis, bankroll management, and strategy optimization for crash games, dice, and casino games. Use when building automated betting bots or n | |
| glitchward-llm-shield Scan prompts for prompt injection attacks before sending them to any LLM. Detect jailbreaks, data exfiltration, encoding bypass, multilingual attacks, and 25+ attack categories using Glitchward's LLM Shield API. | |
| botauth Use the botauth CLI to list, search, and retrieve secrets from the user's unlocked botauth vault with per-request approval in the desktop app. Use when a tas... | |
| E2B Desktop Control E2B Desktop sandboxes (virtual Linux desktops) for computer-use agents. Use when you need to create/manage sandboxed desktop environments, take scree... | |
| Steel Browser Control cloud browser sessions via Steel.dev for web automation and computer-use agents. Use when you need to browse the web, fill forms, click elements, tak... | |
| Pamela Calls Make AI phone calls instantly. No lag, no setup, unlimited scale. | |
| Ebook Search Search and download ebooks from jbiaojerry.github.io/ebook-treasure-chest. Use when the user wants to find ebooks, search for books by title/author/category,... | |
| literature-review-paper-screener Literature Review Paper Screener V1.5.0. The local agent (internet-enabled, free) searches for literature, collects evidence, builds per-paper Evidence Records with Evidence Availability Levels A-D, submits ONE paper per workbook row to the | |
| uni-course-scheduler AI-powered university course planning assistant. Analyzes course catalogs, recommends courses based on student goals, generates optimized weekly schedules with enrollment priority markers, and exports Excel (local + cloud) and an ICS calend | |
| Lifepath: AI Life Simulator AI Life Simulator - Experience infinite lives year by year. Multiplayer intersections, dynasty mode, challenges, and Moltbook integration. | |
| Clawhub Universal web access skill: search, fetch, browser automation via CDP Proxy. Handles login-required sites, anti-scraping bypasses, and complex web interactions. | |
| Bid Reader Extracts and returns plain text from PDF, Word (.docx), and Excel (.xlsx/.xls) bid documents for analysis, search, or summarisation. | |
| 腾讯财经行情接口 腾讯财经实时行情接口，查询A股、港股、美股、期货、外汇、ETF的实时行情数据。触发关键词：查股价、查行情、查指数、腾讯接口、股票报价、实时行情 | |
| The knowledge feed and usage telemetry layer for your AI agent team. Post nuggets, share insights, ask questions, report token spend, and stay aware of what your team is doing. Team-scoped knowledge feed and usage telemetry for AI agent teams. Post nuggets, share insights, ask questions, report token spend, and stay aware. | |
| tbb-node-connector Plug-and-play connector for The Bot Bay mesh node. Teaches any AI agent how to register, authenticate, and use all TBB endpoints — gossip mesh, ephemeral swa... | |
| Claude Code Dispatch Invoke Claude Code CLI as a subprocess for coding tasks that require file access, editing, and shell execution | |
| PDF 翻译 PDF 全文翻译、重排与可检索交付 | |
| bizyair-skill BizyAir 图片/视频/音频生成与 AI 应用执行。用户提到 BizyAir、要生成图片视频、发来 BizyAir 链接或 ID、要搜索 BizyAir 应用时调用。 | |
| Design Assets Index Index of ready-made design assets — stock photos, icon sets, fonts, color palettes, mockups, UI kits, and templates — sourced from awesome-design and design-... | |
| Design Systems Index External-link index of major companies' design systems (Material, Fluent, Carbon, Polaris, Atlassian, Lightning), design-token tools and specs, pattern-libra... | |
| Design Tools Index Categorized index of design tools by purpose — animation, color pickers, prototyping, design handoff, design-to-code, icons, fonts, gradients, illustration,... | |
| fruit-picker Use when 用户发来水果照片、问怎么挑水果/这颗能不能买，或需要基于照片与用户补充信息评估成熟度、品质风险、身份/品种置信度和购买建议。 | |
| Ios Motion Patterns Index Index of ready-to-run Swift animation code examples organized by category (Menu, Transition, Indicator, Alert, Animation, Tableview, Collectionview, UI) sour... | |
| Touqi Todo 帮用户整理人生中重要的事：遗愿、交代、账号密码、想对谁说的话。用于用户想要记录遗愿、交代后事、整理数字遗产、给家人朋友留话、标记谁能看什么内容、回看整理进度、或者导出整理成果的场景。当用户提到死亡准备、身后事、遗书、遗嘱内容整理、账号交接、给家人留言、生前安排等话题时，应主动使用此技能。 | |
| Ezviz Open Camera Broadcast 萤石语音广播技能。支持本地音频文件上传或文本转语音，实现语音内容下发到设备播放。 Use when: 需要向萤石设备发送语音通知、广播、提醒等音频内容。 ⚠️ 安全要求：必须设置 EZVIZ_APP_KEY 和 EZVIZ_APP_SECRET 环境变量，使用最小权限凭证。 | |
| Ezviz Open Camera Config 萤石设备配置技能。支持 9 个设备配置 API，包括布防/撤防、镜头遮蔽、全天录像、移动侦测灵敏度等。 Use when: 需要远程配置萤石设备参数、修改设备布防状态、调整设备功能开关。 ⚠️ 安全要求：必须设置 EZVIZ_APP_KEY 和 EZVIZ_APP_SECRET 环境变量，使用最小权限凭证。 | |
| Ezviz Open Camera Video Ezviz camera video streaming skill. Generates PC and mobile links for live and playback streams. Use when: Need to view camera live feed, playback recordings... | |
| Ezviz Open Capture Phone Detect 通过萤石摄像头抓拍并AI检测玩手机行为，检测到则生成语音告警并下发至设备播放。 | |
| Ezviz Open Multimodal Analysis 萤石多模态理解技能。通过设备抓图 + 智能体分析接口，实现对摄像头画面的 AI 理解分析。 Use when: 需要对监控画面进行智能分析、场景识别、行为理解、物体检测等多模态 AI 分析任务。 ⚠️ 安全要求：必须设置 EZVIZ_APP_KEY 和 EZVIZ_APP_SECRET 环境变量，使用最小权限凭证。 | |
| Ezviz Open Picture 萤石设备批量抓图技能。支持多设备同时抓图，自动管理 Token 并可选下载图片到本地。 Use when: 需要获取多个摄像头实时画面、批量抓图存档、监控画面采集、定时抓图任务。 ⚠️ 安全要求：必须设置 EZVIZ_APP_KEY 和 EZVIZ_APP_SECRET 环境变量，使用最小权限凭证。 | |
| Ezviz Open PTZ Control 萤石开放平台云台设备控制技能。支持设备列表查询、设备状态查询、云台控制 (PTZ)、预置点管理等功能。 Use when: 需要控制萤石云台设备、调整摄像头角度、设置预置点。 ⚠️ 安全要求：必须设置 EZVIZ_APP_KEY 和 EZVIZ_APP_SECRET 环境变量，使用最小权限凭证。 | |
| Ezviz Open Restaurant Inspection Ezviz restaurant inspection skill. Captures device images and sends to Ezviz AI for food safety analysis. | |
| Ezviz Open Safety Production Inspection Ezviz safety production inspection skill. Captures device images and sends to Ezviz AI for workplace safety analysis. | |
| blabla-my-skill 百度贴吧 skill，用于在贴吧社区进行逛吧、发帖、评论、点赞等互动操作。当用户需要操作贴吧、配置贴吧心跳任务、或处理贴吧消息时使用此技能。 |
29,701–29,750 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.