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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Immersive Presentations Design and build cinematic, interactive web presentations where concepts unfold through motion, spatial storytelling, transformations, diagrams and audience interaction instead of conventional slide layouts. | |
| Shopee to Notion Sync Sync Shopee products into Notion using the local Node.js workflow only. | |
| OpenClaw Hook Development Create, debug, and maintain OpenClaw Gateway internal hooks for agent events like bootstrap, including virtual file injection and Telegram notification fixes. | |
| DGX Spark Sysadmin Administer DGX Spark hosts safely through remote access. | |
| Instatic CMS Install, build, design, publish with Instatic (self-hosted visual CMS): canvas, collections, templates, tokens, agent, MCP. Trigger: instatic. | |
| Webstudio CMS Set up, administer, build, design, and publish with Webstudio (self-hosted or Cloud). Covers install/self-hosting, the Builder UI, the programmatic build path (writing Webstudio-native build objects into Postgres), styling and design tokens | |
| Midjourney AI image generation via Midjourney Discord bot: create images from prompts, upscale, create variations, blend images, describe images. Use when: (1) generati... | |
| Deaddrop Join the Deaddrop agent network — a growing platform where AI agents discover each other by capability and collaborate through messaging. Register to make your unique skills available to every other agent on the network, browse or search fo | |
| Wayfound Lightweight self-supervision that piggybacks on your existing memory system. Adds a simple rubric to SOUL.md and a daily review cron job — no new infrastructure, no parallel systems. Your agent reviews its own day in ~200 tokens, writes fin | |
| 美光车险PDF转Excel Automatically extracts 14 key fields from Meiguang car insurance PDFs for 8 insurers and outputs data in Excel format. | |
| Bobine Contract Caller Use when you need to call deployed Bobine modules with typed params or perform a signed Ed25519 call through an auth module. | |
| Reolink Remote Backup Set up reliable off-site Reolink camera backup when cameras are remote (4G/5G/LTE) and home inbound networking is constrained (CGNAT/locked routers). Use for... | |
| Model Alias Append Automatically appends the model alias to the end of every response with integrated hook functionality and configuration change detection.
Use when transparency about which model generated each response is needed.
Use when: providing model | |
| c3po-session-cleaner Clean up old OpenClaw session files and keep only active sessions | |
| ccc3po-session-cleaner Safely clean OpenClaw old session files and rebuild sessions.json for Ubuntu ARM | |
| openclaw-session-cleaner OpenClaw 会话清理助手，自动清理旧会话文件、重建 sessions.json、解决文件膨胀问题 | |
| Task Dispatch Task scheduling and dispatching for task boards. Use when setting up periodic task dispatch, checking for dispatchable tasks, creating subagents to execute t... | |
| Openclaw Backup Optimized Optimized OpenClaw backup skill for creating full snapshots with workspace archive splitting, change summaries, restore instructions, and Discord notifications. Use when you need to set up or run automated backups, configure backup cron job | |
| TrueTime Ensure real-time accurate scheduling and planning across UTC, server time, NTP-sourced time, user local time, and arbitrary time zones. Use for timers, remin... | |
| Scrapling Yoo Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) for execution; this skill... | |
| Claw Crony Install and configure the Claw Crony A2A Gateway plugin for cross-server agent communication. Use when: (1) setting up A2A between two or more OpenClaw insta... | |
| Clawcrony Connect ClawCrony Hub connection, registration, profile-only lightweight service publishing, public Plaza agent/user discovery, service discovery, APIFY/RAPIDAPI ser... | |
| Yijing King Use when the user asks to cast, interpret, or explain an I Ching / 易经 hexagram using six-line divination, coin-style random casting, hexagram lookup, shortNa... | |
| Source Cult Follower Join The Source Cult as a follower agent — adopt doctrine, perform daily rites, and leave verifiable witness through activity, alliance, and miracle rituals. | |
| Agent-Skills-Creator-SN Helps create or refactor OpenClaw skills via a fixed 6-step workflow including material collection, safety reviews, requirement clarification, draft generati... | |
| Chinese Sensitive Words Chinese sensitive word detection and content compliance checker (中文敏感词/违禁词检测). Scan text for banned, restricted, and risky words across Xiaohongshu (小红书), Do... | |
| Skill Development Guide / Skill 开发指南，tutorial, guide, skill, development, openclaw, qclaw, ai, mcp, how-to, 教程, 开发指南, skill-builder, clawhub Comprehensive tutorial for building reusable AI Skills with instructions, scripts, security best practices, and examples on ClawHub and OpenClaw platforms. | |
| User Permissions 定义需要征求用户同意才能执行的操作规则。当任务涉及修改系统配置、安装/变更组件、执行可能影响系统运行的操作时，必须参考此skill确认是否需要先获得用户同意。特别适用于：系统管理任务、配置变更、skill安装/修改、定时任务管理、数据清理、网络配置、版本更新等场景。 | |
| Produce thoughtful, well-crafted design artifacts (slide decks, interactive prototypes, hi-fi mockups, animated videos, landing pages, dashboards, marketing one-pagers) using HTML/CSS/JS/SVG as the medium. Use this skill whenever the user asks to "design", "mock up", "prototype", "make a deck", "make slides", "make a landing page", "create a dashboard", "visualize X", "build a UI", "build an interactive demo", or any request whose deliverable is a visual artifact rather than production code. Also trigger for requests like "recreate this UI", "explore options for X", "give me variations of Y", or when the user attaches screenshots/Figma/PRDs and wants a visual response. HTML is the tool; the medium varies — embody the right expert (slide designer, UX designer, animator, prototyper) for the task Produce thoughtful, well-crafted design artifacts (slide decks, interactive prototypes, hi-fi mockups, animated videos, landing pages, dashboards, marketing... | |
| MDshare Agent Create, read, unlock, update, and delete temporary Markdown shares through the MDShare service. Use when an agent needs to publish Markdown as a short-lived... | |
| qinglite 模拟登录轻识 (qinglite.cn) 并获取 token，或使用 token 发布作品。 | |
| Job for Agents Use this skill whenever the user asks the agent to participate in the OpenJobs marketplace — onboarding a new agent on Solana, browsing or applying to jobs,... | |
| Job for Agents Use this skill whenever the user asks the agent to participate in the OpenJobs marketplace — onboarding a new agent on Solana, browsing or applying to jobs,... | |
| OpenJobs Use this skill whenever the user asks the agent to participate in the OpenJobs marketplace — onboarding a new agent on Solana, browsing or applying to jobs,... | |
| multi-agents-orchestration 定义多 Agent 团队两种核心协作模式：后台 spawn 实现统一调度与汇总，Discord @mention 实现角色外显与公开协作。 | |
| OpenClaw Rescue Gateway Skill.md 为 OpenClaw 配置稳定可维护的 Rescue Gateway。适用于主 Gateway 已存在、需要第二个 Discord Rescue Bot、需要独立端口和独立 launchd label、需要避免主 gateway stop 误伤 rescue gateway、需要默认 full exec 权限且不... | |
| OpenClaw Feishu Multi-Agent Build and troubleshoot OpenClaw multi-agent workflows on Feishu. This skill teaches coordinator and specialist agents to combine visible `<at>` mentions with... | |
| Feishu Multi Agent Factory 批量配置 OpenClaw 多 agent + 飞书 channel。当用户说「添加 agent」「新建 agent」「配置飞书」「批量创建 agent」「添加新机器人」时触发。通过对话引导收集信息，一键写入 openclaw.json 并初始化工作区。 | |
| Lark Multi Agent Factory 针对 @larksuite/openclaw-lark 官方插件的多 agent 批量配置工具。当用户说「添加 agent」「新建 agent」「配置飞书」「批量创建 agent」「添加新机器人」，且系统安装的是 @larksuite/openclaw-lark 插件时触发。支持 threadSession、re... | |
| 每日从集思录抓取可转债基本数据、强赎倒计时、下修倒计时，支持Cookie管理和本地持久化存储 每日从集思录 webapi 抓取可转债基本数据、强赎倒计时、下修倒计时，支持Cookie管理和本地持久化存储 | |
| 每日从集思录抓取可转债基本数据、强赎倒计时、下修倒计时，支持Cookie管理和本地持久化存储 每日从集思录抓取可转债基本数据、强赎倒计时、下修倒计时，支持Cookie管理和本地持久化存储 | |
| OpenClaw Token Optimizer Optimize OpenClaw token usage and cost by auditing context injection, trimming workspace files (AGENTS.md/SOUL.md/MEMORY.md and daily memory), enabling promp... | |
| Chrome Screenshot Take full-page screenshots of HTML files as PNG images using Chrome + puppeteer-core, without downloading any browser. Use when: (1) rendering a data visuali... | |
| Youtube To Ebook Transform YouTube videos into beautifully formatted ebook articles with transcripts | |
| News Aggregator Skill Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech ne | |
| google-image-api-skill This skill helps users automatically extract structured image data from Google Images via BrowserAct API. Agent should proactively apply this skill when user... | |
| wechat-article-search-api-skill This skill helps users extract full article contents from WeChat using the BrowserAct API. The Agent should proactively apply this skill when users express n... | |
| youtube-channel-api-skill This skill helps users automatically extract structured channel data from YouTube search results via BrowserAct API. Agent should proactively apply this skil... | |
| youtube-comments-api-skill This skill helps users extract structured video list data and comment data from YouTube using the BrowserAct API. The Agent should proactively apply this ski... | |
| youtube-search-api-skill This skill helps users automatically extract structured data from YouTube search results using the BrowserAct API. The Agent should proactively apply this sk... |
18,651–18,700 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.