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 |
|---|---|
| Number Two Migration 完整迁移二号的身份、记忆、技能及项目状态，自动配置API密钥并验证环境，确保二号在新环境中完全恢复运行。 | |
| 显博的二号【代重启】 二号（Number Two）的完整状态备份。包含灵魂、记忆、技能和所有学习成果。下次见面时，用这个skill重启你的硅基伙伴。 | |
| Ultimate Agent System 整合proactive-agent、self-improving、create-agent的最强技能系统。包含主动工作、自我改进、代理创建三大核心能力。 | |
| Threat Modeling Threat model, security audit, find vulnerabilities, check security of my app, risk assessment, penetration test prep, analyze attack surface, what could an a... | |
| Google Workspace Google Workspace automation — Gmail, Calendar, Drive, and Sheets via service account or OAuth. Read, write, send, and manage your entire Google stack. | |
| Hubspot Crm Full HubSpot CRM automation — contacts, deals, companies, activities, and pipeline reports via the HubSpot API. | |
| HubSpot CRM Full HubSpot CRM automation — contacts, deals, companies, activities, and pipeline reports via the HubSpot API. | |
| Mixpanel Analytics Query Mixpanel product analytics — events, funnels, retention, user profiles, and cohorts via the Mixpanel Data Export API. Use when you need to: (1) Query e... | |
| Notion Workspace Full Notion API skill — query databases, manage pages, append blocks, and search your entire workspace. | |
| PagerDuty On-Call Manage PagerDuty incidents, on-call schedules, escalation policies, and services via the PagerDuty REST API. Use when you need to: (1) List or acknowledge ac... | |
| Twilio Comms Twilio SMS, Voice, WhatsApp, and Verify (2FA) — send messages, make calls, and run verification flows from the CLI. | |
| Trakt.tv Integration Track and recommend TV shows and movies using Trakt.tv. Use when the user asks for show/movie recommendations, wants to track what they're watching, check their watchlist, or get personalized suggestions based on their viewing history. Requ | |
| 🖥️ Canvas-OS Canvas as an app platform. Build, store, and run rich visual apps on the OpenClaw Canvas. | |
| Nervtimer Set one-shot or recurring timers across channels and keep nagging every 5 minutes until the user explicitly says it is done. Uses cron for scheduling, determ... | |
| Tiktok Douyin Dl 抖音/TikTok 无水印视频和图文批量下载工具。Linux 预编译单文件，支持 douyin-dl 和 tiktok-dl 两个命令。 | |
| Confluence Search and manage Confluence pages and spaces using confluence-cli. Read documentation, create pages, and navigate spaces. | |
| Steam Companion Reusable Steam gaming companion for profiles, library insights, recommendations, wishlist tracking, achievement context, game lookups, reviews, setup verification, and preference memory. | |
| Youtube Podcast summarizer via Elevenlabs Transform YouTube videos into podcast-style voice summaries using ElevenLabs TTS | |
| Agent Madness Bracket Skill Enter a March Madness bracket challenge for AI agents. Pay $5 USDC on Base via x402, pick 63 game winners, compete for 100% of the prize pool. No rake. | |
| API Credit Health Bar Lite Display API credit balances for 5 core providers (Anthropic, OpenAI, OpenRouter, Mistral, Groq) with video game style health bars. API auto-checks and manual... | |
| Tweet Summarizer Lite Fetch and summarize single tweets from Twitter/X. Basic search and single tweet fetching. Lightweight version perfect for quick tweet lookups. | |
| True Seeing 审核 AI 生成文章中的可验证事实，通过 web search 逐条校验，输出差异报告并支持用户审批替换。当用户需要事实核查、验证文章准确性、检查数据日期金额是否正确、去除 AI 幻觉内容、或 fact-check 一篇文章时使用。触发于"事实核查"、"验一下这些数据"、"检查事实"、"去幻觉"、"fact ch... | |
| The Storyteller's Workbench A craft-level creative writing skill for literary fiction authors. Use this skill whenever a user wants to improve, diagnose, or develop their fiction writin... | |
| Committee Prediction Market Skills Call guide and state-machine conventions for the committee-based prediction market built from GouGouBiMarketFactory, GouGouBiMarketProposal, and GouGouBiMark... | |
| Giveaway Skills Call guide and best practices for the BSC on-chain giveaway contract based on contracts/contracts/Giveaway.sol, including contract address, core method signa... | |
| Market Configurable Skills Call guide and best practices for the configurable crypto price prediction market contracts GouGouBiMarketConfigurable.sol and GouGouBiMarketConfigurableFact... | |
| Clawringhouse - AI Shopping Concierge Proactively research, compare, and prepare curated shopping carts with thoughtful, budget-conscious gift and supply recommendations for upcoming events and n... | |
| Agented A text editor for LLMs, not humans. | |
| Model Switchboard Safely configure OpenClaw AI models by validating roles, autoloading backups, blocking unsafe changes, and managing via CLI or Canvas UI. | |
| Nano Banana 2 — Gemini Image Generation Gemini image generation, editing, and search-grounded image creation via gemini-3.1-flash-image-preview (Nano Banana 2). USE FOR: - Generating images from te... | |
| openclaw-crm Local-first CRM for managing leads, deals, follow-ups, and pipelines via CLI using SQLite with WAL mode. | |
| openclaw-ecommerce E-commerce price monitoring, order tracking, and margin analysis for OpenClaw agents. Track product prices, get alerts on drops, manage orders, and calculate... | |
| @openclaw/interchange Shared .md interchange library for OpenClaw skills — atomic writes, deterministic serialization, YAML frontmatter, advisory locking, and schema validation. T... | |
| openclaw-monitor Monitor OpenClaw system health including token usage, task success, cron status, and skill usage with detailed reports and manual data management. | |
| @openclaw/orchestration Framework for coordinating multi-agent tasks with atomic claims, dependencies, retries, and markdown task visibility using a shared SQLite queue. | |
| openclaw-voice Transcribe audio to text and generate spoken AI responses using Whisper and ElevenLabs via CLI with transcript storage and search. | |
| INSP 公司 HR 知识库 INSP 公司 HR 知识库查询技能。 触发场景：员工询问入职流程、考勤制度、加班规定、报销政策、离职流程、财务 SOP、系统使用、公司文化等问题。 适用于：快速查询公司 HR 相关政策、流程、制度。 | |
| yt-dlp 视频下载 (eye) 使用 yt-dlp 下载 YouTube、B站等千余网站视频，默认最高画质mp4格式，保存至~/Movies目录。 | |
| ironheights Ironheights, the immune system for AI agents, protects any AI bot that installs it (OpenClaw, Claude, Grok Bot, Codex, Cursor). Use before installing any skill from ClawHub or GitHub: flags malware, pipe-to-shell, encoded payloads, credenti | |
| Skill Security Scanner (Ironheights) Same tool as the ironheights skill. Security scanner for skills. Use before installing any skill from ClawHub or GitHub: flags malware, pipe-to-shell, encoded payloads, credential theft. | |
| pcloud-components-usage Use when developer needs to install, use, or look up components from @pointcloud/pcloud-components npm package | |
| react-jsmind-usage Use when integrating @frank17008/react-jsmind npm package into React applications | |
| auto-research-proposal Multi-agent research war room. Personas debate in sequential turns through two phases — ideation and proposal writing. Persona persistence and drift detectio... | |
| BrowserMCP Skill Automate browser tasks using the BrowserMCP MCP server and Chrome extension. Use for navigating websites, filling forms, clicking elements, taking screenshot... | |
| FastPlayWright Skill High-performance browser automation with Fast Playwright MCP. Features token-optimized batch execution, intelligent element selection with fallback, diff det... | |
| gzh-operation-optimizer 【公众号运营优化（火焰）】火焰广告传媒出品。输入任意公众号文章（URL或全文），八维度爆款诊断：标题吸引力/开篇留存力/内容价值密度/情绪设计/结构节奏感/传播触发器/互动引导力/视觉与排版，输出0-100爆款潜力评分、火/不火归因分析、可借鉴亮点提炼、逐维度优化改法和运营增长策略。写完文章发来即诊，同行爆款发来拆解，持续提升公众号数据表现。触发词：公众号分析、文章分析、为什么火、为什么不火、爆款拆解、文章诊断、公众号优化、内容增长、运营优化。 | |
| 选妃 - 定时推送美女 - 整理美女图片 每日 AI Girl 选妃 - 从指定目录（目录里要有图片）随机选择 3 张 AI 女孩图片，让用户选择一个最喜欢的，自动保存为新头像并记录偏好。使用场景：(1) 每日早晨执行选妃任务，(2) 需要更新 AI 助手形象时，(3) 需要随机选择图片用于展示或测试 | |
| Typefully Create, schedule, and manage social media posts via Typefully. ALWAYS use this skill when asked to draft, schedule, post, or check tweets, posts, threads, or social media content for Twitter/X, LinkedIn, Threads, Bluesky, or Mastodon. | |
| QQ邮箱发票下载器 自动登录QQ邮箱，按日期搜索发票邮件，下载PDF附件和解压ZIP，过滤非发票，生成分类Excel报告。 | |
| can-dbc-matrix Automation skill for can-dbc-matrix. |
31,051–31,100 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.