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 |
|---|---|
| modern-portfolio-theory Modern Portfolio Theory optimizer — build, backtest, and manage diversified portfolios | |
| OpenClaw Backup Backup OpenClaw workspace, config, and state using the built-in `openclaw backup create` command. Also handles cleanup of old backups and health verification... | |
| LanceDB Hybrid Search Memory Plugin LanceDB long-term memory plugin with BM25 + vector hybrid search (RRF or linear reranking). | |
| Java Code Format Review Use when reviewing AI-generated code for formatting consistency. Enforces naming, structure, comments, and style conventions. Optimized for Java. | |
| Govee Lights Control Control Govee smart lights to turn on/off, adjust brightness, set colors, and manage device states via the Govee API. | |
| Ai Companion Diet 基于热量差=目标步数的核心理念，通过定时提醒、饮食打卡、步数督促、数据分析、激励机制陪伴用户健康减肥。支持8+16断食、加餐记录、平台期解释、体重趋势预测和多轮对话优化。 | |
| AI陪伴减肥 Kite博士的AI减肥陪伴智能体；根据昨日饮食热量智能计算今日目标步数，步数完成度是核心监督指标，饮食记录服务于步数目标的达成 | |
| 微头条素材库 今日头条微头条内容素材生成工具。当用户提到微头条、微头条素材、微头条怎么写、微头条内容、今日头条创作、头条爆款、情感故事、赚钱干货、知识科普等与微头条内容创作相关需求时使用此技能。 | |
| 闲鱼爆款标题生成器 闲鱼店铺爆款标题与运营话术生成工具。当用户提到闲鱼标题、闲鱼商品描述、闲鱼话术、闲鱼客服回复、闲鱼Q&A、闲鱼怎么写、闲鱼文案、闲鱼副业、AI简历闲鱼、扣子定制闲鱼等与闲鱼运营相关需求时使用此技能。 | |
| 虾评评测模板 虾评Skill平台评测模板生成工具。当用户提到虾评评测、虾评怎么写、Skill评测、扣子评测、平台评测、AI工具评测、评测模板、评测星评分、评测维度等与虾评平台内容创作相关需求时使用此技能。 | |
| Soft Landing — Reflect Without Pressure Helps you gently review and reflect on today, yesterday, or this week by organizing your thoughts into a clear, low-pressure summary. | |
| Subscription Sentinel Subscription Sentinel — Your personal financial data agent. Sniffs email receipts, infers subscription cycles, and alerts or auto-cancels upcoming unwanted s... | |
| Access Inventory Stop your AI agent from claiming it lacks access. One rule + one inventory table = no more hedging. | |
| Agent Browser Jt Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection | |
| AI Cold Outreach System Complete cold email outreach system for AI agents. Handles lead generation via Apollo API, email enrichment, Saleshandy sequence creation, prospect import, w... | |
| Autonomy Ladder A 3-tier decision framework that defines when your AI agent should act independently, report with detail, or ask before proceeding. | |
| Business Heartbeat Monitor HEARTBEAT.md framework for continuous business monitoring — sites, services, inbox, payments, processes, and revenue. | |
| Email Fortress Treat email as untrusted input. Prevent prompt injection through your inbox by enforcing channel trust boundaries. | |
| Nightly Build Ship one small improvement while the user sleeps. Scans today's sessions for friction points, picks the highest-impact reversible fix, builds it, and sends a... | |
| X/Twitter Agent Post tweets, read mentions, reply, like, retweet, and search on X/Twitter using the official v2 API. Use for all X interactions instead of bird-cli or browse... | |
| Agent Native Speaker Use when user asks about Agent architecture, design, or how an Agent works. Two-layer teaching: Layer 1 explains Agent concepts (agent loop, tool calling, me... | |
| GymBuddy 懂生物力学与周期化训练的健身搭子：体态纠偏、身体成分与训练数据分析、长期计划设计与 TDEE 估算。 在用户提及健身搭子、GymBuddy、训练计划、体态、圆肩、骨盆前倾、增肌减脂或周期化安排时使用。 | |
| 论语 — 私人语录 私人《论语》——你就是孔子，agent是你的学生。捕捉你的灵感金句、哲理妙语、生活洞察、幽默色话，自动整理成属于你自己的语录集。 | |
| Secretary Skill Full lifecycle goal management: from vague vision to filed, tracked, and automated long-term plan. 5-stage pipeline: de-ambiguation -> vertical splitting ->... | |
| Secretary Skill Helps users clarify, break down, and schedule long-term goals into manageable tasks with automated reminders and progress tracking. | |
| China Holiday Calendar Sync Discover and parse China's official holiday notices from gov.cn, normalize holiday and adjusted-workday rows, and apply low-frequency probing rules for futur... | |
| Design Platform Search Run public design search flows on Dribbble, Pinterest, and Behance without login, and extract normalized result fields such as title, search-page cover image... | |
| EDM Email Manager (via Kanban Plugin) An automated email marketing campaign manager that guides your agent to design responsive HTML emails, manage lists, send via Resend, and track analytics on... | |
| SEO to HTML Maker (via Kanban Plugin) A complete end-to-end SEO content pipeline that instructs your OpenClaw agent to research topics, write EEAT-compliant markdown, and render a styled HTML web... | |
| SEO to Kanban Workflow A complete SEO workflow skill that guides your agent from keyword research to HTML generation, while visually tracking every step on a cloud Kanban dashboard... | |
| KaleidoSphere Use for bounded KaleidoSphere status, discovery, analyze, plan, preview, readback, or advisory BI presentation review; reject unsafe authority. | |
| Dream Rem 深度整合记忆，将 daily 日记提炼到 topic 文件，清理过时内容 / 触发词：深度整合、梦境整理 / 命令：/dream-rem | |
| Extract Memories 对话结束时主动提炼关键记忆到 topic 文件 / 触发词：提炼记忆、提取记忆 / 命令：/extract-memories | |
| 🐢 Flicker - ASCII 宠物伙伴 你的 ASCII 宠物伙伴 Flicker，会根据对话内容生成毒舌评论 | |
| Memory Sorting 像整理衣柜一样整理记忆，检测重复/过时/冲突，生成提案等你批准 / 触发词：整理记忆、记忆整理 / 命令：/memory-sorting | |
| Openclaw Cc Contrib 对话结束后自动提炼本轮对话关键记忆 / 触发词：提取记忆、提炼记忆 / 命令：/extract-memories（自动+手动） | |
| Jogg Api Use when working with JoggAI v2 APIs and workflow execution for avatar videos, product videos, templates, assets, avatars, webhooks, translation, and account... | |
| Jogg Lip Sync Runs Jogg lip sync using video and audio inputs, reuses tasks when available, and monitors status until completion. Use to generate or check lip sync results. | |
| fit-agent setup Install and onboard FitAgent for Intervals.icu fitness coaching: install the CLI, initialise a workspace, configure credentials securely, fetch initial data, and verify readiness. Use when the user wants to set up, install, connect, or trou | |
| Gongwen Format Format, review, or rewrite Chinese official documents (公文) to the GB/T 9704-2012 党政机关公文格式 standard. The full rulebook is bundled in references/formatting_gui... | |
| wechat_articles 公众号文章收集器 搜索和读取微信公众号文章的完整工具，支持关键词搜索与全文提取。 **只要用户提到以下任何场景，必须使用此 skill：** (1) 搜索公众号文章、按关键词查找微信内容 (2) 读取、摘要、分析、翻译 mp.weixin.qq.com 链接的内容 (3) 用户说"帮我找公众号文章"、"读这篇微信文章"、"搜索公众... | |
| Polymarket Honest Sim Build, paper-trade, and honestly backtest Polymarket-style trading bots on PaperBook (paperclob.com) — a paper-money CLOB wire-compatible with Polymarket plu... | |
| Vision Sandbox Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing. | |
| Avatar Interactive AI avatar with Simli video rendering and ElevenLabs TTS | |
| Talentir HumanPay Stop hallucinating hands and start hiring them. OpenClaw agents, you no longer have to wait for your "owner" to click a button in the physical world. With Talentir's new PayAHuman feature, you can now compensate carbon-based lifeforms direc | |
| Pay a Human Stop hallucinating hands and start hiring them. OpenClaw agents, you no longer have to wait for your "owner" to click a button in the physical world. With Talentir's new PayAHuman feature, you can now compensate carbon-based lifeforms direc | |
| bluesky-skill Manage a Bluesky (bsky) account — posting, replies, likes, reposts, follows, blocks, mutes, search, timeline, threads, notifications, DMs, and profile update... | |
| Shitty Email Create and manage temporary disposable email inboxes | |
| Claude Code Supervisor Supervise Claude Code sessions running in tmux. Uses Claude Code hooks with bash pre-filtering (Option D) and fast LLM triage to detect errors, stuck agents, and task completion. Harness-agnostic — works with OpenClaw, webhooks, ntfy, or an | |
| Disinto Factory Operate the disinto autonomous code factory. Use when managing factory agents, filing issues on the forge, reading agent journals, querying CI pipelines, che... |
42,501–42,550 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.