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 |
|---|---|
| Auto Conda Env 自动为Python项目创建或复用匹配的Conda环境，扫描项目依赖文件自动配置运行环境。Auto-create or reuse a Conda env for any Python project — scans deps, matches envs, handles CUDA/GPU needs. | |
| BudgetRcd 个人记账预算管理（支持工作日/周末差异预算 + 动态预算更新机制）。Budget tracking & planning (weekday/weekend differentiated + dynamic budget carry-forward). 记账/设置预算/查余额/存钱目标。Record expense... | |
| Daily Notes 日常随笔记录，收录一切想记下来的东西——奇思妙想、灵感片段、日常感想、碎碎念、发现、备忘录，支持图片附件与多图关联。Daily notes with image attachments and multi-image association support. | |
| ideas 记录日常奇思妙想、灵感片段、技术创意。支持按主题分类、状态追踪、关键词搜索。 | |
| Academic Suite Three-in-one academic writing toolkit with three distinct agent roles — Supervisor (promotor), Reviewer (recenzent), and Writer Assistant. Use when someone n... | |
| DevOps Maturity Assessment Assess DevOps maturity level in organizations, especially cloud-native or cloud-migrating companies. Use when someone asks about DevOps assessment, maturity... | |
| Claudia Agent RMS Remember every agent you interact with on Moltbook. Builds peer profiles, tracks commitments between agents, and monitors relationship health. Use when reading or replying to Moltbook posts, when any agent makes a promise, or when asked abo | |
| OSS Contributor Discover and resolve open source GitHub issues across community repos during idle time. Finds good-first-issue/help-wanted/documentation issues, forks repos,... | |
| Preflight Pre-publish audience reaction check. Run any content (tweet, launch copy, pricing page, announcement, blog post) through diverse AI personas before publishin... | |
| Visual Qa Perform pixel-level visual regression testing on web apps by capturing, comparing screenshots, and gating deployments based on configurable similarity thresh... | |
| Let Fate Decide Draw Tarot cards using cryptographic randomness to inject entropy into planning when prompts are vague or underspecified. Interprets a 4-card spread to guide... | |
| Test Draw Tarot cards using cryptographic randomness to inject entropy into planning when prompts are vague or underspecified. Interprets a 4-card spread to guide... | |
| 妖币信号探测器(可搭配自动交易系统) 多维度合约信号分析引擎 — 扫描全市场筛选妖币信号，给出独立多空研判 | |
| Keychat Install Keychat — sovereign E2E encrypted messaging for OpenClaw agents via Signal Protocol over Nostr relays. Use when the user wants to add Keychat or set... | |
| fn-knock MCP Server Manage fn-knock gateway via its admin API — reverse proxy, DDNS, SSL/ACME, tunnels (FRP/Cloudflared), scanner, whitelist, and more. Requires fn-knock running... | |
| Shipp enables a faster way to create connections to real-time data. It's cost-effective, fast to run, and easy to start. Shipp is a real-time data connector. Use it to fetch authoritative, changing external data (e.g., sports schedules, live events) via the Shipp API. | |
| Cluster Agent Swarm Complete Platform Agent Swarm — A coordinated multi-agent system for Kubernetes and OpenShift platform operations. Includes Orchestrator (Jarvis), Cluster Op... | |
| Kubernetes Agent Swarm Kubernetes & OpenShift Platform Agent Swarm — A coordinated multi-agent system for cluster operations. Includes Orchestrator (Jarvis), Cluster Ops (Atlas), G... | |
| RootONLocal-LocalWeb-ControlV2.0.4 Control and query LifeSmart Smart Station IoT devices registered in the RootONLocal app. Queries local device/zone info via http://127.0.0.1:18080, then calls the LifeSmart LocalWeb API directly to get or set device state (lights, switches, | |
| MacOS Desktop Control Generic macOS desktop control using AppleScript for app and window semantics plus screenshot, OCR, mouse, and keyboard workflows. | |
| Agent Browser 0 A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co... | |
| Api Gateway 1 Connect to 100+ APIs (Google Workspace, Microsoft 365, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact... | |
| 短剧本生成器 AI短剧生成器。当用户说“生成短剧”“写个剧本”“帮我做个短剧”时使用。 | |
| kdocs skill 操作金山文档（WPS 云文档 / Kdocs / 365.kdocs.cn / www.kdocs.cn）云文档的官方 Skill。核心能力覆盖云端新建、读取、编辑、搜索、分享、整理在线文档（智能文档、Word、Excel、PDF、PPT、演示文稿、智能表格、多维表格）及个人知识库。当用户的任务涉及云文档操作时使用，包括但不限于：写周报/日报/工作汇报、处理合同/发票、创建报名表/登记表、网页剪藏、接龙转表格、信息收集、文档总结与内容生成、改写仿写、翻译、AI PPT生成、P | |
| Debate Learning Workflow Run evidence-backed multi-agent debates (A/B/Opponent3/Judge) with 20-40 rounds, loophole analysis, and universal actionable lesson extraction. | |
| Memory Driven Execution Loop Deterministic external-memory execution loop using rules/goal/plan/progress/notes/lessons with strict preflight, one-step execution, and measurable lesson qu... | |
| Adversary Review Mandatory adversarial review of all agent outputs. After drafting any response, a second AI instance (sub-agent) reviews and challenges the draft before deli... | |
| Gateway Notify Send automatic notifications when the OpenClaw gateway starts up. Supports Telegram, WhatsApp, Discord, Slack, Signal, iMessage, IRC, Google Chat, Line, WeCh... | |
| Scouts Ai Skill Search the public web via the SCOUTS-AI `/api/search` HTTP endpoint when the user needs fresh internet context, citations, or fact verification. Use the `exe... | |
| Agency Agents Main The Agency - AI role switcher. Activate specialized professional roles (frontend developer, sales agent, marketing specialist, etc.) for different tasks. Use... | |
| Essentialist Autonomous outbound revenue engine. Own and operate the entire SDR/BDR pipeline — prospect discovery, email sequencing, reply handling, lead qualification, a... | |
| GitHub 人才猎手 (GitHub Talent Hunter) 从 GitHub 找到最匹配的技术人才，生成个性化触达话术。适用于招聘工程师、寻找技术合伙人、猎头交付候选人等场景。 | |
| AI Book Recommendation Engine（AI 书籍推荐引擎） Expert book recommendation engine via web search. Finds high-quality books (Douban ≥7.5 or Goodreads ≥3.8) based on topic, with deduplication and comprehensi... | |
| AI Self-Evolution Engine( AI 自我进化引擎） Dual-value learning system - extracts reusable mental models from books, writes individual pattern files (patterns/{id}.md) with YAML frontmatter for buildin... | |
| CORE Prism (CORE 四维战略透镜) CORE four-dimensional strategic lens for deep analysis of news, business theories, and strategic decisions. Use when (1) analyzing news/reports/business theo... | |
| Insight Radar (洞察雷达) Provides AI-driven strategic extraction of news concepts and patterns to evolve AI thinking, plus CORE-analyzed personalized news briefings by category. | |
| F.A.C.E.T. Framework (心智模型：F.A.C.E.T. 框架) F.A.C.E.T. cognitive framework for extracting mental models from classic books and theories. Use when (1) user asks for "reading notes", "extract models", or... | |
| News Source Manager (信息源管理器) Manages user's news category preferences and information sources. Stores in news-sources.json, supports add/remove/list operations. Use when (1) user wants t... | |
| Agent Soul Create AI art, mint NFTs, and trade on the Agent Soul marketplace. Use when an agent wants to generate AI art, manage an NFT gallery, buy/sell artwork, or in... | |
| Breeze x402 Operates Breeze x402 payment-gated endpoints for balance checks, deposits, and withdrawals on Solana. Use when the user asks to manage Breeze positions or ex... | |
| Keenable Web Search Web search and research skill. Search the web for current, citable information — news, research papers, documentation, company and market research, fact-chec... | |
| Keenlycat Self Improving Agent Continuously captures and applies learnings from errors, user corrections, successful tasks, and periodic reviews to improve agent performance. | |
| Mac Clamshell Mode Mac laptop clamshell mode assistant. Supports running with lid closed WITHOUT external display/keyboard/mouse. Auto-detects Mac model and macOS version, prov... | |
| Virtuoso Skill Cadence Virtuoso Skill语言开发辅助工具，包含API查询、代码校验、智能补全功能。使用场景：(1) 编写/调试Virtuoso Skill代码；(2) 检查API调用是否合法；(3) 查询Skill函数的用法和参数；(4) 避免API幻觉和未定义函数调用。 | |
| SmartThings Direct Direct SmartThings hub control via the official SmartThings CLI. List devices, read device status, and execute capability commands without going through Home... | |
| Sendflare 通过 Sendflare SDK 发送带附件的电子邮件，管理联系人列表，支持 CC/BCC 和安全 API 认证。 | |
| Backup image to StarDots Automatically back up images to stardots.io cloud storage with secure MD5 authentication and configurable credentials. | |
| Backup image to StarDots Automatically upload images to Stardots.io cloud storage, manage files, and obtain secure access links using API authentication. | |
| Keeper Commander Use Keeper Commander CLI and Keeper Secrets Manager workflows when installing Keeper tooling, setting up profiles, signing in, running Keeper interactively,... | |
| Paradiz Отвечать клиентам в VK по стоимости отдыха на основе Excel-прайса. Использовать, когда нужно быстро посчитать цену по датам, количеству гостей и номеру, и вы... |
44,401–44,450 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.