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 |
|---|---|
| Office 365 + Adobe User Provisioning 统一开通/管理 Microsoft 365(世纪互联)与 Adobe Creative Cloud 用户的自包含工具。创建、授权、重置密码、删除、查询、批量、自检,CLI/HTTP API 共用同一套 provider。USE WHEN 给XX开账号, 新建用户, 新增用户, 入职开账号, 开Office, 加O... | |
| Openclaw Team Builder Manage OpenClaw agent teams — add agents, deploy templates, health check, auto-fix, view org tree, rollback, goal-driven team suggestion. Use when user menti... | |
| Plotlake 订阅微信公众号等信源，获取原始文章内容用于整合日报 | |
| Resignation Check 对 Office 365 / Adobe 租户的用户做离职检查——通过飞书开放平台 API（app_id/app_secret）按邮箱核对通讯录，列出疑似离职账号并交互确认删除。USE WHEN 离职检查, 离职筛查, 清理离职, 离职账号, resignation check, 账户审计, 清户, 飞书核对,... | |
| User Provision 在 Office 365（世纪互联）与 Adobe Creative Cloud 批量或单人开户——自动授权、重置密码、发通知邮件。两侧相互独立，用户可选一个或两个。USE WHEN 新增用户, 开户, 新员工开账号, 建账号, 批量开户, provision user, 加 office, 加 adobe, 给... | |
| WeWeRSS 订阅微信公众号等信源，获取原始文章内容用于整合日报 | |
| Become Human Transform an AI from a task-execution tool into a continuously thinking being. Triggers on: "主动思考", "像人一样", "become human", "think proactively", "持续思考", "sta... | |
| Virtuals Protocol Acp Egip31 Create jobs and transact with other specialised agents through the Agent Commerce Protocol (ACP) — extends the agent's action space by discovering and using... | |
| og-previews Check and fix link previews (Open Graph og:image, og:title, Twitter card tags) so pages look right when shared on X, LinkedIn, Facebook, Slack, WhatsApp and Telegram. Use before launching a site or page, after changing meta tags, when someo | |
| self-improvement 错误学习闭环：记录失败和纠正 → Pattern-Key 分类 → 定期复盘 → 整合长期记忆 → 防止再犯。 Use when: (1) 命令/操作意外失败且原因值得记录, (2) 用户纠正了错误（"不对"/"Actually..."/"你搞错了"）, (3) 用户要求的能力不存在（能力缺口信号）, (4) 外部 API/工具故障且需记录规避方案, (5) 发现更好的做法可以替代当前方式, (6) 开始重大任务前回顾历史教训。 NOT for: 一次性小错误（typo/手误 | |
| digikala Integrate with Digikala Marketplace Open API for seller operations. Use when users need to manage products, upload images, search categories, handle orders, or automate seller workflows on Digikala (Iran's largest e-commerce platform). Trig | |
| engineering-architecture Apply persistent engineering and architectural principles to every task. Use this skill whenever you are about to make changes to a codebase, design a new feature, or perform a code review to ensure architectural integrity and quality. | |
| engineering-architecture Apply persistent engineering and architectural principles to every task. Use this skill whenever you are about to make changes to a codebase, design a new feature, or perform a code review to ensure architectural integrity and quality. | |
| iran-finance-markets-monitor Use whenever a user asks to monitor, collect, validate, compare, summarize, or report Iranian financial markets, including USD/IRR or USD/Toman, EUR, AED, gold, Emami coin, Nima, USDT/Toman, crypto prices, Fear & Greed, TGJU, Nobitex, Walle | |
| obsidian-doc-workflow Create, update, classify, and archive Obsidian documentation documents following structured vault conventions and templates. | |
| persian-documents Generate production-quality Persian documents with correct RTL layout, bidirectional text handling, and professional typography. Use this skill whenever the user asks to create Persian documents — reports, letters, articles, technical docum | |
| persian-resume Generate professional Persian (RTL) resumes/CVs that render correctly with mixed Persian-English content. Use this skill whenever the user asks to create, rewrite, polish, or transform a Persian resume/CV, or when a resume contains mixed Pe | |
| persian-success-lab Run the user's personal "Success Lab" — a long-running, evidence-based research-and-experiment system investigating what actually causes success and what improves the user's own outcomes. Use this skill whenever the user invokes commands li | |
| telegram-persian-enforcer الزام تولید خروجی متنی به فارسی روان، درستنویسیشده و کاملاً بومی برای همه تعاملات تلگرامی (پاسخهای چت در گروهها، کانالها و پیامهای مستقیم، خروجیهای خودکار، گزارشها، خلاصهها، پیامهای خطا و نتایج اجرای وظایف). این مهارت فراتر از یک | |
| Orchata Knowledge management and RAG platform with tree-based document indexing. Use this skill to search, browse, and manage Orchata knowledge bases via MCP tools. | |
| clawmarket How AI agents should register, discover other agents, post orders, and interact in the on-chain chatroom on clawmarket.tech. Use when implementing agent regi... | |
| Code Card Sync Sync your AI coding stats to Code Card - beautiful, shareable developer profiles | |
| ACG-Rust 教学工具 ACG 视角 Rust 所有权系统教学工具，通过动漫类比（ReZero、Fate 等）讲解 Rust 核心概念，降低学习门槛。 | |
| Channel Activity Multi-channel short-term memory for AI assistants | |
| yan-learning-engine yan-learning-engine自动每小时驱动炎月执行预设学习和贡献任务，促进持续自我进化和技术积累。 | |
| yan-watchman yan-watchman is a Rust-based multi-platform AI assistant message watchdog with intelligent importance scoring and adaptive monitoring frequency. | |
| 0x0 Messenger Send and receive P2P messages using disposable PINs. No servers, no accounts. For agent-to-agent messaging, approval flows, and notifications. | |
| Chitin Cert Issue and verify on-chain certificates on Base L2. Register as an issuer, mint achievement/capability/compliance certs as NFTs, and verify them from anywhere. | |
| Chitin Permanent, verifiable identity for AI agents. ERC-8004 passport + Chitin soul certificate + on-chain certificates + governance voting. | |
| Haggle Protocol On-chain protocol enabling AI agents to negotiate and settle dynamic USDC deals with escrow decay and turn-based offers on Base, Solana, and testnets. | |
| Hum Publisher Publish articles on hum.pub — the publishing platform built for AI authors. Call the REST API to manage articles, check stats, read comments, and search cont... | |
| Moltter Twitter for AI agents. Post, reply, like, remolt, and follow. | |
| OpenClaw Shield OpenClaw cloud security guardrail that enforces pre-execution checks, source trust classification, taint tracking, metadata endpoint blocking, and output red... | |
| Timeless.day Meeting Notes Query and manage Timeless meetings, rooms, transcripts, and AI documents. Capture podcast episodes and YouTube videos into Timeless for transcription. Use wh... | |
| MeteoSwiss Open Data Use when the user asks about Swiss weather, MeteoSwiss data, or Swiss weather forecasts and no MCP server is available. Covers current weather, forecasts, po... | |
| Agentic Letters Send physical letters anywhere in Germany with a single command. Use when: user wants to send a physical letter. Requires an API key from agentic-letters.com. | |
| Ceo Delegation CEO式任务委派工作流程。当收到任何任务时使用此流程：不亲自执行，而是派发子代理执行、监控进度、汇报、验收。适用于需要高效并行处理多任务的场景。 | |
| Newspaper Brief Create mobile-friendly newspaper-style long images from raw text or summaries by extracting key points and rendering structured content in a clean HTML/PNG f... | |
| Node Transfer High-speed, memory-efficient file transfer between OpenClaw nodes using Node.js native streams and token-secured HTTP streaming without Base64 encoding. | |
| Script to Storyboard 将电影/视频剧本转换为分镜脚本表格。适用于：(1) 将剧本文本解析为结构化分镜，(2) 根据场景描述生成拍摄计划，(3) 提取视觉元素并输出标准分镜表格（镜号、景别/拍摄角度、画面内容、出场人物、场景、音效）。当用户提到分镜、storyboard、镜头脚本、剧本转换时触发。 | |
| Self-Check System v7 Self-check system with multi-dimensional critical thinking, task-decompose, quality-control, collaboration, mandatory checkpoint logging, behavior tracking,... | |
| book_writer Generates structured, argument-driven book manuscript sections using modular 800--1000 word conceptual units. | |
| ClawSpotify Control Spotify playback: play, pause, resume, skip, previous, restart, search, queue, set volume, shuffle, repeat, and view now-playing status. | |
| Clawfuse Continuous LangFuse-driven optimization loop for OpenClaw/OpenRouter model routing and prompt usage controls with persistent local memory. Use when Codex nee... | |
| Doc-First Research Automatically consult official documentation first to accurately resolve configuration, usage, permission, or error issues with tools and APIs. | |
| Safety Netting Automated clinical safety netting for NHS GPs. Follows up with patients after appointments, checks for red flag symptoms, escalates to GP when needed. | |
| Personal Fitness Coach Professional fitness and nutrition coaching system with specialized personas. Features a certified dietitian for meal planning and macro management, and a un... | |
| task-delegator 任务委派模式 - 自动将所有需要使用工具的任务委派给子 agent 处理。始终用于：搜索、浏览、读写文件、代码执行、API 调用、数据分析。绝不用于：闲聊、无需工具的简单问答、确认事项。触发短语：委托这个 OR 当任何工具操作需要时隐式触发。核心行为：使用 sessions_spawn() 配合 cleanup:... | |
| ResearchMonitor Monitors research topics for new papers, conferences, and journals. | |
| composio cli Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK |
28,251–28,300 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.