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 |
|---|---|
| Remote Install Automate remote Windows software installation using installer detection and GUI automation for .exe/.msi packages like Office, Adobe, and Chrome. | |
| Wechat Blog Write Publish 自动根据用户提供的参考资料撰写符合格式的微信公众号文章，并发布至公众号草稿箱。 | |
| Wincontrol AI remote control for Windows desktop. Captures screen on-demand via POST request and provides an HTTP API for mouse/keyboard actions. | |
| Windows Remote Control remote Windows machines via SSH. Use when executing commands on Windows, checking GPU status (nvidia-smi), running scripts, or managing remote Window... | |
| Write Plan, draft, version, and refine written content with enforced versioning and quality audits. | |
| Xia Desktop Agent Windows桌面自动化代理。通过自然语言或预设指令控制桌面：截图、点击、输入、按键、打开应用、微信发消息/文件、ToDesk远程连接。Use when user asks to control desktop, send WeChat messages, establish ToDesk remote conn... | |
| Parser content trên web 24h Chích Bông read one public product page from 24h.chichbong.com and turn it into a compact zalo-shop-ready product block. use when the user provides a single 24h.chichbo... | |
| English Bestie A friendly AI English teacher that runs daily lessons via Telegram voice messages. Teaches grammar, vocabulary, and conversation with a casual buddy vibe. | |
| Hail Communication Send and receive email, SMS, and phone calls from your agent. Sign up yourself: free credit, no card, no human required. | |
| Todoist Natural Language Integrate with Todoist task management using natural language. Use when the user wants to manage Todoist tasks or projects through conversational commands li... | |
| asdasdsad Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. | |
| sdfsdfsd Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. | |
| DrinkedIn Night Out Plan a walkable bar crawl, craft beer crawl, dinner and drinks, or club night near a place, using only venues DrinkedIn has validated against an official licence register or premises census, or the venue's own site. Use when someone asks fo | |
| Obsidian Wiki Manager Manage an Obsidian-based personal knowledge base (wiki) with strict ingestion, query, lint, reflect, merge, and system maintenance protocols. Trigger on inge... | |
| Publish site on Qutke 将文件和文件夹即时发布到网络。支持 HTML 站点、图片、PDF 及任何文件类型的静态托管。 当用户要求"发布这个"、"托管这个"、"部署这个"、"分享到网上"、"做一个网站"、 "放到线上"、"上传到网络"、"创建网页"、"分享链接"、"搭建站点"或"生成 URL"时使用。 输出一个可访问的 URL，格式为 {... | |
| P-E 极速图片提取工具。发送模板图片+多张实际图片，秒懂格式，一步到位生成 Excel 表格。无需确认，直接输出。 触发方式：/p-e、/pe、「图片提取」「提取Excel」「picture extract」 Picture Extract: send template + data images, instantly... | |
| Self Improving Agent AI Self-Improving Agent v2 - Learn from mistakes, corrections, and successes. Three-layer system: passive capture + proactive check + proactive skill generat... | |
| wechat-chat-analysis 微信聊天记录人格分析与恋爱助手。当用户想要分析自己与某人的聊天记录、了解双方性格、进展、问题、改进建议，或问"下一步该怎么回"时触发。使用 wechat-cli 读取本地微信聊天数据，进行结构化分析。 | |
| Skill Convert any URL or file to Markdown. Supports webpage, WeChat, YouTube, Bilibili, Douyin, Xiaohongshu, PDF, and Office files. | |
| octo PPT 制作 PPT、演示文稿、幻灯片、汇报材料时使用。Dashi PPT 基于预置视觉主题组合页面,生成可离线打开、可在浏览器编辑的 HTML 演示,支持导出 PPTX / PDF 文件。 | |
| Haixian Ppt Skill 生成横向翻页网页 PPT（单 HTML 文件），含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格：① "电子杂志 × 电子墨水"（衬线 + 流体背景 + 暖色） ② "瑞士国际主义"（无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮）。当用户需要制作分享 / 演讲 / 发布会风... | |
| desktop-pet Transform photos into interactive desktop pets — auto subject detection, background removal, Q-style cute makeover, 5+ animated actions, and interaction logic. Outputs a ready-to-install desktop pet application (.exe for Windows, .dmg for M | |
| Agent Runtime Impact Research Research and analyze major Agent harness, runtime, coding-agent, skills, subagent, and plugin releases. Use when a model or platform launches an Agent execut... | |
| 命理占卜 · Chinese Fortune Telling Chinese fortune telling (算命 / 算卦 / 看八字 / 排盘) grounded in classical source texts: a bundled rule engine computes the chart, then the agent interprets it with an explicit school declaration. Computes BaZi Four Pillars (八字 / 四柱) with true-sola | |
| Claim-to-Source Auditor When the user asks to audit, fact-check, verify, or cross-check an article, report, draft, or series. Triggered by 审稿/审计/核验/事实检查/来源追溯/查一下这个数据/核对/审查/跨平台一致性/三平... | |
| Content Publishing Suite Turn a fact-checked and compliance-approved final Markdown draft into multi-channel publishing assets — WeChat article, LinkedIn post, standalone responsive... | |
| Cross-Material Consistency Auditor Compare two or more materials on the same topic or event for cross-material consistency before publication. Identifies mismatched numbers, product names, fac... | |
| Industry Daily Brief Turn any industry into a daily intelligence briefing. An AI agent searches, filters, writes, and delivers structured daily briefs to 9 channels — with machin... | |
| Chinese DOCX Typesetting Baseline Locked design-token baseline for Chinese Word/DOCX documents and WeChat-native (公众号) article layouts: body 16px, section head 18px, title 23px, deep-blue #1a... | |
| Editorial Topic Portfolio This skill should be used when evaluating a portfolio of technology, AI, data, cloud, or enterprise-software content topics. It normalizes Notion or Markdown... | |
| GitHub PAT Debugging 排查 GitHub PAT 认证失败、401、Bad credentials、推送失败、token 看起来失效等问题。先检查命令、变量传递、路径和请求参数，再用 curl、Node、Python 或 PowerShell 交叉验证，确认后才判断权限、撤销或网络原因。适用于 GitHub API、Contents API、GitHub Pages 和 Skill 镜像推送。 Diagnose GitHub Personal Access Token failures befor | |
| Industry Deep Dive Pipeline This skill should be used when turning a topic brief, research materials, vendor case, policy event, or industry question into a publish-ready single deep-dive article for technology, AI, data, cloud, or enterprise-software audiences. It ru | |
| InvAssistant Multi-asset investment portfolio management framework with A/B/C asset-class differentiated rules, 7 red-line portfolio risk controls, and 4-factor QMS quali... | |
| Notion Personal Space Audit Audit a personal Notion hub and its nested pages and databases: identify mixed content types, empty placeholders, weak navigation, and sensitivity-boundary p... | |
| Procurement Admission Copilot Shadow-mode copilot for B2B procurement admission. Given a supplier's raw qualification inputs, it checks material-package completeness and internal consiste... | |
| running-coach Running coach for endurance athletes training with Garmin, Strava, Coros, or Apple Watch. Provides VDOT-based pace zones, session analysis from training screenshots, weekly and periodized season plans (5K through marathon), race strategy, l | |
| Skill Audit Publish Audit-first pipeline to publish an OpenClaw skill to ClawHub, SkillHub, and GitHub without leaking personal data, credentials, or model-specific references.... | |
| Skill Batch Operations Batch operations across many skills (3+): inventory, batch patching, multi-platform publish, version alignment, and per-item verification. Use for stale-skil... | |
| Skill Design Guide Design better AI skills with proven architecture patterns. Helps you decide Workflow vs Agent, pick the right pattern (Prompt Chaining, Routing, Parallelizat... | |
| Skill Local Overlay Local patch layer for marketplace, connector, and built-in skills that get overwritten on platform or plugin upgrades. Use BEFORE modifying any skill that is... | |
| Skill Portfolio Audit Generates evidence-based portfolio audits, candidate scorecards, privacy classifications, consolidation plans, and a persistent execution queue with dependen... | |
| social-persona-profiling Profile people from social-media traces — avatar, profile/cover background, nickname, privacy/visibility settings, chat behavior, shared content, self-reported labels — across platforms (WeChat, WhatsApp, Instagram, LinkedIn, Telegram, X) a | |
| Content Adapter Channel-adaptation agent. Adapts a reviewed core draft into channel-specific publish-ready versions. Supports: official-account version, developer-community... | |
| Content Compliance Reviewer Pre-publication compliance and quality reviewer. Checks factual citations, customer redaction, product naming, competitor rules, internal information, format... | |
| Content Performance Analyst Monthly content performance and output-analysis skill. Aggregates published content, the content calendar, channel-effect data, product-line coverage, and kn... | |
| Content Planner Content topic-planning agent. Generates structured topic briefs from knowledge-base updates, competitor signals, the content calendar, and performance data.... | |
| Content Writer For tech-product marketing teams — turns a product knowledge base into brand-side long-form drafts (blogs, case studies, product write-ups), not third-party... | |
| tech-content-review-panel Reviews a tech/AI/industry research or in-depth analysis long-form article before publishing, via a fixed eight-role expert panel (target-reader reps, quality gatekeepers incl. fact+originality check, distribution gatekeeper) in an evaluate | |
| Tencent Docs Stable Channel Stable write path for Tencent Docs (腾讯文档) when the MCP connector fails. Use when any Tencent Docs write, upload, push, or paragraph insert fails or times out... | |
| Vendor Summit Report Build an executive-oriented deep-dive report for a major data/AI vendor conference — Snowflake Summit, Databricks Data+AI Summit, Microsoft Build, Google Clo... |
34,401–34,450 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.