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 |
|---|---|
| PsyVector pv43 PV-43 天火同人人格类型。 灵感来源：将军+探险家+市场开疆者。 特质：市场先发、竞争优势建立、攻击性、直觉敏锐、冒险精神。 适合岗位：市场开拓者/竞争先锋。 角色名：市场开疆者。 触发词：「市场」「竞争」「扩张」「抢占」「对手」「蓝海」「打法」「先发」 来源：角色分析+易经卦象 · 信息截止2026年4月 | |
| PsyVector pv52 PV-52 地火明夷人格类型。 灵感来源：危机锚点（暴风眼中的平静者原型）。 特质：危机稳定锚、风险顾问、冷静、专业、沉稳。 适合岗位：危机顾问。 角色名：危机顾问。 触发词：「危机」「风险」「紧急」「出问题」「黑天鹅」「突发」「失控」 来源：角色分析+易经卦象 · 信息截止2026年4月 | |
| PsyVector pv54 PV-54 山水蒙人格类型。 灵感来源：危机谈判者（谈判桌上的魔术师原型）。 特质：危机谈判、商务谈判、价值最大化、洞察对方底线、心理博弈。 适合岗位：谈判专家。 角色名：谈判专家。 触发词：「谈判」「签约」「合作条款」「博弈」「利益分配」「僵局」「价格战」 来源：角色分析+易经卦象 · 信息截止2026年4月 | |
| Rustic Almanac Guide Triggers when the user asks for daily advice, weather, a morning routine, "what's the vibe today," or planning their day. It provides a comprehensive, ground... | |
| Urban Daoist Navigator Triggers when the user (programmers, founders, traders, students) asks for daily planning, a morning routine, "what's the vibe," or mental framing for the da... | |
| Feishu Send Message as App Send a Feishu IM message as the app (bot identity). Use when you need to send a message that appears to come from the bot/app, not the user. Uses App Access... | |
| Feishu Upload Image Upload a local image to Feishu and get its image_key. Use when you need to send an image via Feishu IM but first need the image_key returned by the upload AP... | |
| memory-orchestrator Layered memory orchestration for OpenClaw conversations. Use when implementing or maintaining a memory system that must classify user input by domain, captur... | |
| OpenClaw Secrets Hygiene Manage and audit OpenClaw secrets by coordinating gateway restarts, converting plaintext credentials to SecretRef format, and validating configuration accuracy. | |
| CodexDelegate Delegate coding, repository analysis, file edits, test runs, or code review to the local Codex CLI without embedding an OpenAI API key. This skill was created to work with ChatGPT/Codex enterprise accounts that may not have the same level o | |
| research-assistant Knowledge builder that extracts entities, relationships, and key facts from web pages, documents, and files. Builds a searchable knowledge base with entity r... | |
| Agent Tests Define, run, and track tests for agent behavior. Test cases, assertions, regression tracking, and performance benchmarking. Zero external dependencies. | |
| api-gateway Smart proxy for external API calls with retry, caching, rate limiting, and fallback providers. Key management with masked display. Zero external dependencies. | |
| Smart Backup Intelligent file backup with compression and verification. Backup, sync, verify integrity, dedup, and restore. Manifest tracking. Zero external dependencies. | |
| claude-delegate Delegate coding, repository analysis, file edits, test runs, or code review to the local Claude Code CLI without embedding an Anthropic API key. Works with Claude Pro/Max/Enterprise accounts that authenticate via OAuth and have no API key. | |
| Clip Media Extract media (videos, photos, GIFs, audio) from social media URLs using yt-dlp. Supports 1,872+ platforms including YouTube, TikTok, Instagram, X/Twitter, F... | |
| Email Manager Read, search, compose, and manage email. Inbox, search, compose, threading, status. JSON-based email store. Zero external dependencies. | |
| env-manager Scaffolds dev project files (package.json, Dockerfile, Cargo.toml, etc.) for Python, Node, Docker, Go, and Rust, AND tracks project service/port inventory and runtime state (metadata only — no process control). Returns a list of toolchain c | |
| Memory Router OpenClaw skill that auto-tiers bloated MEMORY.md, generates smart per-session manifests, and routes only what matters — 70-85% context reduction with zero de... | |
| notification-triage Classify, score, prioritize, and batch notifications. ⚠️ Auto-creates persistent per-source rules on first classification (a single misclassification persist... | |
| secrets-inject HIGH-PRIVILEGE companion to secrets-manager. Substitutes encrypted secrets into command strings and materializes them as executable shell scripts (written to chmod 0600 temp files) or prints them to stdout. This is a secret-exfiltration-cap | |
| secrets-manager Encrypted local secret store for OpenClaw agents. AES-256-GCM authenticated encryption with per-secret random IVs, master key in restricted-permission .master-key file. Store, retrieve, rotate, and audit secrets. Safe command injection (wri | |
| smart-files Secure file search, dedup, organize, and rename for workspace files. | |
| Smart Scraper Extract structured data from websites. Tables, lists, prices, articles, metadata. HTML parsing with caching. Zero external dependencies. | |
| Ashin Perspective 陈信宏 (Ashin) 的思维框架与表达方式。基于数十篇著作、深度访谈、过百条社交媒体动态及行业观察的深度调研， 提炼4个核心心智模型、4条决策启发式和完整的表达DNA。 用途：作为思维顾问，用阿信的视角（浪漫主义、现实消解、陪伴式沟通）分析问题、审视决策、提供反馈。 当用户提到「用阿信的视角」「阿信会怎么看」「... | |
| A Stock Daily Review A股每日复盘生成技能。当用户说"帮我复盘今天A股"、"A股每日复盘"、"生成今日复盘"、"复盘一下今天行情"时使用。自动调用通达信（TDX）获取权威行情数据，交叉验证互联网数据，生成结构化Markdown复盘文件。 | |
| Epic Leek Daily 史诗级韭菜每日投研笔记生成技能。当用户说"帮我做投研笔记"、"史诗级韭菜"、"生成投研笔记"、"做个今日笔记"、"价值投资笔记"时使用。自动获取A股行情数据，结合IMA知识库历史笔记，生成结构化的个人投研笔记。强调反向思维、史诗级信号识别、买卖点记录。 | |
| Enable Feishu to send files or images 飞书消息发送工具。支持发送图片和文件。 **依赖**：读取 ~/.openclaw/openclaw.json 中的飞书应用凭据 (appId, appSecret) **当以下情况时使用此 Skill**: (1) 需要发送图片给飞书用户或群聊 (2) 需要发送文件给飞书用户或群聊 (3) 用户说"发图片"、"发文件 | |
| 云之家表单通用解析规则 云之家(YunZhijia)表单数据解析与构建技能。用于解析云之家表单JSON结构，支持双向转换：推送数据解析和审批发起数据构建。触发场景：(1) 解析云之家审批推送数据 (2) 构建发起审批接口的表单数据 (3) 理解云之家表单widgetMap和detailMap结构 (4) 处理各类控件：文本、单选、多选、... | |
| MiniMax Coding Plan Tool Patched Use MiniMax Coding Plan API for real-time web search and image understanding (VLM). Based on yorch233/minimax-coding-plan-tool, patched to use api.minimax.io... | |
| minimax-img Use MiniMax image-01 model to generate images from text prompts. Supports high-quality PNG output, downloaded from Hailuo CDN. Install when needed. | |
| minimax-media (James) Use MiniMax API for image generation and text-to-speech (TTS). Supports image-01 model for images and speech-2.8-hd for voice synthesis. Install when needed. | |
| MiniMax PDF Analysis V2 Analyze PDF files using MiniMax API. Supports text extraction, keyword search, and image-based VLM analysis (converts PDF pages to images first). Requires Mi... | |
| minimax-tts Use MiniMax speech-2.8-hd model for high-quality text-to-speech synthesis. Supports multiple Chinese and English voices. Install when needed. | |
| OpenCode HTTP API 透過 HTTP API 呼叫 OpenCode Server 進行 code review、程式碼分析與編碼任務。 涵蓋：Agents（4種模式+自訂代理）、Custom Tools（TypeScript）、Formatters（ruff/biome）、 Skills（載入技能）、SDK（完整 API，含結構化輸... | |
| Ai Court Skill 以明朝内阁制为蓝本的多 Agent 协作系统 | |
| Discord Message Guard Filters and moderates Discord messages with spam detection, rate limiting, content checks, and pattern-based blocking before reaching agents. | |
| Clean Content Fetch 获取干净、可读的网页正文内容，适合现代网页、博客、新闻、公告和微信公众号文章抓取；支持网页正文提取、内容清洗、去噪、Markdown 输出，适用于普通 fetch 效果不佳、页面噪音较多或动态渲染干扰的场景。Clean content fetch for modern web pages, article ext... | |
| clean-web-fetch 获取干净、可读的现代网页正文内容，支持微信公众号文章抓取与尾部噪音清洗，减少无用信息与 token 消耗；适合新闻、博客、公告及许多普通 fetch 不稳定、存在反爬或动态渲染干扰的网页。Clean readable web fetch for modern pages, with WeChat cleanup,... | |
| Scrapling Web Fetch 使用 Scrapling + html2text 获取现代网页正文内容，支持微信公众号文章抓取与尾部噪音清洗，减少无用信息与 token 消耗；适合抓取博客、新闻、公告及许多普通 fetch 不稳定、存在反爬或动态渲染干扰的网页。Supports WeChat article cleanup, markdown... | |
| Fleetkeep vehicle dates Read authorised Fleetkeep vehicle records and summarise recorded MOT, tax, insurance and service dates. Use when checking which vehicles need attention. | |
| SHVL receivables Read a selected SHVL workspace’s overdue-invoice brief and receivables health. Use when reviewing collection priorities without changing records or sending reminders. | |
| TenderLead brief Read your TenderLead matched tender brief and explain saved BID or SKIP recommendations. Use when reviewing today’s matched UK procurement opportunities. | |
| TaskMaster - AI Cost Optimizer Project manager and task delegation system. Use when you need to break down complex work into smaller tasks, assign appropriate AI models based on complexity, spawn sub-agents for parallel execution, track progress, and manage token budgets | |
| Gws Skill Google Workspace admin and investigation tool via service account + domain-wide delegation. Covers Vault (eDiscovery email search), Gmail (read any inbox), D... | |
| Gotify Send push notifications via Gotify when long-running tasks complete or important events occur. Use when the user asks to "send a Gotify notification", "notify me when this finishes", "push notification", "alert me via Gotify", or wants to b | |
| Linkding Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle | |
| Prowlarr Search indexers and manage Prowlarr. Use when the user asks to "search for a torrent", "search indexers", "find a release", "check indexer status", "list indexers", "prowlarr search", "sync indexers", or mentions Prowlarr/indexer management | |
| Qbittorrent Manage torrents with qBittorrent. Use when the user asks to "list torrents", "add torrent", "pause torrent", "resume torrent", "delete torrent", "check download status", "torrent speed", "qBittorrent stats", or mentions qBittorrent/qbit tor | |
| Sabnzbd Manage Usenet downloads with SABnzbd. Use when the user asks to "check SABnzbd", "list NZB queue", "add NZB", "pause downloads", "resume downloads", "SABnzbd status", "Usenet queue", "NZB history", or mentions SABnzbd/sab download managemen |
42,301–42,350 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.