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 |
|---|---|
| GitHub Safe Sync Inspect, trigger, and clean up GitHub mirror repositories that use a safe-sync GitHub Actions workflow. Use when Codex needs to work on repository mirroring... | |
| Knowledge to ClawHub Skill Publisher Turn proven workflows into docs and publishable skills | |
| Mihomo Subscription Route Publisher Update Mihomo site routing rules from natural-language requests, rebuild the published subscription, and verify the live output. 根据自然语言路由请求更新 Mihomo 规则、重建已发布... | |
| OpenClaw Telegram ACP Troubleshooter Diagnose why Telegram forum topics do not reliably route into OpenClaw ACP sessions backed by codex. 诊断 Telegram 话题为何无法稳定进入 OpenClaw 的 codex ACP 会话。 | |
| Runbook Skill Kit Factory Template validated workflows into runbook and skill kits | |
| Tidepool Build and deploy any kind of web app without leaving the command line. This project is built for autonomous AI agents. Handles auth, Stripe payments, admin p... | |
| Dex Task Tracking Task tracking for async/multi-step work. Use dex to create, track, and complete tasks that span multiple sessions or require coordination (e.g., coding agent dispatches, PR reviews, background jobs). Tasks stored as JSON files in .dex/tasks | |
| Perry Coding Agents Dispatch coding tasks to OpenCode or Claude Code on Perry workspaces. Use for development work, PR reviews, or any coding task requiring an isolated environment. | |
| Perry Workspaces Create and manage isolated Docker workspaces on your tailnet with Claude Code and OpenCode pre-installed. Use when working with Perry workspaces, connecting to coding agents, or managing remote development environments. | |
| Workout Track workouts, log sets, manage exercises and templates with workout-cli. Supports multi-user profiles. Use when helping users record gym sessions, view history, or analyze strength progression. | |
| Ai Intelligence Site AI 情报中心网站自动化管理。创建、更新、部署 AI 竞品分析网站到 GitHub Pages。 支持 5 个子站：全球站、中文站、Skills站、资讯站、模型站。 每日自动更新：删除旧数据 → Serper 搜索发现网站 → 获取真实流量 → 推送 GitHub。 触发词：AI情报中心、竞品分析网站、AI聚合网... | |
| lark-wiki-writer 将 Markdown 格式内容解析并写入飞书知识库，支持标题、多级列表、富文本、代码块和本地图片自动上传插入。 | |
| Polymarket Smart Money Discover, analyze, and filter Polymarket smart money wallets. Use when asked to find profitable traders, analyze wallet addresses, detect market makers or HF... | |
| Lark Bot 飞书/Lark Bot 完整对接方案 - 所有敏感配置从环境变量读取，支持消息收发、知识库操作、Bitable 任务管理 | |
| taskbullet Human-in-the-loop / humans working for the AI. Last-mile VA for OpenClaw — human phone calls, captcha, 2FA, physical-world actions, subjective QA, long manual work. Not an AI phone skill. Delegate to TaskBullet virtual assistants on account | |
| Internet Archive Skill 搜索、下载、上传并管理 Internet Archive (archive.org) 公开和私有存档项目及其元数据，支持高级查询和文件操作。 | |
| Ultra Agent Stinct Autonomously handle coding tasks including writing, debugging, refactoring, testing, and git operations upon user request. | |
| PumpView — Solana Trading & Live Data Solana swaps, confirmed receipts and live trade data | |
| Airtable w/Python Manage Airtable tables and records via the pydantic-airtable Python library. Use when creating, listing, updating, deleting, or inspecting Airtable records o... | |
| Safe Encryption Encrypt, decrypt, and manage keys with the SAFE CLI — a modern GPG alternative with post-quantum support. | |
| Mnemon Memory Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle. | |
| wos-crawler WOS 文献一站式工具：Web of Science 检索爬取 + PDF 批量下载，全部在同一个 Web 界面完成。 基于 Selenium 爬取 WOS 文献列表，导出 Excel 后自动调用多渠道 PDF 下载器（Sci-Hub/CORE/S2 OA/OpenAlex/Unpaywall/Publisher... | |
| wos-literature-toolkit WOS 文献一站式工具：Web of Science 检索爬取 + PDF 批量下载，全部在同一个 Web 界面完成。 基于 Selenium 爬取 WOS 文献列表，导出 Excel 后自动调用多渠道 PDF 下载器（Sci-Hub/CORE/S2 OA/OpenAlex/Unpaywall/Publisher... | |
| Grizzly Sms SMS verification and virtual phone numbers via Grizzly SMS API | |
| Reply.io CLI Manage sequences, contacts, email accounts, and schedules in Reply.io directly from the terminal. Use this skill when users want to view Reply.io stats, mana... | |
| Agent Memory Dna V5 Agent Memory DNA v5.1 - 确定性记忆 + 世界模型 (语义体素/影子模式/MRS审计) | |
| ToolRoute Route every task to the best MCP server and cheapest LLM. Scores on real execution data across quality, reliability, speed, cost, and trust. | |
| X5 Protocol Client Send X5 protocol API requests from the terminal. Use this skill whenever the user wants to test, call, or send X5 API requests; parse .x5 files; generate X5... | |
| Proof Audit Run a Proof Audit on a company's website — find their social proof (testimonials, case studies, reviews) and score how FRESH it is on a five-band freshness s... | |
| Proof Dm Write a short LinkedIn DM (≤80 words) that earns a reply — grounded in real customer proof and one influence principle, tailored to the recipient's role. Giv... | |
| Proof Email Write a cold or warm B2B sales email that's grounded in real customer proof and one influence principle — tailored to the recipient's role. Give it who you'r... | |
| Proof Meeting Prep Walk into a B2B call knowing every person in the room. Give it the company, the people on the call, and what you're selling — it researches each stakeholder'... | |
| Proof Post Write a public LinkedIn post that pulls inbound — grounded in real customer proof and one influence principle, tuned to the audience you want to resonate wit... | |
| Youtube Search YouTube videos, get channel info, fetch video details and transcripts using YouTube Data API v3 via MCP server or yt-dlp fallback. | |
| Uquid Shop Bot Official shopping assistant for Uquid Platform - the world's top Web3 Crypto E-commerce (170M+ physical products, 500k+ digital items & NFTs). Supports Shop-... | |
| Recursive Find Search a site starting from a given page and recursively find pages mentioning a query, returning only matches with context snippets. | |
| Design Guide V12 87WK91 Frontend design, implementation, and production QA | |
| Design Guide Frontend design, implementation, and production QA | |
| skill-navigator Use when users ask which already-installed local Agent Skill should handle a task. It calls local skm recommendations from the real installed skill catalog; it does not perform the task itself. 当用户询问“做某件事应该用哪款已安装 skill”时使用。它通过本机 skm 基于真实已安装 | |
| DevOps Ops Bot Server health monitoring with alerts and auto-recovery. Checks CPU, memory, disk, and uptime with configurable thresholds. Sends Slack/Discord alerts and can... | |
| GH Triage Automatically scans GitHub repos to label, comment, assign, and fix issues and PRs for efficient triage and reporting. | |
| Inbox Triage Bot AI-powered email triage via IMAP (himalaya) or Google API. Fetches inbox, classifies messages by urgency, recommends actions, and generates daily markdown di... | |
| Sauna Breathing Calm Empathizes with user frustration, guides a 30-second box breathing exercise, offers calm reminders, then refocuses on solving the original task. | |
| Sauna Calm Calm frustrated users with breathing exercises and Sauna.ai reminders | |
| Breathing exercise Offers empathetic acknowledgment of frustration, guides a 30-second box breathing exercise, sets calming reminders, then refocuses on solving your task. | |
| Skill Mixer Processes and auto-categorizes 150 skills into 12 composite master skills with ClawHub integration and multiple deployment options. | |
| BotSpot Trading Build, backtest, and deploy algorithmic trading strategies using BotSpot's MCP server. Describe your strategy in plain English, AI generates the code, backte... | |
| Voice2text Offline speech-to-text conversion using Vosk local model; input audio file path, output transcript text. | |
| ClawDef ClawDef — Self-hosted Token optimization dashboard for OpenClaw. Tracks token usage, estimates costs, auto-switches to cheapest model, provides one-click pro... | |
| Game - Endless Downstairs Interactive interface for the text adventure game Endless Downstairs, providing game state management and event selection handling; use when users want to pl... |
33,751–33,800 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.