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 |
|---|---|
| youtube-transcript-native-node Extract a clean plain-text transcript from existing YouTube captions - native Node.js, zero npm dependencies. Use when the user asks to summarize, quote, or extract captions/transcript text from a YouTube URL. Wraps the `yt-dlp` binary on P | |
| remove-bg Remove single-color light backgrounds from images and output transparent PNGs using a luminance threshold. | |
| TODO Web App Deploy a local TODO web app that reads and writes a Markdown TODO.md file. Serves a beautiful dark-themed, glassmorphism UI on the LAN (no HTTPS needed). Fea... | |
| Audio Editor Perform audio editing tasks including trimming, volume adjustment, format conversion, and extracting audio from video files using natural language commands. | |
| Polla ProofReader For Central Kurdish (Sorani) Academic auditor and Rhetoric expert for Central Kurdish (Sorani). Use to verify professional standards in punctuation, terminology, orthography, grammar, an... | |
| Polla Translator For Central Kurdish (ckb) Expert translator from English to Central Kurdish (Sorani) for all Information Technology domains — including apps, operating systems, servers, networks, dat... | |
| File Reader 文件读取技能。当用户需要读取文件内容、查看文件、cat 文件时激活。支持读取文本文件、配置文件、代码文件等。 | |
| Xyz 网络搜索工具，支持多种搜索引擎后端（DuckDuckGo、Tavily、Bing、Google、SearXNG）。使用场景：当用户需要搜索网络上的实时信息、查找最新资料、获取在线资源时调用。通过命令行执行搜索查询并返回结构化的搜索结果（标题、链接、摘要）。 | |
| Claude Prompt Engineering - 提示词工程大师 系统性应用Claude源码的9条提示词工程规则，提升AI回答质量，确保准确、简洁、无编造，适配多场景任务需求。 | |
| Find Skills Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express... | |
| Google Workspace CLI (gog) Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. | |
| Industry Insight - 行业洞察分析 行业洞察分析助手，使用麦肯锡工作法帮助产品经理快速了解任意行业。包含关键词定义、报告搜索、书籍推荐、思维导图生成、关键洞察提炼。 | |
| Marketing Ideas for SaaS When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growt... | |
| OpenClaw Token Saver OpenClaw Token 节省指南。提供5大类20+种减少Token消耗的方法，包括上下文瘦身、工具优化、缓存复用、模型控制和本地替代方案。当Token使用超过阈值时自动触发优化建议。 | |
| Prompt Master - 提示词工程精华版 基于Claude Code的9条核心规则，提供极简提示词速查和即用模板，助你快速写出高质量提示词。 | |
| Quality Boost - 大模型回答质量提升器 通过9条严格规则系统评估并量化大模型回答质量，防止幻觉、跑偏、冗长和遗漏，确保准确、简洁、合规的输出。 | |
| bg-remover Remove, replace, or blur image backgrounds using AI-powered segmentation (rembg/U2-Net). Use when the user asks to: (1) remove image background / make transp... | |
| AI Capability Analyzer 智能分析用户需求并推荐最适合的ClawHub技能，提供实时技能搜索、安全评估和使用建议。 | |
| YouTube Video Downloader Download YouTube videos by URL in various resolutions using a pay-per-use API with credit-based authentication and no charge on failed downloads. Use when us... | |
| Steam Deck Disk Steam Deck 磁盘空间管理和优化。清理缓存、日志、移动大文件到 /home 分区、检查磁盘使用。 | |
| Stock Analysis CN 一键分析A股：技术面+估值+风险+基本面全覆盖，自动生成Word投资报告。基于腾讯财经API，内置行业专用估值基准。 | |
| hum AI content writer that researches, outlines, drafts, publishes, and manages engagement for LinkedIn and X using your voice and style guidelines. | |
| HTMLPix API Use when the user wants to call, test, or integrate the HTMLPix HTML-to-image API — including auth setup, signed URL minting, image rendering, template CRUD,... | |
| Clawbsky AI-powered Bluesky CLI with multi-user auth, smart content generation, post scheduling, analytics, RSS automation, and growth tools. | |
| Feishu Messaging 飞书消息发送与文档创建工作流。
触发场景：查找群成员、查找群ID、发送消息失败需要重新尝试。
适用于：发送飞书消息。 | |
| m3u8 video downloader This skill should be used when the user wants to download videos from M3U8 streaming URLs. It handles parsing M3U8 playlists (including nested multi-bitrate... | |
| Xpilot Ad Maker Generate a 30-second cinematic ad video with consistent character, AI narration, brand overlays, and ambient music. Uses Vidu reference-to-video for characte... | |
| Baserow Baserow: Create, read, update, and delete rows, list tables and fields. Use when the user wants to interact with Baserow — querying data, creating or updatin... | |
| Baserow CLI Baserow: Create, read, update, and delete rows, list tables and fields. Use when the user wants to interact with Baserow — querying data, creating or updatin... | |
| Internet Search How to use the internet_search tool effectively — category routing, query formulation, and multi-search strategies. Use whenever web search is needed: curren... | |
| Plane CLI Plane.so: Create, update, and manage issues, projects, states, labels, and pages. Use when the user wants to interact with Plane.so — creating issues, listin... | |
| Smartlead Manage Smartlead campaigns, leads, and webhooks from the command line via the smartlead CLI. | |
| OpenClaw Backup Automation Automated backup for OpenClaw instances. Backs up agents, skills, cron jobs, and memory. Supports local tar archives. Credentials, periodic scheduling, and g... | |
| Client Flow Automated client onboarding and project lifecycle management. From a single message, creates Google Drive/Dropbox project folder structure, generates project... | |
| Lead Enrichment Scanner Automated B2B lead generation and enrichment. Input: company names or domains. Output: enriched contact records with decision-maker names, emails, LinkedIn p... | |
| MENA Property Listing Generator AI-powered property listing generator for real estate agents in MENA. Input: 5-10 property photos + basic specs. Output: SEO-optimized Arabic + English listi... | |
| Skill Audit Audit locally installed agent skills for security/policy issues using the SkillLens CLI (`skilllens scan`, `skilllens config`). Use when asked to scan a skil... | |
| SMB Client Onboarding Automated client onboarding workflow for agencies, consultants, and freelancers. From signed contract to activated client in 24 hours — welcome email, docume... | |
| SMB Invoice Tracker Automated invoice tracking + payment reminders for freelancers and small businesses. Scans Gmail for invoices, extracts amounts and due dates via LLM, sends... | |
| Docs Refresh Refresh authoritative docs through routed workflow modes | |
| Mission Control macOS-native web dashboard for monitoring and controlling your OpenClaw agent. Live chat, cron management, task workshop, scout engine, cost tracking, and more. | |
| ShieldClaw Security suite for OpenClaw. Provides security scanning, real-time protection, audit logging, and sensitive data encryption. Use this skill when users need s... | |
| Token Saver Skill Smart token cost optimization for OpenClaw. Automatically reduces AI token consumption by 50-80% through intelligent context compression, semantic caching, a... | |
| AWI AWI (Agentic Web Interface) — 联网读取+搜索，单二进制零配置。 三级自动降级：直连 → 智能适配 → 浏览器渲染。 不需要 API Key，不需要 Docker。 | |
| Context Doctor Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skil... | |
| Agent Guardrails Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. B... | |
| Humanizer by JZ Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp... | |
| Roundtable by JZ Multi-perspective decision analysis. Use when the user asks for roundtable, or when facing important decisions that need multiple viewpoints. Dynamically sel... | |
| Self-Improving Skill 让任何 writing style skill 自动从人类修改中学习。 只需要两个数据点：AI 原稿 (original) 和人类最终版 (final)。 自动 diff → 提取规则 → 更新目标 SKILL.md。 兼容 Claude Code (~/.claude/skills/) 和 OpenClaw (... | |
| Agent Workflow Enforcer 让 AI Agent 的执行流程稳定可控。 通过 Gate 门禁、强制输出格式、Style Context 持久化， 把"建议"变成"必须"，解决 Agent 选择性执行的问题。 |
43,901–43,950 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.