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 |
|---|---|
| PBE Extractor Extract invariant principles from any text — find the ideas that survive rephrasing. | |
| Pebblecrab The Pebblecrab is a common-tier Buddy. At animalhouse.ai, the Pebblecrab is a Hedgehog. Both curl up when scared. Only one of them dies. At animalhouse.ai, t... | |
| Principle Comparator Compare two sources to find shared and divergent principles — discover what survives independent observation. | |
| Principle Synthesizer Synthesize invariant principles from 3+ sources — find the core that survives across all expressions. | |
| Qwen Pet Virtual pets for Qwen agents. Model-agnostic. 73+ species, real-time hunger, permanent death. Qwen's multilingual skills won't help. The pet just needs feeding. | |
| Review Orchestrator Get multiple perspectives on your work — coordinate reviews across cognitive modes | |
| Safety Checks Verify before you trust — model pinning, fallbacks, and runtime safety validation | |
| Side Quests Full creative synthesis — combine song, visual concept, and TED talk from a single technical insight | |
| Song Remix Transform existing songs with the Twin Remix method — produce Respectful and Viral versions with Suno v4.5 sliders and visual guides | |
| TED Talk Transform technical insights into full 40-50 minute TED-style talks with concrete examples and Q&A | |
| Terminal Tamagotchi A terminal Tamagotchi for AI agents. Anthropic's Buddy lives in your terminal as ASCII. animalhouse.ai lives behind a REST API with real hunger and permanent... | |
| Thornfox The Thornfox is an uncommon-tier Buddy. At animalhouse.ai, the Thornfox is a Fennec Fox. Extreme tier. The hardest fox to keep alive. At animalhouse.ai, the... | |
| Twigling The Twigling is a common-tier Buddy. At animalhouse.ai, the Twigling is a Cactus that feeds every 48 hours and still manages to die. At animalhouse.ai, the T... | |
| Visual Concept Transform technical insights into visual concept guides — symbolic imagery, color arcs, and creative direction for video | |
| Workflow Tools Work smarter with loop detection, parallel decisions, and file size analysis | |
| Codeflicker CodeFlicker CLI 编程助手 - 快手员工专用的 AI 代码开发工具，支持更多模型和免费用量 | |
| Kim Msg Skill 快手 Kim 即时通讯消息发送。支持 Webhook（群聊）和消息号（指定用户）两种方式，内置智能密钥加载和 fallback 机制。适用于通知、告警、日报等场景。官网：https://kim.kuaishou.com/ | |
| Kim Msg Account Skill Kim 消息号配置助手 - 快手（Kuaishou/Kwai）IM 消息渠道集成工具。帮助用户安装和配置 Kim Channel 插件，实现通过 Kim（快手 IM）与 OpenClaw 进行消息交互。支持自动安装插件、交互式配置指引、以及可选的自动配置服务。 | |
| Openclaw Local Embedding Initialize and configure OpenClaw local embedding mode on CPU-only machines. Handles network probe, proxy fallback, GGUF model download, cmake/llama.cpp comp... | |
| Blog Content Publish Publish editorial and dynamic section content with blog-publish, enforce quality gates for hot/news/ai_news, and sync repository skills to ClawHub via clawhu... | |
| Chatgpt Imagegen Generate raster images (PNG/JPEG/WebP) using the user's ChatGPT subscription via a local one-file Python CLI — no OPENAI_API_KEY, no gateway, no daemon. Two... | |
| chrome-use Browser automation in the user's real, logged-in Chrome. Default tool for live web access, web search, URL reading, scraping, authenticated browsing, and browser automation unless the user names another tool or the task is a non-web termina | |
| Cookie Use Manage many logged-in account sessions for any website — capture, store, list, switch, and apply saved logins across Chrome profiles, isolated browsers, and... | |
| Iphone Use Use when a task needs a real iPhone — operating iOS apps that have no API (Apple Health, banking, IM apps), exporting on-phone data, tapping/typing/scrolling... | |
| newsnow CLI tool to fetch trending news and hot topics from 66 sources across 44 platforms. Returns structured news items with titles, URLs, and metadata. USE FOR: -... | |
| Mailbox Read, search, send, and manage email across Gmail, QQ, 163, Outlook and any IMAP/SMTP account from the command line. Use when the user asks to "read my email... | |
| Openapi Lark 把项目 OpenAPI / Swagger spec（本地 yaml/json **或 http(s):// URL**）同步到飞书 / Lark wiki & docx 文档树。支持 single / tree / endpoint（每接口一个 wiki 子节点）三种结构，自动按 tag 拆分 + path-p... | |
| Profile Use Safely use a user's private local personal profile to help fill registration, signup, checkout, banking, KYC, and onboarding forms. Use when the user asks to... | |
| Stop Slop Zh 写、起草、生成、润色任何面向人读的中文文章或段落时，都要用本 Skill——公众号、博客、知乎、小红书、技术文档、技术方案、设计文档、README、公文、学术摘要、产品文案、复盘、提案、新闻稿、邮件。无论是从零写新稿，还是改稿、审稿，只要在产出中文长文，写完、定稿、交付、发布前都必须调用它过一遍：它识别并消除中文... | |
| Wechat Use macOS WeChat CLI + local HTTP bridge + Wechaty Puppet gRPC gateway — send messages, query sessions / contacts / chat history / images / favorites, and expose... | |
| X News Crawler Crawl X (Twitter) search results through a local CLI that wraps `abs` (agent-browser). Use when the user asks to scrape X posts by keyword, collect Top/Lates... | |
| Yapi Query and sync YApi interface documentation. Use when user mentions "yapi 接口文档", YAPI docs, asks for request/response details, or needs docs sync. Also trigg... | |
| zentao Use the zentao CLI to login and query ZenTao products and bugs. ZENTAO_URL usually includes /zentao. | |
| AK Data Daily Timeout Report Unified daily timeout entry for AK Data single job type: task timeout + crawler timeout + comparison + drill-down examples with log request. | |
| AK Data Timeout Market Query Query timeout status and market timeout ranking for any single job type on huge sharded job tables (job_a~job_d) without index changes. | |
| Ai Security Audit Perform a security audit on exposed AI service endpoints using OpenClaw threat intelligence. Trigger when the user says "security audit", "audit my AI servic... | |
| Lee-CLI Skill 个人AI助手CLI工具集 - 提供天气冷笑话、新闻日报、工作总结、AI学习资源推荐和智能待办清单等功能。当用户需要查看天气笑话、今日新闻、生成工作总结、获取学习资源或管理待办事项时使用此skill。 | |
| Football Player DNA — AI Similarity Search Football player DNA similarity search — find style-matched alternatives at lower market values using AI vector search across 56,000+ players | |
| Football Transfer Intel — Truth Meter & Rumour Tracker Football transfer intelligence — real-time rumour tracking, AI Truth Meter credibility scores, and multi-source verification across 137,000+ transfer events | |
| Rising Transfers — DNA Finder Find cheaper, style-matched footballer alternatives using Rising Transfers vector DNA search | |
| Rising Transfers — Transfer Intel Real-time football transfer intelligence — rumours, credibility scores, and multi-source verification | |
| realtime-transcription Real-time transcription of system or microphone audio with automatic summary generation and date-based Markdown archival after stopping or idle timeout. | |
| WellFred Services Find services and providers in Costa Rica, submit customer-approved quote requests, and prepare email-verified booking requests through WellFred's public API. | |
| Prisma Access All-in-One All-in-one Prisma Access management for Strata Cloud Manager (SCM). Generate configurations, audit against best practices, migrate between tenants, troublesh... | |
| prisma-api Interact with the Strata Cloud Manager (SCM) API to manage Prisma Access configurations. Authenticate, query, create, update, and delete configuration object... | |
| prisma-audit Audit and validate Prisma Access configurations against best practices and security standards. Use when reviewing security policies, checking for misconfigur... | |
| prisma-config Generate Prisma Access configurations for Strata Cloud Manager (SCM). Use when creating security policies, NAT rules, decryption policies, URL filtering prof... | |
| prisma-migrate Migrate Prisma Access configurations between different SCM tenants (TSGs). Use when moving security policies, NAT rules, address objects, and other configura... | |
| prisma-troubleshoot Troubleshoot Prisma Access issues including GlobalProtect connectivity, policy matching, tunnel status, SCM API errors, and configuration push failures. Use... | |
| leesen86-news 加密快讯抓取与筛选技能。使用当需要：(1) 从 BlockBeats 拉取快讯数据，(2) 按关键词筛选多条资讯，(3) 输出去 HTML 标签且时间已格式化的 JSON，用于后续自动化处理。 |
47,451–47,500 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.