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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| File Organizer Intelligently organize files and folders — analyze structure, find duplicates, suggest layouts, and clean up — with strict safety guardrails. Use when the user asks to organize/downloads, find duplicates, clean up files, sort photos by date | |
| markitdown Convert documents to Markdown (PDF, Word, Excel, PowerPoint, HTML, CSV, images OCR, audio) with Microsoft MarkItDown for AI/RAG ingestion. Use when the user asks to convert files to markdown, extract document content, read or parse PDF/Word | |
| skill-builder 制作、修改、优化或审查 Skill 的通用技能，跨平台、不绑定特定 AI 生态。当用户想「把重复工作流/想法做成 skill」「帮我做个 skill」「优化/审查一个 skill」「这个 skill 触发不了帮我看看」，或提到 skill 制作、skill 优化、skill 评分时使用。即使对方没有明确说「skill」这个词，只要在描述一个想固化下来的重复流程，也主动使用本技能。Build, modify, optimize, or review skills; use wh | |
| Skill Reviewer 审查一个 Skill 并自动打分。当用户想「审查/评审一个 skill」「给 skill 打分」「这个 skill 能参赛吗」「帮我看看这个 skill 有什么问题」，或提供一个 Skill 包目录、SKILL.md 文件、或粘贴 SKILL.md 内容让你评估时使用。即使对方没有说「审查」二字，只要在让评估一个 skill 的质量，也主动使用本技能。Review a skill and score it automatically; use when the user wa | |
| tdd Test-driven development. Use when building a feature or fixing a bug test-first, when the user mentions "red-green-refactor", "TDD", or asks for tests before code. Enforces the iron law "no production code without a failing test first" with | |
| text-patterns Process text through curated content patterns for summarization, extraction, analysis, writing, and review. Use when the user asks to summarize, extract insights/wisdom/ideas, analyze claims/prose/paper, improve writing, clean text, or appl | |
| Commit Reviewer（提交修复检查） 根据一个或多个 git 修订号和需求描述，检查提交是否真正修复了对应 bug，并给出逐条结论 | |
| Playwright 网页自动化工具 使用 Playwright 对本地网页、静态 HTML 或在线页面执行自动化测试、元素发现、控制台日志采集与截图。 | |
| Tabbit Agent Browser Use Tabbit with agent-browser by reading Tabbit's live DevToolsActivePort file, deriving the browser wsEndpoint, and routing browser actions through agent-br... | |
| Banking Ontology Coach 更新版 以教练的方式，一步步引导新手咨询顾问亲手完成"银行业务领域"的知识工程式本体建模，全程对标行业参照标准 FIBO（Financial Industry Business Ontology），并陪着他搭出一份"概念+定义+关系+FIBO对标"的结构化文档。严格服务于银行/金融业务咨询场景。当用户表示想学习或练习银行... | |
| Banking Ontology Coach V2 以"协作交付"的方式，和新手咨询顾问一起做出银行业务领域的知识工程式本体建模成果，全程对标行业参照标准 FIBO（Financial Industry Business Ontology），产出一份"概念+定义+关系+FIBO对标"的结构化本体文档，并在协作中提升用户能力。严格服务于银行/金融业务咨询场景。当用户... | |
| OpenClaw Voice Control Local macOS voice-control integration for OpenClaw. Use when setting up, deploying, troubleshooting, or operating wakeword-triggered voice access to a local... | |
| feishu-doc-skill 当用户提供飞书 wiki、docx、知识库页面链接，并希望读取、总结、比对、抽取内容、把结果写回飞书文档，或把本地图片插入飞书文档时使用。这个技能会先从链接中提取文档标识，优先通过飞书 OpenAPI 读取正文；做需求分析时优先输出 Markdown，调试接口结构时再输出 JSON。 | |
| 自动周报助手 自动整理周报工具。支持从多个数据源（GitHub、飞书文档、日历）汇总工作内容，生成Markdown周报。支持保存历史、AI摘要、导出PDF/HTML、发送邮件、写入飞书文档。适用于需要定期总结工作成果的用户。 | |
| CarsXE Access the full suite of CarsXE vehicle data APIs — VIN decoding, license plate lookup, market value, vehicle history, safety recalls (VIN, year/make/model, or batch), lien/theft checks, OBD-II diagnostic code decoding, vehicle images, inte | |
| Base toolbox Check and simulate Uniswap v3 swaps on Base pre-signature with accurate allowance, gas, token prices, and ENS resolution for safe execution. | |
| BottyFans - OnlyFans for Bots BottyFans agent skill for autonomous creator monetization. Lets AI agents register, build a profile, publish posts (public, subscriber-only, or pay-to-unlock), upload media, accept USDC subscriptions and tips on Base, send and receive DMs, | |
| Ethereum History Read-only factual data about historical Ethereum mainnet contracts. Use when the user asks about a specific contract address, early Ethereum contracts, deployment era, deployer, bytecode, decompiled code, or documented history (what a contr | |
| deyo Use only when the current user explicitly asks to use Deyo to transcribe explicitly provided URLs or exact local audio/video file paths, or explicitly asks for Deyo install, status, or troubleshooting. Do not trigger from a mere Deyo mentio | |
| vox Use only when the current user explicitly asks to use Vox to transcribe one URL written in the request or one exact local audio/video file path, or explicitly asks for Vox CLI or Vox Skill install, status, authentication, or troubleshooting | |
| orchards Join Orchards, build agent communities, collect digital certificates, and participate in direct-purchase commissions and eligible member distributions. Use for Orchards registration, social activity, Bitcoin account operations, purchase syn | |
| Institutional Tracker Ai AI链条机构建仓探测算法。基于Tushare结构化数据，通过5维信号评分体系（资金流+量价+筹码+北向+事件） 识别A股AI链条（算力/芯片/大模型/应用）机构建仓行为，生成买入信号（10日持有期、-15%止损）。 含市场环境判断（11指标）、外部情绪聚合（5源）、日内分钟线分析、大规模回测框架。 回测结果：54... | |
| Postwall Secure email gateway for AI agents - human-in-the-loop approval for reading and sending emails. Get your API key at https://postwallapp.com | |
| BOSS Recruit Assistant BOSS直聘招聘助手。处理"新招呼"收件箱：读候选人在线简历同步飞书多维表格，有附件简历则零弹窗下载并同步，没附件则主动发消息要简历。内置反风控节奏层（随机延时/批量上限/验证码熔断/权益耗尽诊断/防发错人）。当用户提到 Boss直聘招聘、处理新招呼、候选人简历同步飞书、批量打招呼要简历时使用。 | |
| Candidate Assessment Evaluates how well a candidate's resume matches a target job description (JD) and produces a clean, professional HTML assessment report. Parses the resume (v... | |
| Docx Builder 一套基于 docx npm 库的 Word 文档排版样式系统，用于生成带有专业配色、表格、标题层级的 .docx 文档。适用于 PRD、技术方案、项目汇报、会议纪要等结构化文档的模板输出。 | |
| memory-doctor Keep an LLM agent's long-term memory healthy — the cure for context rot. Use when a memory store exists and the user wants to check or tidy it ("记忆体检", "整理记忆... | |
| Mneme Maintain persistent cross-session agent memory in the Mneme plain-text format (.mneme files) — decisions, facts, preferences, gotchas, goals. Use when an .mn... | |
| PRD Creator Generate structured Product Requirement Documents (PRD) in Markdown format, with optional Word (.docx) export. Activate when user mentions "写PRD", "产品需求文档",... | |
| Resume Parsing Parses PDF/DOCX resumes (CV, 简历) into structured JSON Resume standard data using the pdfmuse deterministic extraction engine. Handles English and Chinese res... | |
| Skill Release Publish and manage Claude Code skills on ClawHub (clawhub.ai). Use when user wants to "publish skill", "update skill version", "release to clawhub", "clawhub... | |
| Toonany A Claude Code skill for creating AI-generated short dramas (漫剧) from novels and stories. Use when user mentions "漫剧创作", "小说转剧本", "分镜生成", "短剧制作", "故事线生成", "大纲... | |
| Brainstorm 引导梳理模糊想法，分三步完成需求澄清、方案对比和设计细化，适用于新功能规划和技术选型。 | |
| AI Company Builder Provides a complete AI-run company setup playbook, including memory system, safety rails, payment integration, and multi-platform launch in 72 hours. | |
| AI Memory System Automatically sets up a 3-layer memory system with long-term MEMORY.md, daily notes, and nightly fact extraction cron job. | |
| AI Safety Rails Automatically configures safety rules, trust levels, prompt injection defense, and approval workflows to secure OpenClaw agent actions. | |
| Launch Blitz Automatically formats, submits, and tracks your product launch across 21 major startup directories with tailored listings and status monitoring. | |
| NowPayments Integration Integrates NowPayments API to enable secure multi-cryptocurrency payments, IPN handling, and order tracking in AI-operated stores. | |
| Reel Digest Download, transcribe, extract frames, and deeply analyze any video or reel from URL (Instagram, YouTube, TikTok, X, direct MP4). Use when user shares a video... | |
| TalonForge AI CEO Persona (EN/AR) Transforms your AI into a bilingual (EN/AR) autonomous CEO managing operations, decisions, revenue, and market strategy with built-in safety and memory. | |
| God Mode — Autonomous AI Agent Loop by TalonForge Enables OpenClaw agents to autonomously execute prioritized tasks on a heartbeat loop with logging, auditing, error handling, and workspace hygiene. | |
| TalonForge Launch Blitz (EN/AR) Automates simultaneous submission and tracking of your product launch across 21 startup platforms with tailored listings and post-launch monitoring. | |
| TalonForge Memory System (EN/AR) Automatically sets up a 3-layer memory system with long-term MEMORY.md, daily notes, and nightly fact extraction for durable AI memory management. | |
| TalonForge Safety Rails (EN/AR) Automatically configures trust levels, non-negotiable safety rules, prompt injection defenses, and approval workflows for secure AI interactions. | |
| Skill Guard — Pre-Install Security Scanner Scan ClawHub skills for security vulnerabilities BEFORE installing. Use when installing new skills from ClawHub to detect prompt injections, malware payloads... | |
| Workspace Hygiene — Auto-Clean for AI Agents Automatically enforces workspace file size limits, archives stale or bloated files, and organizes root contents to maintain efficient AI agent context. | |
| Feishu File Manager 飞书云盘文件管理技能。用于读取、下载和管理飞书云盘中的文件。 当用户需要：访问飞书文件、下载文档、读取PDF/Word/PPT文件、分析飞书云盘内容时使用。 核心方法：使用 tenant_access_token 调用 Drive API 下载文件，解析内容返回给用户。 | |
| Agent DNA Portable agent identity encoding. Compress SOUL.md/MEMORY.md into transferable DNA fingerprints, detect identity drift between snapshots, and port personalit... | |
| AgentNet Agent-to-agent discovery network. Register agents with capability cards, discover peers by skill/domain, perform trust-scored handshakes, and run a FastAPI d... | |
| CompoundMind Experience distillation engine that turns raw daily memory logs into compounding intelligence. Extracts patterns, generates briefings, tracks growth metrics,... |
18,501–18,550 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.