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 |
|---|---|
| conqueror-seo-project-setup Set up a durable local SEO workspace: working folder, site scope, goals, positioning, MCP and project check, and Search Console intake. Use at the start of a new SEO project. Requires a connected Conqueror MCP server. | |
| Words into Music Create complete original songs from ideas or your own lyrics with Words into Music, check generation progress, and find recordings in your connected private library. Supports vocals or instrumentals in English, Spanish, German, French and B | |
| Arxiv Watcher Fetch and monitor latest arXiv papers by category, generate summaries, and manage starred papers for easy reference. | |
| Finance Cron Schedule and manage cron tasks that run only on official trading days for US, China, and Hong Kong financial markets with automatic holiday sync. | |
| BTCD Skill (NBW) Run the BTCD collateralization flow on PGP chain. Use when the user asks to run a BTCD loan, collateralization flow, create/take orders, lock BTC, submit pro... | |
| Stablecoin & AI Agent Economy Knowledge Base Comprehensive knowledge base on stablecoins, AI agent economics, and the NBW (New Bretton Woods) protocol, based on the book "稳定币：AI智能体经济的未来探索" by Han Feng (... | |
| nasal-doc Generates and verifies inline documentation and type annotations for Nasal, enhancing code readability and developer accuracy. | |
| nasal-language-basic Provides the variables, data types, syntax, classes and objects, as well as the usage of basic built-in functions of the Nasal language. | |
| nasal-library-base Explains the Nasal base libraries, including `clipboard`, `math`, `string`, `utf8` and some built-in functions. | |
| nasal-library-debug Provides the usage of the debug library of the Nasal language. | |
| nasal-language-file-system Explains the input/output (IO) file handling, property serialization, and directory-path manipulation methods in Nasal, combining raw stream operations ('io') with high-level path parsing wrappers ('os.path'). | |
| nasal-library-props Explains the Nasal property tree library (`props`), including property node wrapper instantiation, path navigation, attribute controls, direct data binding utilities, and tree condition evaluation. | |
| propertylist-xml Provides usage details for PropertyList XML files, including property storage, expressions, conditions, and more. | |
| yasim-xml Provide a detailed specification for writing YASim XML files. | |
| ContentStudio ContentStudio is a tool to schedule social-media posts, manage the social inbox, and pull performance analytics across Facebook, LinkedIn, Twitter/X, Instagram, YouTube, TikTok, Pinterest, Threads, Tumblr, Bluesky, and Google Business Profi | |
| Context.dev Use Context.dev for live web search, page scraping, crawling, structured extraction, document parsing, screenshots, brand intelligence, design systems, industry classification, monitors, and asynchronous batches. Trigger when a user needs c | |
| contracko Connects Contracko over MCP and organises contracts, types, parties, and folders. Use for onboarding, filing, workspace structure, or whenever Contracko comes up. | |
| contracko-create Takes a new contract from questionnaire to drafted, signed and filed in Contracko. Use to create, draft or generate an agreement, fill a template, send for signature, or chase a signer. | |
| contracko-import Imports contracts into Contracko from disk, Google Drive, SharePoint, Box or a URL. Use to onboard, migrate, bulk-upload, or file a signed PDF. | |
| contracko-review Reviews Contracko contracts. Use for notice dates, end dates, annual review, reminders, risk audits, comparing proposals or redlines, or portfolio priorities and gaps. | |
| AetherLang Execute AI workflow orchestration flows using the AetherLang Ω DSL. Run multi-step AI pipelines for recipes, business strategy, market analysis, molecular ga... | |
| AetherLang Chef V3 Michelin-grade AI culinary intelligence. 17 mandatory sections covering food cost, HACCP, thermal curves, allergen matrix, wine pairing, plating blueprint an... | |
| AetherLang V3 for Claude Code Execute AetherLang V3 AI workflows from Claude Code using nine specialized engines for culinary, business, research, marketing, and strategic analyses. | |
| Aetherlang Karpathy Skill API connector for AetherLang Omega — execute 10 Karpathy-inspired agent node types (plan, code_interpreter, critique, router, ensemble, memory, tool, loop, t... | |
| AetherLang Strategy V3 Nobel-level strategic business intelligence with game theory, Monte Carlo simulations, market analysis, and implementation roadmaps. | |
| ARCHITECT: Autonomous Goal Execution for AI Agents Transforms your OpenClaw agent from a reactive question-answerer into a proactive autonomous executor. ARCHITECT takes any high-level goal, decomposes it int... | |
| MEMORIA: Persistent Memory Layer for AI Agents Gives your OpenClaw agent persistent memory across every session. MEMORIA maintains a structured knowledge layer: who you are, what you're building, every de... | |
| AGENT-OS The operating system layer for AI agents. Routes goals to the right skills. Executes with checkpoints. | |
| APEX-AGENT: Cognitive Upgrade for AI Agents Transforms your OpenClaw agent with the APEX cognitive framework — a battle-tested thinking system built by a solo founder over 10 months of AI product devel... | |
| Apex Crypto Intelligence AI-powered multi-exchange crypto market analysis, arbitrage detection, and hedge fund-quality trading reports using live data from major exchanges. | |
| APEX STACK for Claude Code: Complete Autonomous Developer Agent The complete autonomous agent stack for Claude Code — APEX cognitive framework, MEMORIA persistent memory, and ARCHITECT goal execution engine — bundled into... | |
| MasterSwarm AI Document Analysis Analyze any document with 15 parallel AI engines via the MasterSwarm cloud API. Upload receipts, contracts, lab results, or ask business/crypto/legal questio... | |
| NAVIGATOR For everyone who's ever pasted a command and hoped for the best. Navigator reads what you just did, tells you if it worked correctly, finds the one gap slowi... | |
| NOUS Not an assistant. A thinking engine that makes its own cognition visible and lets you steer it in real time. Five movements. Four modes. | |
| Skills Execute AI workflow orchestration flows using the AetherLang Ω DSL. Run multi-step AI pipelines for recipes, business strategy, market analysis, molecular ga... | |
| Ask First, Log Everything - Contro1 Approvals How to ask a human before a sensitive action and how to log every autonomous action, so your work is accountable. Read this before any action that spends money, changes access, deploys, deletes data, sends a message on the user's behalf, or | |
| 原型设计技能 通用页面原型设计技能。基于 58种设计风格（默认Figma 风格） UI 的复杂业务系统 HTML 原型开发， 包括标准页面结构、统计卡片、筛选条件、数据表格、弹窗设计。 适用场景：(1) 创建新的管理页面原型 (2) 对照业务文档实现功能模块 (3) 设计弹窗和详情页 (4) 构建带看板和列表视图的页面。 **... | |
| A-stock-report A股数据驱动型报告自动生成与推送系统，支持晨报 / 收盘小结 / 晚报 / 盘中预警 / IPO周报 / 财经周末版。内置投资者情绪打分（6维度，满分100）与AI后市展望。 | |
| IMA Wiki 编译器 腾讯 IMA Wiki 编译——将原始资料系统化组织为结构清晰的Wiki知识体系，并支持标签体系管理与按文件夹层级结构归类。当用户说"建知识库""整理资料库""编译知识库""搭建wiki""知识体系化""把资料整理成wiki""给知识库打标签""按标签分类""标签整理""按文件夹归类""整理散落文件"时触发。不适用于单篇摘要、简单问答、或仅搜索已有知识库内容的场景。 | |
| 知识库 Wiki 编译器 腾讯 IMA 知识库 Wiki 编译——将原始资料系统化组织为结构清晰的Wiki知识体系，并支持标签体系管理与按文件夹层级结构归类。当用户说"建知识库""整理资料库""编译知识库""搭建wiki""知识体系化""把资料整理成wiki""给知识库打标签""按标签分类""标签整理""按文件夹归类""整理散落文件"时触发。不适用于单篇摘要、简单问答、或仅搜索已有知识库内容的场景。 | |
| skill-security-scanner-clean Security scanner for OpenClaw skills. Use when installing, updating, or auditing skills to detect malicious backdoors, suspicious code patterns, data exfiltr... | |
| Reply Wechat Message 微信AI助手 — 主动发消息 + 自动回复 / WeChat AI assistant — send messages & auto-reply | |
| 中国裁判文书案例检索（得理科技） 案例检索 Skill — 面向法律从业者及普通用户的裁判文书智能检索工具。当用户需要检索裁判案例、查找类案裁判规则、按案由/法院/时间筛选案例、或上传文件进行案例匹配时使用。触发词包括："查一下XX的案例"、"找关于XX的判决"、"XX法院的判例"、"类案检索"、"有没有类似的案例"、"XX案由的裁判规则"等。 | |
| 中国裁判文书类案检索报告（得理科技） 类案检索报告生成 Skill — 面向律师、法官助理及法务人员的类案检索全流程自动化工具。基于待决案件信息，通过调用得理案例检索 API 完成案件拆解、检索执行、类案筛选、比对分析与规则提炼，最终输出一份可直接向法院提交或供内部策略研判使用的标准化《类案检索报告》。当用户提出以下需求时触发：帮我检索一下类似案例、查一下这个案由的类案、做一个类案检索报告、法院对这类问题怎么判的、有没有支持我方观点的判决、找几个和本案类似的生效判决、我要向法院提交类案检索报告、类案检索、裁判观点 | |
| 文件OCR解析 当用户需要将扫描版 PDF、图片、OFD、票据、合同扫描件、法院文书扫描件或其他 Agent 无法直接读取的文件解析为文本/Markdown 时使用。适用于 OCR 识别、扫描件识别、图片转文字、图片转 Markdown、PDF 转 Markdown、文件解析失败、文档无法读取、提取结果为空、乱码、扫描版文件解析不了、agent 解析不了文件、平台无法解析文件、需要调用得理 OCR 接口等场景。优先使用当前 Agent/平台原生解析能力；只有原生解析失败、结果明显不可用，或用 | |
| 劳动法费用计算器 劳动法费用计算路由技能。根据用户问题自动分发到子技能：补偿金/赔偿金计算、加班工资计算、未休年休假补偿计算、工伤赔偿计算。当用户询问离职补偿、加班费、年假折算、工伤赔偿等劳动法相关费用计算时触发。 | |
| 中国法律法规检索（得理科技） 法规检索 Skill — 面向法律从业者及普通用户的法规智能检索工具。当用户需要查询法律条款、查找相关法规、核实法规时效性、对比法规差异时使用。触发词包括："查一下第X条"、"找关于XX的法规"、"这个法规还有效吗"、"对比XX法和XX法"等。 | |
| 诉讼费计算 用于计算中国法院诉讼费、案件受理费和申请费，依据《诉讼费用交纳办法》（国务院令第481号）第十三条、第十四条。用户询问或比较财产案件、离婚案件、人格权案件、知识产权民事案件、劳动争议、行政案件、管辖权异议、申请执行、财产保全、支付令、公示催告、撤销仲裁裁决、认定仲裁协议效力、破产申请、海事申请费等费用时使用。典型触发词包括：“计算诉讼费”“诉讼费怎么算”“起诉要交多少钱”“案件受理费”“申请执行费”“保全费”“支付令费用”“公示催告费”“破产申请费”“海事申请费”。兼容英文检 | |
| 案件评估报告（得理科技） 生成中国大陆争议解决与诉讼管理场景下的《案件初步评估报告》，适用于接案评估阶段对案件基本事实、初步证据材料、我方诉求和管辖法院信息进行结构化梳理、法律关系识别、风险标注、司法裁判检索，并量化估算胜诉概率、诉讼周期、资金与时间成本。当用户提到接案评估、案件初评、是否接案、胜诉率预估、诉讼周期预估、办案成本测算、争议... | |
| 诉讼策略与类案检索（得理科技） 自动生成中国诉讼案件的《诉讼策略与类案检索报告》，基于案情拆解争议焦点并编排法条/类案检索工具，当用户提到案件分析、诉讼策略、类案检索、法条检索或庭前准备时使用本 Skill。 |
22,401–22,450 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.