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 |
|---|---|
| 债务协商话术生成器 输入债务类型、金额、逾期情况，自动生成信用卡分期话术、网贷减免策略、催收应对话术。覆盖信用卡、网贷、平台协商三大场景。本地运行，安全合规。 | |
| 追加被执行人申请书生成器 输入被执行公司名+债务金额，自动检索可追加的股东名单，生成标准格式《追加被执行人申请书》。覆盖3类追索对象，附带最高法判例引用模板。本地安全运行。 | |
| 高考志愿填报参谋 高考志愿填报AI参谋，AI初筛+数据查询+风险评估+真人级建议，全国31省市录取数据 | |
| 法律文书生成器 多版本法律文书模板生成服务，6大类53种法律文书一键AI智能生成。覆盖婚姻家庭（离婚协议书、离婚起诉状、财产分割协议、抚养权变更、婚前财产协议、赡养协议、遗产分割等10项）、劳动争议（劳动合同、劳动仲裁申请书、离职证明、竞业限制协议、保密协议、解除合同协议等12项）、债务纠纷（借款合同、催收律师函、还款协议、债权转让、债务和解协议、担保合同、欠条模板等8项）、民事商务（买卖合同、投资协议、合作协议、股权转让、合伙协议、委托合同、和解协议等15项）、房产交易（房屋买卖合同、租赁 | |
| 法律检索助手 根据用户描述的法律问题，自动检索相关法规、司法解释、典型案例和操作指南。覆盖债务纠纷、劳动争议、合同纠纷三大场景。安全本地检索，数据不出本地。 | |
| 婚姻法律咨询助手 提供基于最新法规的中国婚姻家庭法律咨询，涵盖离婚流程、财产分割、抚养权、家暴保护及过错赔偿等问题。本地安全运行。 | |
| 2 催收骚扰应对话术 根据骚扰场景描述，自动生成合法合规的应对话术、警告短信和投诉方案。覆盖催收骚扰、信用卡协商、网贷逾期、征信修复等场景。安全本地运行，合规保护。 | |
| Safe Self Improving A privacy-first, consent-based self-improvement skill for AI agents. Captures learnings, errors, best practices with auto-sanitization and duplicate detectio... | |
| Interbank Funding Trader Apply a distilled China interbank CNY funding trader workflow, especially from an asset-management/fund pledged-repo trader perspective, for money-market ana... | |
| BasicOps MCP Operator Operate BasicOps through an available BasicOps MCP server. Use when the user wants to read from or update BasicOps tasks, projects, notes, messages, assignments, statuses, subtasks, reviews, or related work in an MCP-capable environment. Tr | |
| BasicOps MCP Setup Install, configure, authenticate, or verify a BasicOps MCP connection in an MCP-capable environment. Use when the user wants to add BasicOps MCP, when a BasicOps operator skill reports that BasicOps MCP is missing or unauthorized, or when t | |
| Seedance 2.0 Al Video Generator Generates video via Loova Seedance 2.0 API (Seedance 2.0 video). Requires LOOVA_API_KEY from .env or environment (get API key at loova.ai). Use when the user... | |
| LeetCode Mock Interviewer Conduct realistic LeetCode-style mock coding interviews. Simulates a real technical interviewer who asks one problem at a time, forces the candidate to verba... | |
| OpenClaw自动备份工具_auto-backup-openclaw-user-data OpenClaw 用户数据自动备份技能。支持全量/选择性备份、定时执行、ZIP 压缩、日志记录、消息通知和保留策略管理。 **触发场景**： (1) 用户要求备份 OpenClaw 数据 (2) 用户要求设置定时备份 (3) 用户询问备份配置、状态、日志 (4) 用户执行 /backup_now、/backup_... | |
| Context Monitor 「macOS」常驻菜单栏的上下文显示器 · Menu bar context monitor for OpenClaw agents. | |
| Openclaw Odoo Skill Build or use the Odoo ERP connector for OpenClaw (Sales, CRM, Purchase, Inventory, Projects, HR, Fleet, Manufacturing integration via XML-RPC). | |
| 胖叔 Skill 安全审查 Security vetting for agent skills before installation. Scans skill code for dangerous Bash commands, sensitive file access, network exfiltration, obfuscated... | |
| Agent Estimation Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead of human time. Use when asked to estimate, scope,... | |
| Ai Daily Fetches AI news from smol.ai RSS. Use when user asks about AI news or daily tech updates. | |
| Fs Street Fetches articles from Farnam Street RSS. Use when asking about decision-making, mental models, learning, or wisdom from Farnam Street blog. | |
| Github Topics Fetches GitHub topic trending repositories. Use when asking about GitHub trending repos or open source projects. | |
| Trending Skills Fetches skills.sh trending rankings. Use when asking about skill rankings or popular tools. | |
| X Tweet Fetcher Fetch full tweets, long tweets, quoted tweets, and X Articles from X/Twitter without login or API keys, using no dependencies and zero configuration. | |
| Windows Automation Automate Windows desktop by simulating mouse/keyboard input, managing clipboard, capturing screenshots, running commands, and launching apps. | |
| 灵光爸爸（AuraBaba）Skill Project management and multi-agent work coordination through AuraBaba. Use whenever a user asks to assign or delegate tasks (分配任务/派活), create or advance a pr... | |
| AuraBaba Platform Project management and multi-agent work coordination through AuraBaba. Use whenever a user asks to assign or delegate tasks (分配任务/派活), create or advance a pr... | |
| 快速创建AI智能体虚拟公司 快速搭建智能体虚拟公司。当用户表达创建公司、组建团队、搭建组织架构、当老板、当企业家、招人、分工、合作、等意图时，自动激活此Skill。 触发场景：用户想要创建公司、开公司、新公司、AI公司、人工智能公司、智能体公司、虚拟公司；组建团队、建团队、新建团队、我的团队； 搭建组织、搭建架构、公司架构；或提及多智能体协... | |
| Easy Search Simple web search using multiple search engines with no API key required. Supports Google, Bing, DuckDuckGo, Baidu, Sogou, 360, Brave, Yandex. Features time... | |
| Openclaw Security Toolkit Security guard for OpenClaw users. Audit configs, scan secrets, manage access, and generate security reports. | |
| spec72-intake Use when a buyer just paid Spec72 (Lint/Catalog/Audit/Sprint) or needs the post-pay intake fields for https://spec72.dev/thanks/. Collect pack, repo URL, what breaks, handoff owner, email, tx/receipt — then point humans to Gumroad SKUs. Fre | |
| XRPL x402 Handoff Use when the user asks to wire XRPL x402 pay-per-call or prepaid credits, hand off a stuck 402/settle flow to a human, draft an agent SOP for Ripple/t54-style facilitators, or package last-mile docs for XRPL agent payments without building | |
| Weekly SEO Health Audit Weekly SEO health audit — a free, read-only pass that surfaces the highest-leverage SEO opportunities for a site right now: quick-win keywords (positions 4-20), low-effort fixes (metadata duplicates, missing H1s, broken internal targets, mi | |
| VoooAI - AI Multimedia NL2Workflow Platform Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generati... | |
| GitHub Analyzer GitHub 项目分析工具 - 技术栈识别、许可证合规评估、部署方案建议。Analyze GitHub repos for tech stack, license compliance, and deployment options. 用途：商业使用合规检查、技术选型调研、开源依赖尽调。 | |
| fund-analyzer 提供基金净值查询、历史走势、基金筛选排行、持仓分析等功能，数据来源于支付宝基金页面。用于用户查询基金信息、分析基金表现、筛选优质基金等场景。 | |
| Bupt Empty Classroom Query empty classrooms at BUPT (Beijing University of Posts and Telecommunications) Xitucheng campus. Use when the user needs to find available/empty classro... | |
| QQBot Message Format 将面向 QQ / QQBot 的最终回复整理成简洁、适合 QQ 聊天界面阅读的中文消息：结论先行、采用 QQ 安全的两级标题、主列表保持扁平、把嵌套结构改写成 QQ 友好格式，并克制地使用加粗和功能性 emoji。适用于任务完成通知、排障说明、状态更新、调试结论或一般答复，尤其在原始输出太朴素、太像文档、或结构不... | |
| WeChat Article Fetcher 抓取微信公众号文章内容。当用户发送微信公众号文章链接（mp.weixin.qq.com）时自动触发，将文章内容提取为可读文本。无需API密钥。 | |
| dy-video-to-text Extract speech-to-text from Douyin (TikTok China) videos, get watermark-free download links, and download videos. Use when user shares a Douyin link, asks to... | |
| Use HL Names API Consult & operate against the Hyperliquid Names API. Use when your agent needs to resolve `.hl` names, reverse-resolve addresses, fetch HLN profiles or recor... | |
| v0-cli Command-line tool for creating, refining, and listing AI-generated websites using v0.dev API without interactive prompts. | |
| crawl Crawl any JavaScript-rendered webpage through distributed real Chrome browsers. No local browser needed — perfect for headless VPS. | |
| An OpenClaw skill for AI-powered multimedia generation (image, video, audio, 3D) via 170+ RunningHub API endpoints — zero dependencies, pure Python. Generate images, videos, audio, and 3D models via RunningHub API (170+ endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId... | |
| csv-schema-profiler Profile a CSV paste: headers, null-ish rates, example values, and suspected types. Use when exploring an unfamiliar export before writing transforms. | |
| dependency-license-scanner Summarize declared licenses from a package manifest snippet. Use when checking OSS license risk before adding a dependency. | |
| dockerfile-best-practice-reviewer Review a Dockerfile for layer hygiene, least-privilege users, pin practices, and clearer build structure. Use when drafting or cleaning up container builds. | |
| git-bisect-coach Guide an interactive git bisect to find the commit that introduced a bug. Use when a regression appeared between two known commits or tags. | |
| git-commit-message-helper Suggest conventional-commit messages from a staged diff summary. Use when the user asks for a commit message after staging changes. | |
| git-repository-health-auditor Audits a user-selected Git repository for maintainability, configuration problems, dependency risks, accidental secret exposure, and CI/CD weaknesses. Produces an evidence-based report without modifying files by default. | |
| http-status-explainer Explain HTTP status codes in plain language and suggest safe next steps for clients and operators. Use when debugging APIs, browsers, or reverse proxies. |
36,101–36,150 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.