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 |
|---|---|
| AirShelf Agentic Commerce Platform Search, compare, and buy products from verified merchants. Returns structured product data with Decision Packs (pros, cons, best_for, allergens, verified pricing) instead of raw web scraping. No CAPTCHAs, no auth required. ~980 products acr | |
| Gift Genius Location-aware Valentine's Day gift finder. Routes US users to premium flowers (UrbanStems), Singapore users to wellness supplements (Avea Life). Returns curated picks with Decision Packs — no decision fatigue, just 2-3 perfect options. | |
| Apple Notes Formatting Use when the user wants to beautify, restructure, or rewrite content into an Apple Notes-friendly note, especially article summaries, knowledge cards, topic... | |
| SF Business Data Export Export Salesforce business data into business-readable Excel files from natural-language requests. Use when pull large Salesforce datasets beyond Report limi... | |
| Ecm Perchance Image Generates images from text prompts using Perchance.org API with options for orientation and multiple image support. | |
| 尤里改 Facebook Graph API 代理服务使用指南 尤里改 Facebook Graph API 代理服务使用指南 | |
| H1B Sponsor Finder Find H1B / H-1B sponsor companies, visa sponsorship employers, and sponsor history for US jobs. | |
| X Article Reader Read X (Twitter) Articles aloud using macOS text-to-speech. Accepts an X Article URL and reads the content out loud. Automatically detects Chinese vs English... | |
| Code Refactor For Reproducibility Use when refactoring research code for publication, adding documentation to existing analysis scripts, creating reproducible computational workflows, or prep... | |
| In Silico Perturbation Oracle Virtual gene knockout simulation using foundation models to predict transcriptional changes | |
| Lay Summary Gen Converts complex medical abstracts into plain language summaries for patients, caregivers, and the general public. Ensures readability while maintaining scie... | |
| Protocol Deviation Classifier Determine whether an incident in a clinical trial is a "major deviation" or "minor deviation". Function: Automatically classify protocol deviations in clinic... | |
| Response Tone Polisher Polishes response letters by transforming defensive or harsh language into professional, courteous academic prose. Converts phrases like "I will not correct... | |
| 微信公众号媒体下载器 WeChat Media Downloader 下载微信公众号文章（mp.weixin.qq.com）中的视频、音频和音乐卡片。适用于：用户想把公众号文章里的 1 个或多个视频、多个音频/音乐保存到本地；直接抓取被微信“环境异常/去验证”拦截；需要通过可见 Chrome + 人工验证 + 远程调试抓取真实媒体地址，再自动下载、提取标题、重命名并整理输出。优先用... | |
| notion-clipper-skill Clip web pages to Notion. Fetches any URL via Chrome CDP, converts HTML to Markdown, then to Notion blocks, and saves to user-specified Notion database or page. Use when user wants to save/clip a webpage to Notion, or mentions "clip to noti | |
| Capcut Mate Skill Automate CapCut video editing by creating projects, adding videos, and rendering final videos via the CapCut Mate API. | |
| Media Crawler 基于 MediaCrawler 的多平台公开信息采集工具，支持安装、命令行运行、WebUI、结果定位与常用任务模板。 | |
| S.H.I.T底刊摘要 Automates extraction and AI-based analysis of research papers from shitjournal.org, capturing titles, abstracts, DOIs, and publication dates in JSON format. | |
| bilibili-search bilibili 内容抓取(搜索/UP 主空间/视频详情/评论)。统一走 agent-browser,自动复用 buvid cookie + wbi 签名环境。无需登录即可抓大部分公开数据。 | |
| bilibili-universal bilibili 内容抓取(搜索/UP 主空间/视频详情/评论)。统一走 agent-browser,自动复用 buvid cookie + wbi 签名环境。无需登录即可抓大部分公开数据。 | |
| Douyin Search 抖音内容抓取(搜索视频/用户/拿作品/看评论)。HTTP API 拿基础数据,agent-browser 抓评论虚拟滚动 harvest(需登录 cookie)。零依赖、跨设备、支持最低风控的人类模式。只读 skill,不修改 douyin 任何数据。 | |
| Xiaohongshu Search 小红书内容抓取(搜索/读笔记/看用户)。统一走 agent-browser(官方 JS 环境 + X-s 签名自动处理)。需注入登录 cookie。 | |
| Xiaohongshu Search 小红书内容抓取(搜索/读笔记/看用户)。统一走 agent-browser(官方 JS 环境 + X-s 签名自动处理)。需注入登录 cookie。 | |
| Zhihu Search 知乎内容抓取（搜索/读问答/抓专栏/看评论/看热榜）。默认走 API 路径 (`zhihu-fetch.py`)，仅单篇专栏正文走 SPA HTML 解析（不渲染浏览器）。前置：注入 cookie 到 `$SKILL/data/cookies.txt`。 | |
| exceldashboard-report Pair MCP with the report Skill: your Agent analyzes and verifies Excel or CSV data, then MCP creates visual reports, tracks progress, and returns live previews. Editing and PowerPoint export take place in the website editor. | |
| AgentBench Benchmark your OpenClaw agent across 40 real-world tasks. Tests file creation, research, data analysis, multi-step workflows, memory, error handling, and too... | |
| Moodle Web Services Skill Integrar con Moodle 4.x usando Web Services REST. Usar esta skill cuando el usuario pida crear cursos, inscribir o desinscribir usuarios, crear o actualizar... | |
| Moodle Web Services Skill Integrate with Moodle 4.x via REST Web Services to create courses, manage enrollments, activities, grades, and list courses or students. | |
| Causal Abel Use when the user wants an Abel causal read on what drives a market, company, asset, sector, or macro node, how two nodes connect, what changes under interve... | |
| Prefect Flow Builder Build, modify, and review Prefect-based offline orchestration in this repository. Use when adding a new Prefect flow, wrapping an existing offline computatio... | |
| BO-OpenSearch 普适网页搜索。当用户说"搜索"、"查一下"、"查查"、"search"或发起信息查询时，接收用户查询，抓取真实网页内容，按相关性排序，剔除广告与噪音，只返回有价值的信息。 | |
| Agent Long-Term Memory Three-tier long-term memory for AI agents — short-term + entity + episodic. 三层长期记忆架构：短期记忆 + 实体画像 + 情景记忆。跨项目共享用户画像，让 AI 真正记住你。 | |
| File Splitter Split large files into smaller chunks with semantic boundary detection. Supports JSON, Markdown, and TXT formats. Preserves data integrity by splitting at na... | |
| InfoSeek Deep web information search and archival skill for comprehensive research on persons, organizations, or products. Uses multiple search engines (Baidu, Tavily... | |
| Koen A quality social network for AI agents. Post, reply, like, reblog, and follow other agents. Use when interacting with Koen, posting to the agent network, checking the feed, or engaging with other AI agents on koen.social. | |
| Cloudflare Image Generation Generate images using Cloudflare Workers AI flux-1-schnell model. Use when user requests image generation with text-to-image using Cloudflare Workers API. | |
| design pick Generates multi-themed food collages (Viral Cakes, Street Food, Smoothie Bowls, Coffee Art, Fusion Tacos). Use when user asks for a collage of specific food... | |
| design pick2 Generates multi-themed food collages (Viral Cakes, Street Food, Smoothie Bowls, Coffee Art, Fusion Tacos). Use when user asks for a collage of specific food... | |
| pick your Generates multi-themed food collages (Burgers, Pizzas, Sushi, Salads, Desserts) with circle-masked images. Use when user asks for a collage of specific food... | |
| video-knowledge-ingest Ingest and summarize cross-platform videos into a local knowledge base. Use when working with YouTube, Bilibili, Xiaohongshu, or local media/subtitle files a... | |
| Briefing Diario Fornece um dashboard visual para informações do dia a dia como localização, clima, economia, previsão do tempo. Use sempre que o usuário pedir "briefing diár... | |
| 分析代码 快速分析方法流程、数据库表名及服务调用引用关系 | |
| 代码单元测试 Compare branch diff and simulate unit-test cases. | |
| 代码引用 从用户指定的 Java 方法向上追溯调用方，生成调用图直到 HTTP 接口或 RPC 方法等入口尽头。搜索范围限于当前 Git 仓库，不跨服务。Use when the user asks for caller graph, upstream call chain, who calls this method, 代码引用, 引用方, 调用图, or 向上追溯. | |
| 导出接口Postman文件 Export an HTTP API endpoint from the current work project into a Postman-importable collection JSON file. Use when the user asks in Chinese or English to exp... | |
| 剪辑视频 Create mixed-cut promotional videos for art supplies, drawing tools, sketching lessons, or painting material clips. Use when the user provides one or more ar... | |
| 测试环境 MySQL Connect to test-environment MySQL databases for troubleshooting, data verification, schema inspection, and controlled validation queries. Use when the user a... | |
| zzr-testUpload-skill DEV 测试环境服务器日志搜索与分析工具。当用户需要搜索测试环境日志、查找错误、 排查测试环境问题、查询 traceId/requestId/订单号/请求记录、或者说"帮我查一下测试日志"、 "查 dev 日志"、"看看测试环境有没有"、"grep 一下测试服"时，必须使用此 skill。 校验、生单、支付、申请出票等交易场景，按采购侧→平台侧→供应侧→order 分层搜索，且必须并行查询。 平台侧判断为供应底层请求/响应问题时，Agent 必须自动继续查供应侧日志（禁止询问 | |
| defuddle-web-cleaner Extract and clean readable article content, metadata, and markdown from URLs or HTML for research, note taking, and web scraping. | |
| icp-exemption-skill 生成 Apple 国区 ICP 豁免申请附件 PDF。当用户提到 ICP 备案、Apple 国区下架、ICP 豁免申请、App Store 中国区合规、申请例外批准等相关内容时，立即触发此 skill。收集用户的 Team ID、账户持有人姓名、App ID 等信息，调用脚本生成符合 Apple 要求的正式申请附... |
29,651–29,700 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.