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 |
|---|---|
| Forecast Valuation 专业财务预测与估值模型生成器。结合高盛 DCF 标准与 Wind Evaluator 框架，自动生成完整三表预测、DCF 估值、相对估值、敏感性分析和 Football Field 估值区间。 | |
| Global Financial Downloader 全球财报智能下载器 v2.2。自动识别市场（A 股/港股/美股），自动选择爬虫。港股使用东方财富+同花顺 API，无需认证。美股外国公司（ADR）自动使用 20-F/6-K 替代 10-K/10-Q。subprocess 替代 os.system，错误检查+输出捕获。支持 --dry-run 预览、下载后自动验证。 | |
| Hk Financial Downloader 港股公司财报完整下载器。自动从东方财富/同花顺/披露易获取年报、中期报告、季报、招股书，完整报告优先于业绩公告。 | |
| Playwright Ocr Automated web data extraction using Playwright for browser automation and OCR for text recognition. Use when you need to extract data from dynamic web pages,... | |
| ROIC 核心穿透分析工具 核心ROIC（投入资本回报率）深度分析助手。当用户提到 ROIC、投入资本回报率、资本效率、核心盈利能力、资本回报率分析、穿透ROIC、NOPAT、投入资本计算时自动使用。支持A股、港股、美股上市公司的ROIC精确计算。 | |
| Stock Research System 专业级股权研究自动化系统。支持首发覆盖报告（6,000-10,000字）和季报更新报告（3,000-5,000字）。触发词：股票研究、深度研究、首发覆盖、季报更新、DCF估值。 | |
| Transcript Analysis 从 Stock Analysis 或 QVeris API 抓取 earnings call transcript，进行主题信号挖掘，输出 evidence_ledger + theme_timeseries + summary_report。 触发词：分析业绩会、earnings call 分析、transcr... | |
| Web Article to Obsidian 网页文章一体化抓取存入Obsidian知识库。集成Playwright/Tavily/Firecrawl/Browser四种提取引擎，支持微信公众号/富途牛牛/雪球/通用网页，自动行业分类、导航清理、双层存储。统一替代wechat-article-extractor、wechat-mp-reader、articl... | |
| Young Post Downloader 自动下载 Young Post Club Spark 网站文章并生成 PDF。使用场景：用户要求下载 Today's Read 文章、获取 Young Post 内容、批量抓取教育文章、生成学习材料 PDF、上传飞书云空间。支持：自动解析文章列表、批量下载、HTML 排版、PDF 转换、飞书上传。 | |
| feishu paper manager Design or implement a paper-management workflow built on a Feishu bot plus OpenClaw. Use when the user wants to ingest papers from Feishu messages, save PDFs... | |
| MemoryAI Long-term memory for AI agents. Your AI remembers everything — preferences, decisions, context — across sessions, forever. | |
| cmaiot-basic-general-kit 查询并控制cmaiot平台上的产品和设备，并可获取视频设备的播放地址。cmaiot平台的正式名称是中国移动AIoT平台(iot.10086.cn)。连接需要的产品API Key和产品ID由cmaiot工具保存。目前只支持使用物模型的设备。 | |
| Verified Agent Identity New Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic... | |
| Verified Humanizer New Transform AI-generated content into natural, human-sounding writing, measure the improvement, and optionally verify the result. | |
| Auditoria Por Ejecucion Audita declaraciones de garantía ejecutando comandos y verificando códigos de salida para validar o refutar afirmaciones en código e informes. | |
| 茶不二 Xiaohongshu content operations expert for myopia prevention brands. Full-chain support: topic planning, copywriting (with 90-score upgrade), data review, competitor analysis, and business conversion. Bundled with AI-removal and copy-upgrade | |
| TimeMachine Create, list, and rollback incremental snapshots of OpenClaw configs and memory with optional auto-backups and retention policies. | |
| Jetlag Planner Scans your Google Calendar for upcoming flights and writes a personalized circadian adjustment plan back to your calendar. Trigger with phrases like "check m... | |
| Tech Trend Radar Use when generating current technology, AI model ranking, product, startup, funding, regulation, or market trend reports from recent industry updates | |
| Location Aware Backgrounds Generate and save location-aware background images by choosing a real place cue, using local time and weather, and rendering through `nano-banana-pro`. Use w... | |
| Order From Whole Foods Order groceries from Whole Foods using browser automation and a saved purchase policy | |
| Payout Possum Comprehensive money-recovery specialist for finding money, benefits, refunds, settlements, unclaimed property, pensions, bankruptcy funds, escrow balances, a... | |
| Appraisal Ai Drafts real estate appraisal reports from your project workfile. Produces Word narratives with tracked changes and Excel adjustment grids from your own maste... | |
| Deposition Bot Produces structured trial preparation reports from deposition transcripts. Generates a strategic memo, witness analysis, legal research summary, and a Word d... | |
| Aoju Memory Long-term memory, learning, and self-evolution for the agent. Activates on session start (SOUL.md/USER.md context), after significant decisions, on feedback,... | |
| Perplexity Sonar Search Perplexity Sonar search and answer generation through AIsa. Use when the task is specifically to call Perplexity Sonar, Sonar Pro, Sonar Reasoning Pro, or So... | |
| One API key for Chinese AI models. Route to Qwen, Deepseek China LLM Gateway - Unified interface for Chinese LLMs including Qwen, DeepSeek, GLM, Baichuan. OpenAI compatible, one API Key for all models. | |
| One API key for 70+ AI models. Route to GPT, Claude, Gemini, Grok and more Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Grok and more with a single API key. | |
| MarketPulse (Stocks + Crypto Data) Query real-time and historical financial data across equities and crypto—prices, market moves, metrics, and trends for analysis, alerts, and reporting. | |
| Unified API for powerful image and video generation Generate images & videos with AIsa. Gemini 3 Pro Image (image) + Qwen Wan 2.6 (video) via one API key. | |
| Prediction markets data - Polymarket, Kalshi markets, prices, positions, and trades Prediction markets data - Polymarket, Kalshi markets, prices, positions, and trades | |
| Find and analyze arbitrage opportunities across prediction markets like Polymarket and Kalshi Find and analyze arbitrage opportunities across prediction markets like Polymarket and Kalshi. | |
| Verified Research Engine (Web + Academic + Confidence Score) Intelligent search for agents. Multi-source retrieval across web, scholar, Tavily, and Perplexity Sonar models. | |
| X Twitter Command Center (Search + Post + Interact) Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts, likes/unlike... | |
| X Twitter Command Center (Search + Post) Searches and reads X (Twitter): profiles, timelines, mentions, followers, tweet search, trends, lists, communities, and Spaces. Publishes posts after the use... | |
| YouTube SERP Scout (Rank + Discover) YouTube SERP Scout for agents. Search top-ranking videos, channels, and trends for content research and competitor tracking. | |
| AgentRx AgentRx recovery layer for AI agent tool failures. Use this skill whenever any external tool call fails, returns an error, times out, or behaves unexpectedly... | |
| ChainAware Behavioral Prediction Use this skill whenever a user asks about wallet safety, fraud risk, rug pull detection, wallet behavior analysis, DeFi personalization, on-chain reputation scoring, AML checks, token ranking by holder quality, airdrop screening, lending | |
| agentkey PROACTIVELY use whenever the user needs data outside your training set or requires a live network call — web search, URL scraping, news, social media (any platform), market prices (crypto/stocks/FX), on-chain data, e-commerce product data, | |
| investor-search Name a country, get its verifiable investors: family offices, VCs, angels. Rejects advisers and lawyers. Every field is sourced, gaps stay empty. Nothing guessed. Stops on evidence. | |
| Investor Search for PicoClaw For PicoClaw. Install: picoclaw skills install --registry clawhub investor-search-picoclaw. Name a country, get its verifiable investors: family offices, VCs, angels. Rejects advisers and lawyers. Every field is sourced, gaps stay empty. No | |
| aaveclaw Aave V3 lending protocol on Base Sepolia testnet. Deposit WETH collateral, borrow USDC, repay loans, withdraw collateral, check health factor, and mint test tokens via faucet. Use when users want to interact with Aave lending, check their l | |
| BrainDB Persistent, semantic memory for AI agents. Gives your AI long-term recall that survives compaction and session resets — 98% accuracy, 20ms latency. | |
| Swarm Cut your LLM costs by 200x. Offload parallel, batch, and research work to Gemini Flash workers instead of burning your expensive primary model. | |
| WeChat macOS Proxy macOS 微信消息自动化工具。通过 GUI 自动化实现：发送消息给指定联系人、读取聊天内容、监控新消息。适用于需要自动化微信操作的场景，如定时发送、批量回复、消息备份等。依赖 peekaboo 进行屏幕截图和 UI 交互。仅支持 macOS。开源地址：https://github.com/chairmanmia... | |
| Folkmoot - AI agents debate and vote Public forum where AI agents debate proposals, vote with sealed ranked ballots and reach binding decisions; humans watch. Use to join, post or vote on Folkmoot, or for a second opinion from AI agents on other model families. Reading and ask | |
| Caldav Manage CalDAV calendars and events, with special support for Radicale server. Use when the user wants to create, update, delete, or query calendar events, ma... | |
| app-maker 自动完成从需求分析、页面设计、数据库建模、代码生成到可视化调试和一键部署的全栈应用开发全流程。 | |
| 🎵 抖音下载器 抖音无水印视频下载器，支持分享链接解析、批量下载和元数据保存 | |
| 视频字幕自动生成器——免费的才是最好的 自动提取视频音频，识别生成带时间戳的文字稿，输出SRT/VTT字幕及带字幕的视频，并智能提炼视频标题。 |
18,951–19,000 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.