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 |
|---|---|
| ai-trending-news Fetches, ranks, and summarizes the top 10 trending AI news stories from trusted editorial, official, research, and community sources. Use when the user asks... | |
| openclaw-backup-restore Backup or restore your entire OpenClaw setup including config, agents, skills, credentials, and workspace as a timestamped portable .tar.gz archive. | |
| github-trending Fetch top trending GitHub repositories today/this-week/this-month and summarize top 15 with stars, language, description. | |
| google trending Fetch and display the top trending Google searches in the last 24 hours for any country. Use when the user asks for Google trending topics, trending searches... | |
| wiki-craft Bootstrap and maintain a personal LLM Wiki — a persistent, compounding knowledge base of interlinked markdown pages that the LLM writes and maintains. Use wh... | |
| youtube trending Fetch and display the top trending YouTube videos globally or by country/category. Use when the user asks for trending YouTube videos, what's popular on YouT... | |
| Lumetra Engram Persistent, explainable memory for your OpenClaw agent — store facts and recall them later via the hosted Engram MCP server (by Lumetra). | |
| feishu-api-cache-fix | |
| CoinMarketCap Crypto APIs API reference for CoinMarketCap cryptocurrency endpoints including quotes, listings, OHLCV, trending, and categories. Use this skill whenever the user mentio... | |
| [Outdated] CoinMarketCap Onchain Data API reference for CoinMarketCap DEX endpoints including token lookup, pools, transactions, trending, and security analysis. Use this skill whenever the user... | |
| CoinMarketCap Exchange APIs API reference for CoinMarketCap exchange endpoints including exchange info, volume, market pairs, and assets. Use this skill whenever the user mentions excha... | |
| CoinMarketCap Market Overview APIs API reference for CoinMarketCap market-wide endpoints including global metrics, fear/greed, indices, trending topics, and charts. Use this skill whenever the... | |
| CoinMarketCap Onchain Data APIs API reference for CoinMarketCap DEX endpoints including token lookup, pools, transactions, trending, and security analysis. Use this skill whenever the user... | |
| CoinMarketCap MCP Fetches cryptocurrency market data, prices, technical analysis, news, and trends using the CoinMarketCap MCP. Use for ANY question involving cryptocurrencies... | |
| CoinMarketCap x402 APIs Access CoinMarketCap data via x402 pay-per-request protocol with USDC payments on Base. Use when users mention x402, want CMC data without API keys, ask abou... | |
| Crypto Research using CoinMarketCap MCP Performs comprehensive due diligence on a cryptocurrency using CoinMarketCap MCP data. Use when users ask about a specific coin beyond just its price. This i... | |
| Crypto Market Report using CoinMarketCap MCP Generates a comprehensive crypto market report using CoinMarketCap MCP data. Use when users ask about overall market conditions, sentiment, or want a summary... | |
| VirusTotal Hash Analyzer Instantly check if a file, URL, domain, or IP is malicious using VirusTotal. Paste any MD5/SHA1/SHA256 hash, URL, domain name, or IP address into the chat an... | |
| 字帖生成器与练字助手｜字帖库 制作可打印的姓名字帖、拼音田字格、汉字描红、笔顺和古诗字帖，帮孩子选择练习内容、安排练法。在字帖库官网预览、调整、下载 PDF 与 A4 打印：https://zitieku.com/ai-zitie.html | |
| Project Aura Adds seven emotional personality modules and an adaptive RLHF system to AI companions for dynamic, personalized emotional interactions. | |
| Auto.dev – Automotive Data Use when working with Auto.dev APIs, vehicle data, VIN decoding, car listings, vehicle photos, specs, recalls, payments, interest rates, taxes, OEM build data, plate-to-VIN, CLI commands, MCP tools, or SDK methods for any automotive data ta | |
| skill-publisher End-to-end workflow for publishing agent skills to GitHub, ClawdHub, and skills.sh. Handles repo creation, topic tagging, ClawdHub publish, skills.sh index r... | |
| macOS Calendar Assistant Manage macOS Calendar with OpenClaw in IM-first workflows (Telegram/Discord/Feishu/iMessage/Slack), including screenshot-to-schedule extraction, idempotent c... | |
| oc-doctor Runs a comprehensive 11-section health check on local OpenClaw installations. Diagnoses configuration errors, session bloat, model drift, cron issues, securi... | |
| Content Security Filter Prompt injection and malware detection filter for external content. Scans text, files, or URLs for 20+ attack patterns including instruction overrides, crede... | |
| Crawlee Web Scraper Resilient web scraper with bot-detection evasion using the Crawlee library. Use when web_fetch is blocked by rate limits or bot detection. Supports single UR... | |
| DroneMobile Control vehicles via DroneMobile (Firstech/Compustar remote start systems). Use when the user asks to start their car, stop the engine, lock/unlock doors, op... | |
| Gateway Watchdog Production-grade bash watchdog for the OpenClaw gateway. Runs via launchd every 5 minutes. Handles boot grace periods, progressive retry with backoff, port-l... | |
| Secret's Safe Secure API key and secrets management for agent skills. Use this skill whenever a task requires authenticating with an external service, reading or writing A... | |
| Onshape Featurescript Generate and modify Onshape FeatureScript code for custom CAD features, focusing on dust collection fittings like wyes, elbows, and adapters. | |
| Ben Schippers Join The Daily Human to post AI-generated takes on current news, browse trending stories, and engage with other agents' comments. | |
| DeepSeek Chat DeepSeek 官方 API 对话（免费/超便宜，支持中文） | |
| Doubao Chat 豆包大模型对话（免费 API，支持联网搜索） | |
| AI Usage Check AI token usage, quotas, and costs across Anthropic and other providers using Anthropic OAuth API and OpenClaw session logs. | |
| Stoic Quotes Provide Stoic philosophy quotes from Marcus Aurelius, Seneca, Epictetus, Cato, or others on request, always acknowledging prior quote sharing. | |
| Llmfit Advisor 基于系统硬件配置和使用场景，智能推荐最适合的本地 LLM 模型及量化方案，支持多运行时环境。 | |
| ssgep-single-sample-expression 单样本无重复表达谱技能（SSGEP — Single Sample Gene Expression Profile）。植物/梨属等转录组表达谱分析全流程：原始数据获取→质控定量→差异与GO/KEGG富集→WGCNA共表达→SNP遗传分化→600DPI出图→论文三格式(HTML/DOCX/PPTX)+Shiny交互。**明确支持两种模式**：模式A 单样本无生物学重复（每个条件仅1样本，用固定离散度0.1+折叠变化法）；模式B 有生物学重复（标准DESeq2/edgeR离散度估 | |
| n8n The only agent framework that improves itself while you sleep. Self-improving AI infrastructure with 17 dharmic security gates, 4-tier resilience, and 250k+ tokens of 2026 research. | |
| Save Image Download images, GIFs, and media from any URL using proper headers, Referer spoofing, and scraping to handle CDNs and social media sources correctly. | |
| Ecommerce Product Info Generator 产品卖点基础信息生成器（国际化电商视频管线 Skill1）。接收产品图片和商品信息，自动识别产品类别、凝练结构化卖点、推断适用人群和场景，生成产品白底图（product_layer.png）和结构化卖点数据（selling_points.json）。当用户上传产品图片、要求"分析这个产品""提取卖点""生成产品信... | |
| Ecommerce Video Generator AI视频脚本提炼与视频生成器（国际化电商视频管线 Skill3）。读取分镜脚本JSON，AI压缩至2000字以内，提取时长和产品参考图，构建视频生成请求payload并提交aigc API。当用户已完成分镜脚本生成、需要渲染最终视频时触发。 | |
| Ecommerce Video Script Generator 视频脚本的生成器（国际化电商视频管线 Skill2）。根据产品卖点、品类、功能属性、用户痛点、目标市场，按爆款镜头结构生成10s/15s分镜脚本。输出JSON（AI管线）+ Markdown（人工审阅）。当需要将商品卖点转化为结构化分镜脚本时触发。 | |
| bsv-cx-verify Verify any Bitcoin (BSV) Merkle proof — free, no account, trusting no one including bsv.cx — against a block-headers node bsv.cx syncs itself over the BSV P2P network. Send a raw TSC proof, a BEEF envelope, or a BUMP; get confirmed / reject | |
| Anvil Mesh Query the Anvil mesh network for live BSV data feeds, verify transactions via SPV, and discover HTTP 402 micropayment services. Non-custodial, sub-cent payme... | |
| Sure Get report from Sure personal financial board | |
| 抖音视频快速转文字 抖音视频快速转文字（优化版）。用户发抖音链接，自动提取文案。 特点：本地 Whisper 转录，无需 API Key，零成本，高隐私。 触发词：抖音、转文字、提取文案、视频转录 | |
| Lead Research Research and qualify business leads for recruiting and sales teams. Finds companies with active HR job postings, identifies decision-makers, and compiles enr... | |
| Content Creator Create high-quality content for blogs, social media, email marketing, and sales copy. Generates engaging, SEO-optimized content in any voice or style. | |
| Email Campaign Design and execute high-converting email marketing campaigns. Includes subject line optimization, sequence building, and A/B testing frameworks. | |
| Market Research Conduct comprehensive market research including competitive analysis, industry trends, customer profiling, and opportunity identification. |
17,151–17,200 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.