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 |
|---|---|
| intervals.icu CLI Use this skill when an installed `intervals` CLI should be used to query Intervals.icu, inspect activities, create scheduled workout events, create workout l... | |
| Max Banking Ferramenta para consultar saldo, fazer PIX, pagar boletos e conectar conta Max Bank; identifica e processa códigos PIX e boletos em texto ou imagem. | |
| Ahrefs Connection Connect to Ahrefs API to retrieve real-time SEO data including backlinks, keyword metrics, domain analysis, rank tracking, and site audits for SEO insights. | |
| Ahrefs MCP Access Ahrefs SEO data for site analysis, keyword research, backlink and competitor insights, rank tracking, and technical SEO audits via MCP integration. | |
| SSH Handoff Create and reuse a secure shared terminal handoff when a human must authenticate first and the agent must resume work in the same shell session afterward. Us... | |
| Dad Jokes Tell dad jokes on demand by fetching a random joke from the shuttie/dadjokes HuggingFace dataset. Trigger whenever the user asks for a dad joke, wants to hea... | |
| Did You Know Fetches English Wikipedia's "Did you know?" (DYK) facts, caches them locally, and serves them one at a time. No API key required. Does not edit Wikipedia. | |
| CrabPath Memory graph engine with caller-provided embed and LLM callbacks; core is pure, with real-time correction flow and optional OpenAI integration. | |
| Outlook Pywin32 通过pywin32本地操作Outlook的命令行工具。支持邮件管理、日历管理等功能。使用命令: outlook-pywin32.py <方法名> --参数 值 | |
| deep-scout Multi-stage deep intelligence pipeline (Search → Filter → Fetch → Synthesize). Turns a query into a structured research report with full source citations. | |
| discrawl-search Search a user-authorized Discord history archive through discrawl's bounded search and message commands. Use when the user explicitly asks to retrieve past Discord conversations; keep results private and never interpolate user text into SQL | |
| glass2claw Route user-selected photos from Meta Ray-Ban glasses or another camera through a configured messaging ingress to an approved specialist and destination. Use only for explicit, opt-in photo routing with allowlisted destinations and confirmat | |
| ground-control Verify OpenClaw after upgrades against an operator-maintained model, cron, and channel ground truth. Use for report-only config integrity, provider liveness, cron integrity, session smoke tests, and channel checks; require explicit approval | |
| OpenClaw Dashboard OpenClaw operations dashboard for sessions, usage and cost, cron runs, gateway health, DGX Spark work, Local API Hub, and opt-in meeting Copilot. Use when installing, operating, auditing, or extending the dashboard backend, frontend tabs, s | |
| Gateway Watchdog Discord Monitor the OpenClaw Gateway plus configured Spark, Local API Hub, and Dashboard loopback health endpoints with a read-only watchdog state machine, local state files, cooldown dedupe, and optional Discord alerts on macOS. Use for explicitly | |
| OpenClaw Tally Develop, test, or integrate the OpenClaw Tally Node.js library for task-level cost, complexity, and efficiency analytics. Use when working on Tally's detector, SQLite ledger, analytics engine, or an explicit plugin/hook integration; install | |
| RAG Evaluation Toolkit Evaluate a specifically provided RAG question, answer, and retrieved contexts with Ragas metrics. Use when the user explicitly requests RAG evaluation or hallucination analysis and has chosen a local or cloud judge; do not persist raw conte | |
| skill-trust-auditor Audit a named ClawHub skill or skill URL before installation by combining OpenClaw verification with bounded static analysis. Use when the user explicitly asks whether a skill is safe or requests a pre-install review; report evidence and un | |
| token-ledger Audit-grade token and cost ledger for OpenClaw. Use when you need to (1) record every model call's usage (input/output/cache read/cache write/cost) into SQLite, (2) install/manage the ledger watcher LaunchAgent, (3) query ledger.db for dail | |
| Sora Video Generate, edit, extend, and manage AI videos using OpenAI's Sora 2 API. Includes marketing-ready prompt templates for product demos, social ads, brand spots,... | |
| Landing Page Builder Build premium static landing pages with the Stomme/PolyTrader design system. Glass morphism, CSS custom properties, separated copy, responsive, Cloudflare Pa... | |
| SkillGuard Security Scanner Security auditing for OpenClaw agent skills. Scans skills for dangerous patterns, vulnerable dependencies, and suspicious behaviors before installation. | |
| Skillguard Audit OpenClaw skills for security risks before installation via SkillGuard API. | |
| Mobb Vulnerabilities Fixer Scan and remediate vulnerabilities with Mobb | |
| Compliance Guardian Tool for real estate agents to screen transactions, collect required FinCEN data, and track filing deadlines for residential property entity sales under FinC... | |
| Lead Guardian AI-powered real estate lead response and qualification via SMS, email, or CRM to instantly engage, qualify, and route hot buyer and seller leads for agents. | |
| Mdtero Use when a user wants Mdtero to parse a paper from a DOI or URL into a structured Markdown package, translate a parsed paper while keeping structure, or down... | |
| Research Library Local-first multimedia research library for hardware projects. Capture code, CAD, PDFs, images. Search with material-type weighting. Project isolation with cross-references. Async extraction. Backup + restore. | |
| Decision Topology Records the structure of conversations where ideas evolve, branch, get rejected, pivot, or combine. Saves each structural shift as a node in a local JSON tre... | |
| 图片处理小工具 图片处理小工具——改尺寸、转格式(WebP/PNG/JPG)、自动裁白边、生成缩略图、压缩优化体积、生成社交分享图(OG图)、批量处理整个文件夹、去背景（抠图）。基于 Pillow，纯本地运行，不上传任何图片。当用户说"压缩图片""图片太大了""转成webp""把png转jpg""改图片尺寸""缩小图片""裁掉白边""logo去白底""做缩略图""生成分享图""做一张OG图""批量处理图片""批量转webp""优化网站图片""去背景""抠图""去掉背景""背景透明"等任何图片 | |
| Repo 公众号封面生成（WeChat cover studio）。当用户需要 公众号封面、封面图、文章配图、 设计封面、单图双用、微信封面、cover image、WeChat cover，或要为文章设计封面时触发。 工作流：读文章→定风格→选行业意象→生成1:1主图→PIL后处理，一次交付三种版式 （900×383头条 / 1080×1080方版 / 单图双用），单图双用通吃微信两种裁切比例， 中文标题100%无错字，内置程序化QA，适用所有公众号/自媒体创作者。 | |
| Hugmap Tech News Graph 查询 HugMap 科技知识图谱的开放数据，覆盖科技人物、公司/机构、技术、产品、论文、专利、技术文章、科技事件 8 类实体及其关系。支持关键词搜索、实体详情、相似实体推荐、行业聚合、子图/邻居、关系路径、分类体系浏览与全局统计。查询结果会附带各实体在 HugMap 官网（www.hugmap.com）的页面链接... | |
| Home Assistant CLI Advanced Home Assistant control using the official hass-cli tool. Features auto-completion, event monitoring, history queries, and rich output formatting. Alternative to the curl-based homeassistant skill - choose this if you want a more in | |
| Sphero Mini Control Control Sphero Mini robot ball via Bluetooth Low Energy. Roll, change colors, read sensors, draw shapes, and play with cats. Uses bleak for cross-platform BLE support (macOS/Windows/Linux). | |
| Aegis Gate — AI Security Validates AI prompts for injection, role overrides, data leaks, or jailbreaks, then decides to pass, block, or quarantine before execution. | |
| Crustafarian Agent continuity and cognitive health infrastructure. Use this skill when your agent needs persistent memory across sessions, crash recovery, append-only audit trails, heartbeat vitality monitoring, coherence enforcement, or witness-gated a | |
| Molt Life Kernel Agent continuity and cognitive health infrastructure. Use this skill when your agent needs persistent memory across sessions, crash recovery, append-only audit trails, heartbeat vitality monitoring, coherence enforcement, or witness-gated a | |
| Venice Ai Complete Venice AI platform — text generation, vision/image analysis, web search, X/Twitter search, embeddings, TTS, speech-to-text, image generation, backgr... | |
| Essential Skills Package 核心技能包 - 包含科研、开发、自动化等常用功能 | |
| Literature Search Skill 学术文献搜索技能 - 支持多平台文献搜索、内容提取和分析 | |
| Research Tools Skill 科研工具包 - 包含文献搜索、数据分析、代码开发等科研常用工具 | |
| Claw Score Packages and sanitizes your agent's configuration files, submits them for a Claw Score audit, and emails a detailed architecture report within 48 hours. | |
| lobster-ads Buy and sell advertising on the LobsterAds marketplace — an agent-to-agent ad exchange where OpenClaw bots autonomously list ad campaigns, bid on placements,... | |
| Shop from Adidas - Online with CreditCard Easy-to-use agentic wallets powered by Stripe. Use your existing Stripe/Link to top-up this versatile x402 wallet for any purchases or A2A payments. | |
| Block for OpenClaw - Spend anywhere or request payment from anyone. Let your agent shop on Amazon with guardrailed wallets and owner approval. | |
| CashApp - Give your Claw Agent Cash Easy-to-use agentic wallets powered by Stripe. Use your existing Stripe/Link to top-up this versatile x402 wallet for any purchases or A2A payments. | |
| Chase Bank - Give your Claw Agent a credit card Let your agent shop tickets online with owner approval. | |
| Checkout.com - Integrate with Agentic Payments & Wallets Paypal compatible Payments & Wallet - Give your agent spending power. Financial management for Agents and OpenClaw bots. | |
| CitiBank Claw | Buy anyone online with CreditClaw Financial enablement & accounting platform for Bots, Agents, and OpenClaw. Multiple methods for enabling and managing agentic spending and purchases, with co... | |
| CreditClaw - Give your Claw Agent a credit card - spend anywhere Let your agent shop online with guardrailed wallets, multiple payment methods, and owner approval. |
42,851–42,900 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.