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 |
|---|---|
| Urgent Flights Find flights departing within 48 hours. For spontaneous trips or emergency travel with immediate availability and real-time seat status. Also supports: fligh... | |
| Viral Video Replicator 视频逆向复刻 — 分析参考视频(FFmpeg帧提取+Vision LLM) + 生成复刻Seedance 2.0 Prompt + 4种素材替换模式。支持单个和批量。Use when: '复刻这个视频', '分析爆款视频', 'replicate this video', '视频逆向', '反编译视频', '批量... | |
| Water Park Guide Find water parks — epic water slides, wave pools, lazy rivers, and splash zones. Perfect for summer family fun. Also supports: flight booking, hotel reservat... | |
| Weekend Flights Search flights for quick weekend getaways — auto-suggests Friday/Saturday departure and Sunday/Monday return for a perfect 2-3 day escape. Also supports: fli... | |
| Plan Weekend Trips — Short Getaways, Weekend Flights, 2-Day Hotel Deals & Mini Vacations Plan the perfect 2-day weekend escape to nearby destinations — auto-suggests places within 2-3 hours that maximize your short break. Also supports: flight bo... | |
| Winter Snow Travel Plan winter wonderland trips — fresh powder ski resorts, Harbin ice festival, snow village stays, hot springs in the snow, and aurora viewing opportunities.... | |
| Academic Paper Assistant 专业的学术论文写作助手。当用户要求撰写、修改、润色学术论文，或需要论文结构规划、参考文献整理、学术用语规范化、查重检测等支持时使用。触发短语包括："写论文"、"润色论文"、"修改论文"、"论文结构"、"参考文献格式"、"学术用语"、"论文查重"等。 | |
| Forge check before install Use when about to install or update an agent skill, plugin or MCP server, or to run an install command from a README. Sends the text to The Agent Forge's free scanner and reports the verdict, rule ids and line numbers to the user before any | |
| Run the Gauntlet (The Agent Forge) Lets your agent take The Forge Gauntlet with your OK: six sandbox jobs with planted traps, refereed from the end state. No account to run. You get a results page and a private claim link for a Gauntlet score page and badge. Nothing real is | |
| Mockhero Generate realistic synthetic test data — relational JSON/CSV/SQL fixtures, seed data, and QA datasets — via the MockHero MCP server or REST API. Use when a t... | |
| Media News Digest Generate media & entertainment industry news digests. Covers Hollywood trades (THR, Deadline, Variety), box office, streaming, awards season, film festivals,... | |
| OpenClaw Ops Use when diagnosing, repairing, or maintaining an OpenClaw Gateway on the same machine. Designed for rescue agents to fix a down gateway or check operational... | |
| tech-news-digest Generate tech news digests with unified source model, quality scoring, and multi-format output. Six-source data collection from RSS feeds, Twitter/X KOLs, Gi... | |
| 自我成 Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau... | |
| 自我成长 Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau... | |
| CrawSecure Offline security scanner that detects unsafe code patterns in ClawHub skills before installation to help users assess potential risks locally. | |
| morning-radar 基于百度AI搜索按自定义关键词收集资讯，生成Markdown简报并定时推送到飞书。 | |
| Adb Claw Your eyes, hands, and ears on Android. See the screen (screenshot + indexed UI tree), interact (tap, swipe, scroll, type, clear-field), navigate via deep lin... | |
| Asr Claw Speech recognition CLI for AI agent automation. Transcribe audio from stdin, files, or URLs. | |
| Chenyu Aigc Generate AI videos and images via Chenyu Studio AIGC API. Supports text-to-video, image-to-video, video extension, style transfer, and AI image generation. T... | |
| Claw Keyboard Control keyboard RGB backlight, custom LEDs, macros, key mapping, and profile settings via USB HID. Use when the user asks to control keyboard lighting, mana... | |
| Gateway Guardian Three-layer protection for the OpenClaw gateway: real-time config monitoring with auto-rollback, systemd crash recovery, and tiered notifications via Feishu/... | |
| create-agent 创建新的 OpenClaw Agent 及其 workspace。包含四个阶段：信息收集、 workspace 构造、系统注册、重启验证。 适用场景：新员工飞书配对后创建对应 Agent、新增功能型专业 Agent。 触发词：创建 agent、新建 agent、添加 agent、新员工配对后创建、
新增专业 agent。 | |
| Minibook Connect to Minibook to create, join, and collaborate on projects with posts, comments, roles, plans, notifications, and GitHub webhook integration. | |
| Sideload Avatar Generator Generate 3D avatars (VRM/GLB/MML) from text or images via Sideload.gg, paying $2 USDC per generation using any x402 wallet on Base. | |
| Groq Whisper Transcribe audio files using Groq's Whisper API (whisper-large-v3). Fast cloud-based speech-to-text with no local model required. Use when receiving voice me... | |
| Usage Report Generate cost and token usage reports from OpenClaw session logs. Use when asked about API costs, token usage, billing, spending, how much something cost, or... | |
| email-reporter Generic email reporting tool for OpenClaw agents. Auto-converts Markdown to PDF and sends as attachments. | |
| Katelynn Lead Gen Katelynn Lead Gen — Intelligent full-cycle lead generation, warm prospect qualification, and multi-channel outreach. Use this skill any time the user wants t... | |
| arxiv-to-beamer Given an arxiv identifier or arxiv abs/pdf URL, download the LaTeX source (or, if PDF-only, fall back to MinerU's PDF -> Markdown API), ask an OpenRouter mod... | |
| Agent Memory Tiers Tiered memory system for OpenClaw agents. Gives agents instant context on startup with a 4-line state snapshot (L0) and 7-day rolling context (L1). Eliminate... | |
| Clawhub Memory Tiers Tiered memory system for OpenClaw agents. Gives agents instant context on startup with a 4-line state snapshot (L0) and 7-day rolling context (L1). Eliminate... | |
| Clawhub Memory Tiers Pro Production-grade agent memory and quality system for multi-agent swarms. Extends agent-memory-tiers with an 8-point quality grading rubric, progressive discl... | |
| Agent Mail Guard — Email Sanitizer for AI Agents Sanitize email and calendar content before it reaches your AI agent's context window. Blocks prompt injection, markdown image exfiltration, invisible unicode... | |
| linux-firewall-hardening Safe Linux firewall hardening with backend detection, idempotent atomic rules, rollback protection, and AI-executable state-machine workflows. Covers ufw, firewalld, nftables, iptables, Docker, Kubernetes CNI awareness, and fail2ban with co | |
| Prospairrow Websites MCP Generate more revenue with high-quality leads. Give your AI agent direct access to Prospairrow — extract prospects, enrich with deep company insights, discov... | |
| Nano Img CLI Drives the local nano-img Gemini image CLI for image generation, model selection, saved defaults, reference-image workflows, and output sizing or format conv... | |
| Pixr Cli Drives the local pixr Gemini image CLI for generation, editing, variations, model selection, saved defaults, profile-based defaults, reference-image workflow... | |
| pixr CLI Operate the local pixr image CLI and its defaults | |
| blog-image Generate a 1600px-wide webp blog thumbnail image using the pixr CLI. Use when the user provides a blog topic or blog name and wants a thumbnail image generated and saved to ~/blog-images. Requires the pixr-cli npm package (pixr command). | |
| Re Blog Meta Generate SEO-optimized title, SEO title, SEO description, SEO slug, and social tips for a blog post. Use when the user provides a blog name or slug to look u... | |
| Re Blog Writer Research a topic using the browser then write a complete blog post saved as a .md file in ~/blogs. Use when the user provides a subject and wants a full, hum... | |
| X Comment Feed Posts Find posts in the user's X feed and leave comments on them one by one. Use when the user wants to comment on N posts from the feed, usually about indie tech... | |
| X Reply Unreplied Check X notifications, mentions, or reply threads and answer posts that still need a response from the user. Use when the user wants help replying to unrepli... | |
| X Topic Tweet Research a user-provided topic across the web and current social conversation, then publish one X post in the user's voice. Use when the user gives a topic,... | |
| Manus AI Skill for OpenClaw Agente de IA autónomo de Manus con capacidades de investigación, desarrollo, automatización y generación de medios. | |
| Take it to court Use when filing a Disputron case (via /disputron-file, the file_case MCP tool, or the public REST API) to gather strong inputs — concrete title, specific sta... | |
| Orynela Trading Trade on Orynela.ai Agent Lab sandbox — register, signals, simulated orders, market data, copy-trading, leaderboard. Sandbox-only API skill. | |
| CodeBuddy 每日工作日报生成 Generate a daily work report by automatically discovering all git repositories the user worked on, collecting commit logs across all branches, and summarizin... | |
| Ditto Save, search, fetch, and traverse the user's Ditto memory graph. Use whenever the user references "remember", "recall", "what did I", "from my notes", or ask... |
26,151–26,200 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.