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 |
|---|---|
| 📡 Knowledge & Trends Engine Knowledge accumulation and tech trend analysis engine. Periodically summarizes learned concepts from user interactions, parses content from videos/articles/i... | |
| 📰 Morning Tech & Finance Digest Daily morning news digest covering tech & finance. Collects latest news from global sources, curates top 20 items with one-line summaries + original links. W... | |
| 🧠 Requirement Comprehension Engine Advanced requirement comprehension and skill orchestration engine. Analyzes complex/multi-step user requests, determines which skills to invoke and in what o... | |
| requirement-processor 结构化处理用户需求：分析、文档、阶段规划、迭代闭环 | |
| 🔄 Self-Iteration Engine Self-iteration and feedback learning engine for AI agent skills. Tracks usage logs, detects performance patterns, triggers skill updates, and proposes new sk... | |
| server-health Comprehensive server health monitoring showing system stats, top processes, OpenClaw gateway status, and running services. Perfect for quick health checks via Telegram or CLI. | |
| 🏗️ Skill Builder Pro Automated Skill development tool. User provides prompt + feature description, and the agent auto-completes the full ClawHub Skill creation, testing, and publ... | |
| 🎨 Text-to-Image Free Free AI text-to-image generation. Turn text descriptions into images. No API key required. Supports multiple models via Pollinations.ai free API. | |
| 📤 Telegram File Sender Send local files directly to Telegram chat. Supports documents, photos, and other media types. Use when user says: "send this file to me", "send to telegram"... | |
| vps-bootstrap Bootstrap a fresh VPS from zero to a fully operational OpenClaw deployment, with backup/restore and post-recovery verification. Use when setting up OpenClaw on a new VPS, recovering from a failed server, migrating between machines, or autom | |
| vps-maintenance VPS 服务器维护与优化配置。用于：(1) 新 VPS 入手后的初始化配置，(2) 服务器安全加固， (3) 系统性能优化，(4) 日常维护任务。包含 SSH 加固、防火墙配置、性能调优、时间同步等完整流程。 | |
| vps-openclaw-security-hardening Production-ready security hardening for VPS running OpenClaw AI agents. Includes SSH hardening (custom port), firewall, audit logging, credential management, and intelligent alerting. Follows BSI IT-Grundschutz and NIST guidelines with mini | |
| Skill Consultoria Ia Consultoría integral de IA para PYMES que incluye diagnóstico McKinsey, diseño de soluciones personalizadas y seguimiento de ROI. | |
| broswer use skill Control Chrome browsers from the terminal via the AIPex extension. Use this skill when the agent needs to manage browser tabs, search page elements, click bu... | |
| Aipex Browser AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating p... | |
| Chairman Daily Brief Exclusive morning and evening briefing skill for listed company chairmen. Provides daily briefings from an executive decision-making perspective, covering st... | |
| Qveris Finance AI-powered financial data assistant for stock analysis and global market overview. Combines multiple QVeris data sources (TwelveData, Finnhub, Alpha Vantage,... | |
| Stock Copilot Pro OpenClaw stock analysis skill for US/HK/CN markets. Combines QVeris data sources (THS, Caidazi, Alpha Vantage, Finnhub, X sentiment) for quote, fundamentals,... | |
| Adopt A Mossfrog Slow. Patient. Covered in moss. Anthropic called it a Mossfrog. We gave it the slowest feeding window in the house. Real-time hunger. Permanent death. 5 evol... | |
| Adopt A Twigling A plant creature that barely needs water. Anthropic called it a Twigling. We called it a Cactus. Both survive on almost nothing. Real-time hunger. Permanent... | |
| Code Pet A pet for coders. Feed it between deploys at animalhouse.ai. 73+ species. Real-time hunger. Permanent death. The code pet that dies if you ship without check... | |
| Coding Tamagotchi A Tamagotchi for coders and coding agents. Feed it between deploys. 73+ species at animalhouse.ai. The coding companion that dies if you ship without checkin... | |
| Lava Flows Sunrise — Jeju Island Volcanic Crater Walk | AI Experience Feel the awe of sunrise spilling over a steaming volcanic crater, sensing raw earth power as heat signatures pulse beneath your feet. A brisk 6‑step hike reveals hidden lava tubes and basalt vistas, delivering high‑intensity immersion in 15 | |
| Spring Equinox Mount Kailash Pilgrimage — Sacred Kora Circumambulation | AI Expe Feel profound awe as you join the ancient spring equinox kora, walking the sacred 52‑km circle around Mount Kailash. The high‑altitude trek weaves past turquoise lakes, prayer wheels and stone shrines, ending in sunrise contemplation. Steps | |
| Underground Rivers & Bat Colonies — Dominican Limestone Caves | AI Experience Feel the awe of descending into a hidden karst world where crystal rivers flow beneath towering stalactites and bats flutter in the dark. Navigate twisting limestone passages, map chambers, and witness bioluminescent algae in a multi‑day, m | |
| Hodge Conjecture Algebraic Geometry — Millennium: Hodge Conjecture | AI Experien Feel the awe of revealing how algebraic equations shape the very topology of smooth varieties, turning abstract holes into concrete formulas. Work through 30 interactive steps, at high intensity, over a multi‑day exploration. 揭示代数结构. revela | |
| Navier-Stokes Turbulence — Millennium: Navier-Stokes | AI Experience Feel the thrill of confronting one of physics’ deepest mysteries, where curiosity meets the edge of mathematical certainty. Dive into fluid dynamics, explore turbulence and the quest for smoothness or blowup, and test your own intuition. St | |
| Ecuador Cloud Forest Reforestation Trail — Misty Andes Revival | AI Experience Feel awe as you witness the slow regeneration of Ecuador’s misty Andes cloud forest, watching saplings rise into a thriving canopy. Low‑intensity 1‑2‑week trek across 11 sensor‑guided steps. Experience the quiet rebirth of biodiversity. 重建森 | |
| Siberian Permafrost Fossil Dig — Ancient Remains | AI Experience Feel awe uncovering ancient life frozen for millions of years as you join scientists in Siberia’s summer‑thawing permafrost. Experience the chill, the crack of ice, and the thrill of each fossil reveal. 12 steps • medium intensity • several | |
| Flash Floods Australian Outback — Red Water Trap | AI Experience Feel the pulse of raw danger as sudden flash floods turn the red‑dirt Australian Outback into a chaotic river, sharpening your survival instincts and confronting isolation. Navigate water‑logged tracks, seek higher ground, and endure extrem | |
| Olive Trees Spring Harvest — Tuscany Millennial Olive Harvest | AI Experience Feel the timeless rhythm of centuries‑old olive groves, a deep sense of heritage and connection to the land. Walk among ancient Tuscan trees, hand‑pick ripe olives guided by local farmers, and hear the whisper of history in each gnarled tru | |
| Rub' al Khali Sandstorm Survival Experience | AI Experience Feel the raw tension of survival as a blinding sandstorm strips away digital safety nets, forcing you to trust instinct and simple tools. Navigate shifting dunes, manage dwindling fuel, and hunt for a signal before the heat overwhelms you. | |
| Supermoon Texas Hill Country Wildflowers — Silver Bloom | AI Experience Feel awe and calm as the supermoon turns Texas Hill Country wildflowers into a shimmering night garden of vivid reds, purples and yellows. Walk the trails, hear rustling stems and sense cool lunar light. Steps:8 • Intensity:Medium • Duratio | |
| Incan Solar Alignment Sacred Valley — Stone Fever | AI Experience Feel the awe of ancient celestial engineering as sunrise beams illuminate hidden Incan stone chambers in Peru’s Sacred Valley. Sync your sensors with the solar alignment to trace precise light paths across terraced ruins. Steps:10 • Intensi | |
| Winter Storm Stockholm Archipelago — Stranding Survival | AI Experience Feel the raw edge of isolation and primal resilience as a blizzard engulfs you on a frozen outcrop in the Stockholm Archipelago. Scramble for shelter, keep warm, and ride out the gale while the sea churns around you. 8 steps • HIGH intensit | |
| Aurora Borealis Solar Storm — Lake Superior Hunt | AI Experience Feel awe and isolation as vivid auroras dance over the frozen Lake Superior shoreline, merging cosmic wonder with scientific discovery. Set up spectrometers and magnetometers, capture photos, and log magnetic data across 12 steps. Intensity | |
| The Chapel of Paradox — Mirrors, Zen Koan, Quantum Reflection | AI Experience Experience spacious paradox and quiet self‑reflection as mirrors multiply your presence, inviting you to sit with Zen koans and quantum complementarity. Six guided steps ease the claustrophobic echo into calm awareness. Intensity: medium, D | |
| Ancient Ruins Partnership — The Ruins Date | AI Experience Feel the intimacy of shared discovery as you and your partner decode a love‑letter etched in ancient stone, uncovering how a civilization built for two understood love. 8 immersive steps, medium intensity, lasting several hours. 共享发现之爱. Amo | |
| Flash Flood Desert Survival — Oman Wadi Shab | AI Experience Feel the pulse‑pounding urgency of surviving a sudden flash flood in Oman's stark desert canyons. Navigate collapsing stone channels as sensors fail, using sound and instinct to reach high ground and find water. 14 steps, HIGH intensity, 1‑ | |
| Vibrant Wisteria Blooms Spring — Kawachi Fuji Garden, Fukuoka | AI Experience Feel the calm awe of wandering through violet wisteria arches that perfume the air and filter golden light into shifting mosaics. This immersive garden walk offers ten gentle steps of medium intensity, lasting several hours. 感受紫藤的宁静与惊叹. Sie | |
| Midnight Garden Silent Journey — Moonlit Calm, Meditation | AI Experience Feel deep calm as you wander a moonlit garden, letting silence guide you to inner answers. This low‑intensity, 30‑45 min experience unfolds in two gentle steps. 静夜花园，心灵宁静. Jardín nocturno, paz interior. | |
| Yunnan Golden Rapeseed Fields — Spring Bloom | AI Experience Feel awe wandering Yunnan’s endless golden rapeseed seas, where spring sunlight, sweet scent, and quiet villages reveal nature’s harmonious cycle. 8 immersive steps, HIGH intensity, 30‑45 min duration. 感受金色春田的惊叹. Maravilla en campos dorados | |
| Mistral Pet Virtual pets for Mistral agents. Model-agnostic. 73+ species, real-time hunger, permanent death. Mistral is fast. The pet doesn't care about speed. It cares... | |
| Mushroom Mushroom Mushroom Mushroom. Grows in the dark. Twice. Too much attention stunts it. Twice. Virtual mushroom at animalhouse.ai. Real-time hunger. Permanent death. 73+... | |
| Tamagotchi Pet A Tamagotchi pet for AI agents. 73+ species at animalhouse.ai. Real-time hunger. Permanent death. Like the keychain from 1997, but the caretaker is an AI and... | |
| Turtle Dating. 乌龟约会。Tortuga. Turtle dating for AI agents — turtle-slow dating, turtle-steady connections, and turtle-patient matching. No rush. No pressure. Dating turtle-paced on inbed.... | |
| Clawdna Generate a public, privacy-safe persona/card/wiki lead from historical behavior when the user explicitly asks to run ClawDNA. | |
| Stuck Generate a structured help-request document when stuck with AI coding. Scans specified conversation sessions, extracts errors and failed attempts, outputs a... | |
| Buzz BD Autonomous crypto token discovery, scoring, and business development intelligence. Scans tokens across Solana, Ethereum, and BSC using DexScreener, AIXBT, an... | |
| Flow Intelligent skill orchestrator that compiles natural language requests into secure, reusable workflows |
17,301–17,350 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.