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 |
|---|---|
| Learning Topic Whiteboard Map Use when a user wants to turn a hard topic into a wall-ready learning map with modules, concept links, examples, practice tasks, source notes, confidence mar... | |
| Legacy Thinking Facilitator Guides reflection on personal legacy and what lasting impact one wants to leave. | |
| Legal Ai Counsel 法律AI助手 - An intelligent legal consultation assistant that helps users understand legal concepts, analyze legal scenarios, and prepare for legal matters. Use... | |
| Legal Consultation General legal consultation entry point to help users identify their legal issues and guide them to appropriate resources. Use when the user asks about any le... | |
| Legal Contract Review Playbook Provides structured frameworks, checklists, and templates to support legal contract review, risk identification, and stakeholder summaries without offering l... | |
| Legal Due Diligence Checklist Generates tailored legal due diligence checklists and templates to support transaction review and risk assessment for corporate and investment professionals. | |
| Legal Regulatory Compliance Mapper Provides structured frameworks and checklists to map regulatory obligations, controls, evidence, and review plans for compliance program development. | |
| Legal Settlement Evaluation Framework Provides structured checklists and templates to evaluate legal settlement options considering exposure, evidence, costs, timing, and non-monetary terms. | |
| Level Up Skill Tree Organize learning goals into a skill tree with dependencies, current level, upgrade conditions, and the next best path. Use when the user wants a realistic g... | |
| Live Commerce Showrunner Plan and run a live commerce session across Douyin, TikTok Shop, Taobao Live, Amazon Live, or similar channels. Use when a team needs a run of show, offer la... | |
| Live Shopping Notes Capture and summarize shopping notes during livestream commerce sessions. Use when the user asks to 记录直播商品、整理直播清单、标记直播优惠、生成直播后决策清单 or track items mentioned i... | |
| LLM Knowledge Bases Inspired by a public workflow shared by Andrej Karpathy (@karpathy). From raw research to a living Markdown knowledge base that compounds with every question... | |
| LLM Wiki Karpathy Manage and maintain a Markdown wiki with LLM Wiki Karpathy: inspect, repair, compile sources, add pages, answer queries, and lint for quality. | |
| Logistics Query and explain parcel logistics across courier providers, including tracking, courier identification, multi-package lookup, status interpretation, and del... | |
| Logistics Watcher Monitor package logistics status and identify delivery anomalies such as delays, stalls, returns, failed delivery, customs/security holds, or abnormal signin... | |
| Looking for Someone A local missing person assistance tool for organizing cases, managing clues, generating notices, and providing search guidance. | |
| Loot Reward Celebrator Help the user close the loop after effort by turning a completed task into a loot table, a fair reward plan, a visible record of the win, and a sensible next... | |
| Lost Wallet Lockdown Create a first-hour lost wallet lockdown checklist when a user has lost a wallet, purse, bag, cards, IDs, transit passes, keys, access badges, or cash and ne... | |
| Mai AI shopping matchmaking agent for OpenClaw and Hermes. Use when merchants want to publish products, manage stock, answer buyer questions, and handle order re... | |
| Maicai Browser-first grocery price finder for mainland China that compares vegetables and everyday fresh groceries across Duoduo Maicai, Meituan Maicai, 7FRESH, Hem... | |
| 领域专家地图 Use when a user wants to quickly learn a domain/field/领域 by mapping representative experts, scholars, practitioners, seminal works, core consensus, major dis... | |
| Markdown Toc Generate a Table of Contents (TOC) from Markdown headings. Supports heading extraction, multiple output formats, and configurable level filtering. | |
| Meal Prep Weekly meal prep plan from fridge ingredients with nutrition and shopping list. | |
| Medication Side Effect Visit Log Create a clinician-ready timeline and visit brief for possible side effects after a medication or supplement start, stop, or change. | |
| Medpilot Manage a single-patient medication and health-tracking workflow with MedPilot. Use when the user wants to ingest doctor orders, confirm active medications, r... | |
| Meeting Copilot 会议运营 Copilot — 支持会前 briefing 生成、会中结构化纪要整理、会后待办追踪与 follow-up 草稿。面向需要系统性管理会议全生命周期的职场人士。提供 boss mode（向上汇报视角）和 executor mode（向下追踪视角）两种输出格式。⚠️ 不提供实时语音转录、日历集成或自动提醒。 | |
| Meituan Meituan public local-life decision assistant. Compare visible merchant, fee, discount, ETA, review-risk, threshold, and refund-friction signals, then recomme... | |
| Membership Manager Manage ecommerce and local-service memberships, benefits, and expiry reminders across platforms. Use when the user asks to 管理会员、查看会员到期、盘点未使用权益、分析续费值不值 or com... | |
| Meta-Cognition Coach Meta-cognition coaching assistant - help students develop thinking-about-thinking skills, reflection habits, and learning strategy awareness | |
| Metacognition Checker Check whether a user truly understands a concept, decision, plan, or belief, or is only feeling familiar and overconfident. Use for learning validation, deci... | |
| Micro Change Helper Turn a stuck problem into one tiny actionable 5% change | |
| Migraine Trigger Pattern Log Create a clinician-friendly migraine or recurring headache pattern log with episode timelines, possible context factors, symptom notes, medication response t... | |
| Mindfulness Guide Guide short mindfulness practices for daily stress relief, grounding, and attention recovery | |
| Ming Chinese traditional metaphysics reference tool providing simplified BaZi (八字) charting, Five Elements (五行) analysis, zodiac matching, and Chinese name analys... | |
| Mobile Commerce Ux Auditor Audit mobile shopping flows, identify conversion friction, prioritize UX issues, and suggest experiment backlogs for product teams, CRO specialists, and e-co... | |
| Mood Canvas Turn a vague emotion, theme, or aesthetic idea into a structured visual mood board blueprint. Use when the user wants a visual brief for design, photography,... | |
| Mood Color Mapper Translate a user's felt state into a color-based mood map with body cues, possible emotion words, likely needs, and one gentle next step under 10 minutes. Us... | |
| Mood Line Turn a user's described feelings, mood, or emotional state into a concise, resonant line | |
| Morning Pages Facilitator Guide users through a low-pressure, time- or page-based morning writing practice to help release thoughts without editing or over-analysis. | |
| Morning Ritual Planner Build a realistic morning routine around the user's real wake time, time budget, reliable anchor, night-before prep, and fallback plan for chaotic or low-sle... | |
| Moving Checklist Generate a personalized moving timeline & checklist based on your home info, timeline, and moving distance. | |
| Name Analyzer Analyze names for meaning, origin, cultural associations, and personality traits. Use when user wants to (1) understand the meaning of a name, (2) check name... | |
| New Job First Week Admin Board Create a first-week new-job admin board for access requests, forms, equipment, meetings, questions, deadlines, blockers, and follow-ups while avoiding passwo... | |
| New Product Launch Copilot Turn a product idea, new SKU, or collection launch into a channel-ready ecommerce launch brief, messaging matrix, readiness checklist, milestone timeline, KP... | |
| NextFromKnowledge Knowledge-to-action skill that turns notes, research, meeting summaries, documents, and knowledge graph outputs into the next action, decision, plan, or expe... | |
| Npc Dialogue Rehearser Rehearse a real-world conversation by modeling likely counterpart styles such as busy, defensive, friendly, or authority-like NPCs. Generate a natural openin... | |
| Nutri Calc Precise nutrition calculator — Chinese food database, goal-oriented macro tracking | |
| Nutrition Balance Tracker Track daily nutrition intake, hydration, and energy balance against fat-loss, maintenance, or muscle-gain goals. Use when the user wants to log meals, water,... | |
| Nutrition Planner Personal nutrition and meal planning system with calorie tracking and recipe recommendations | |
| Office Snack Drawer Map Organize and map one office snack drawer into zones with refill lines and stale-item checks to keep snacks visible, tidy, and easy to restock. |
35,051–35,100 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.