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 |
|---|---|
| Douyin Script Writer Turn a topic into a Douyin-ready short video script with hook, storyboard, captions, and BGM suggestions. | |
| Dream Interpretation 用中文理解并解读用户描述的梦境：优先上网搜索“周公解梦/解梦/梦见/梦到”相关中文资料，提炼传统民俗解释；当用户还想知道现实含义时，补充一段现代心理学视角。Use when the user describes a dream, asks“这个梦什么意思/帮我解梦/周公解梦/梦见XX代表什么/梦到XX是什么意思”... | |
| Dry Clean Pickup Schedule Create a simple dry-cleaning pickup tracker and bag tag note template for dropped-off garments, pickup dates, special notes, and reminder text, without handl... | |
| Ecommerce Customer Journey Mapper Generates a heuristic markdown report mapping e-commerce customer journeys, identifying friction points, and prioritizing actionable improvements without rea... | |
| Ecommerce Dropshipping Product Research Evaluates dropshipping products by scoring demand, competition, margin, creative fit, and risk to recommend go, test, or reject decisions. | |
| Ecommerce Pulse Board Synthesize ecommerce operational health across channels, inventory, marketing efficiency, customer metrics, and fulfillment into a single operator pulse brie... | |
| Ecommerce Sustainability Advisor Generate practical e-commerce sustainability improvement plans, packaging recommendations, claim-risk cautions, and phased action roadmaps for founders, oper... | |
| Efficiency Manager Local execution coach that captures activities, reviews time use, suggests the best next move, and helps build realistic day plans from task inputs, deadline... | |
| Elevator Outage Access Plan Build a temporary access coordination plan for an elevator outage, including affected-person roster, alternative routes, contact assignments, delivery guidan... | |
| elm Help users make better Eleme ordering decisions from public merchant and promotion information. Use when the user wants to compare Eleme stores, judge whethe... | |
| Emotion Journal Help users record emotions, identify triggers, notice patterns, and build a gentle self-observation habit | |
| Energy Peak Finder Turn several days of observation into a simple energy pattern review with likely peak windows, low windows, disruptors, task matching, and a one-week experim... | |
| Enforcement Assistant Assist with civil enforcement application (执行申请) preparation and process guidance after obtaining a court judgment. Provides procedural guidance only. | |
| Enlightenment Provide grounded knowledge, distinctions, and reflective support around enlightenment-related topics such as 开悟, 觉醒, 见性, 无我, 空性, spiritual insight, and inner... | |
| Ergonomic Bag Pack Check Use when a user wants a practical audit for a backpack, work bag, school bag, purse, messenger bag, or daily carry that feels heavy, awkward, or uncomfortabl... | |
| Event Ticket Help Sheet Build a time-sensitive event ticket help sheet with ticket facts, proof bundle, official contact paths, arrival plan, and on-site script for confusing ticket... | |
| evidence organizer Organize and structure evidence for legal proceedings. Use when the user asks about 证据整理、证据清单、证据链、怎么组织证据、准备证据、证据目录, or wants to organize evidence for a case.... | |
| Expense Approval Workflow Designer Creates structured expense approval workflow frameworks with actionable recommendations and next-step checklists for process design. | |
| Expense Categorization Optimizer Provides structured guidance, templates, and recommendations to optimize expense categorization for improved financial tracking and planning. | |
| Family Conflict Mediator Analyze family conflicts calmly and provide mediation steps, dialogue suggestions, and resources for non-emergency situations. | |
| Family Crypto Explainer A plain-language explanation helper for talking to family members about crypto involvement. Use when discussing crypto with non-crypto people. Prompt-only. | |
| Family Finance Manager Family Finance Health Manager / 家庭财务健康管家. Provides comprehensive family financial management including income/expense analysis, savings goal breakdown, insur... | |
| Family Memory Timeline 自动分析家庭照片和对话，生成结构化时间线故事，帮助回顾和珍藏家庭重要记忆。 | |
| Family Nutrition Planner 家庭营养规划师 - 根据家庭成员健康需求、饮食偏好和营养目标， 生成营养均衡的一周菜单、食材采购清单和分餐计划。 | |
| Feedback Loop Feedback Loop - Collect, analyze, and act on user feedback for continuous agent improvement | |
| Financial Education Path Designer Creates structured financial education frameworks with actionable recommendations and clear next-step checklists for learning paths. | |
| Financial Goal Progress Tracker Provides structured analysis, actionable recommendations, and next-step checklists to help track and manage progress toward financial goals. | |
| Financial Health Check Analyzer Provides structured financial health assessments with templates and actionable recommendations based on user-provided context and goals. | |
| Financial Ratio Benchmarker Provides financial ratio benchmarks with structured analysis, actionable recommendations, and next steps without executing code or external calls. | |
| Financial Report Interpreter Interprets income statements, balance sheets, and cash flows into plain-language insights, ratio analysis, and management questions for financial review. | |
| Find Items Search for products on Chinese e-commerce platforms (Taobao, JD, Vipshop, PDD, Meituan, Ele.me, etc.) using web search. This skill helps users find products,... | |
| Focus Master Manage tasks with configurable Pomodoro timers, track time spent, analyze time allocation, block distractions, and generate efficiency reports. | |
| Focus Session Timer Build a focused work session card with the right session mode, a visible finish line, start ritual, distraction capture plan, break rule, and interruption re... | |
| Focus Sprint Coach Turn 'I should work' into 'I'm in the zone': a cognitive sprint coach that helps you start, sustain, and optimize deep focus through activation rituals, dist... | |
| Freshippo Shop Freshippo (盒马鲜生) in safe decision-assist mode: fresh grocery selection, shopping-list planning, delivery-window strategy, price/freshness checks, and ma... | |
| Game Controller Charging Dock Map Create a dock layout card for game controllers, with assigned slots, cable labels, return rules, charge routine, and a shared setup reset checklist. | |
| Game Inventory Manager Sort clutter, obligations, files, objects, or attention drains through a game inventory lens. Classify what should stay equipped, stay in quick access, move... | |
| Gaming Backlog Guide Match the user’s current mood, available time, platform habits, and energy level to the right kind of game experience, then suggest a low-friction way to sta... | |
| Gaming Session Scheduler Fit gaming into real life with safe play windows, launch conditions, stop rules, and guilt-reducing balance guidance. Use when the user wants to enjoy games... | |
| 高考志愿填报助手 基于位次和规则辅助生成高考志愿方案 | |
| Generosity Practice Designer Designs sustainable generosity practices that align personal values with meaningful giving. | |
| Gentle Reframe Companion Gently reframe emotional distress into a more accurate and bearable narrative | |
| Gift Idea Match Board Create a privacy-light gift-idea match board that maps recipients, occasions, interests, constraints, and thoughtful idea candidates without collecting sensi... | |
| Git Blame Production code audit via git blame. Natural language risk analysis — overtime commits, scattered changes, no-PR-review merges, and impact domain tracing for... | |
| Goal Chunking Helper Helps break a big goal into clear milestones, next actions, dependencies, and a review checkpoint for actionable progress and reduced overwhelm. | |
| Grocery Price Comparer Compare fresh grocery prices across Hema, Dingdong, Meituan Maicai & more — find the best deals on your shopping list. | |
| Group Buy Helper Analyze group-buy and bargain campaigns, estimate success probability, and suggest participation strategies | |
| Growth Loop Orchestrator Orchestrate growth loops across the skill portfolio by connecting usage, feedback, improvement, and adoption into self-reinforcing cycles. Use when designing... | |
| Growth Milestone Celebrator Recognize genuine growth with evidence-based milestones, meaningful celebration, and a next step that sustains momentum without empty praise. | |
| Guest Ready Home Reset Build a fast guest-ready home reset for people expecting visitors soon, including a 60-minute reset plan, supplies list, quick task assignments, guest essent... |
34,951–35,000 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.