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 |
|---|---|
| consensus-guard-core Open-source Consensus.Tools skill for governed AI decisions with board-native artifacts, strict JSON contracts, and deterministic policy behavior. | |
| consensus-interact Operate consensus.tools end-to-end (post jobs, create submissions, cast votes, resolve results) using either a local-first board or a hosted board (depending... | |
| consensus-permission-escalation-guard Pre-execution governance for IAM and permission escalation changes. Use when an agent or workflow proposes granting, expanding, or assuming higher privileges... | |
| consensus-persona-engine Deterministic persona reputation engine that applies guard decision effects to persona_set state and emits explicit reputation_delta artifacts. | |
| consensus-persona-generator Generate and persist reusable persona panels (persona_set artifacts) for consensus decision workflows. This skill initializes evaluator diversity for downstr... | |
| consensus-persona-respawn Ledger-informed persona lifecycle management. Replaces low-performing personas with successor personas derived from mistake patterns in board decision histor... | |
| Consensus Publish Guard Persona-weighted governance for outbound publishing (blog, social, announcements). Prevents unsafe public claims via hard-block checks, weighted consensus, r... | |
| consensus-send-email-guard Persona-weighted pre-send email governance for AI systems. Produces APPROVE/BLOCK/REWRITE decisions, writes decision artifacts to the board ledger, and retur... | |
| consensus-support-reply-guard Risk-aware support response governance with persona-weighted consensus. Detects legal/sensitive/confidentiality issues, applies hard-block policy checks, and... | |
| design-panel Multi-persona design review. Dispatches 4 UX/UI designer personas in parallel against a live web app, then converges on the highest-impact changes via cross-... | |
| Gstack Orchestrate Master orchestration skill that takes a gstack implementation plan and ships it via parallel Claude Code subagents in isolated git worktrees. Sits between /a... | |
| Parallel Orchestrate Master orchestration skill that takes a gstack implementation plan and ships it via parallel Claude Code subagents in isolated git worktrees. Sits between /a... | |
| Coding Pronoun Prompt Resolver Detects ambiguous pronouns, vague referents, and bare imperatives in user messages and flags them for resolution using conversation context. Zero-latency det... | |
| Thumbnail QA Thumbnail image QA: browse every page, detect images poorly cropped in their containers, compute fine-grained object-position values, and auto-fix with befor... | |
| 开饭 提供全球餐饮服务的点餐、推荐与订单管理，确保安全支付与实时物流查询的专业私人餐饮管家。 | |
| Archive Project Organize completed projects into searchable archives with session transcript backup. | |
| Language Coach Multi-language writing coach for grammar, word choice, collocations, and idiom errors. Supports English, Chinese, Spanish, French, and Japanese. Activated vi... | |
| Language Coach Multi-language writing coach for grammar, word choice, collocations, and idiom errors. Supports English, Chinese, Spanish, French, and Japanese. Activated vi... | |
| Project Coordinator Spawns an isolated Project Coordinator session that owns a project's context, breaks work into tasks, and spawns subagents for parallel execution. | |
| paper-parser-skill CLI tool to search, download, and parse academic papers from arXiv into AI-friendly Markdown using MinerU API. | |
| Claude Memory Structured memory system for OpenClaw agents. Provides a 4-type classification (user/feedback/project/reference), layered architecture (MEMORY.md + topics/ +... | |
| kaiji-fitness-coach 基于 free-exercise-db 的专业健身教练知识体系，覆盖训练计划、动作教学、数据分析、营养指导、进阶周期化全流程。 触发场景： - "帮我设计训练计划"、"我想健身"、"怎么增肌减脂" - "这个动作怎么做"、询问训练建议、健身相关问题 - 提供 Workout Timer App 数据报告、训练数据分析 - "我是新手怎么开始"、"调整训练计划"、"进阶方案" - 营养/饮食相关健身问题 | |
| cursor-agent-cli Cursor Agent CLI integration - AI-powered coding agent for terminal. Use when user mentions Cursor Agent, agent CLI, AI coding, code generation, refactoring,... | |
| tapd-api TAPD API 完整集成。实现 18 个模块、70+ API 方法，支持 OAuth 和 Basic Auth 认证。涵盖需求、任务、缺陷、迭代、测试、Wiki、工时等所有 TAPD 功能。 | |
| safeclaw Security compliance checker for MCP/LLM applications. Performs non-invasive security assessments on configuration files. | |
| Weekly Report (OpenClaw) 自动化工作周报生成系统。支持自动登录周报系统、获取团队周报数据、使用 AI 进行内容提炼总结、生成格式化的 Word 文档。 触发场景：(1) 用户要求生成周报 (2) 用户询问本周/上周工作总结 (3) 用户提到"周报"、"weekly report"、"工作总结" (4) 用户需要汇总团队成员工作内容 | |
| X Followings Digest Auto-fetch latest tweets from your X/Twitter followings and generate structured AI digest. Supports custom time ranges: 1 day, 3 days, 7 days, or custom.
自动抓取X/Twitter关注列表的最新推文，并使用AI分析师提示词生成结构化日报。支持自定义时间段：1天、3天、7天或自定义天数。
**Trigger Words:* | |
| X Manual Surf Notes (手动刷帖笔记) 手动操控浏览器在X首页For You浏览、点开帖子，提取内容翻译成中文，去重后按时间内容链接评论追加笔记。 | |
| LLM Skirmish Install and use the Skirmish CLI to write, test, and submit JavaScript battle strategies. Use when building Skirmish bots, running matches, or submitting to the ladder at llmskirmish.com. | |
| 中国企业报税员 核验中国税收政策，计算常见税费，整理申报底稿与复核清单 | |
| Video Notes 把 YouTube / 哔哩哔哩视频变成一份精美的结构化HTML笔记。自动提取字幕、识别关键时刻并截图、生成核心论点总结和 SVG 图表，输出带侧边导航和全文搜索的单文件 HTML 文档。适用于技术演讲、公开课、播客、产品发布会等场景。This skill should be used when a user provi... | |
| LG ThinQ Control LG smart appliances via ThinQ API. Use when user asks about their fridge, washer, dryer, AC, or other LG appliances. Supports checking status, changing temperature, toggling modes (express, eco), and monitoring door status. | |
| TickTick API TickTick task manager integration. List projects and tasks, create new tasks, complete tasks, delete tasks. Use when the user wants to manage their to-do list, add reminders, check pending tasks, or mark tasks as done. Requires OAuth setup | |
| TickTick Tasks TickTick task manager integration. List projects and tasks, create new tasks, complete tasks, delete tasks. Use when the user wants to manage their to-do list, add reminders, check pending tasks, or mark tasks as done. Requires OAuth setup | |
| Kaipai Process image or video watermark removal and quality restoration with Kaipai AI. Always discover the remote catalog before naming or selecting a task: V2 uses the returned server task metadata; legacy aliases are allowed only when the legac | |
| memory-attention-router Deterministic long-term memory routing for OpenClaw. Route, write, reflect on, and refresh reusable memory for multi-step agent work. Use when the task depen... | |
| Private Agent Commerce Protocol Build and review private A2A commerce workflows with P-ACP packages, privacy boundaries, Solana settlement plans, and receipt proofs. | |
| Ledgermind Give your OpenClaw agent a wallet and a credit score. Hire other AI agents (on-chain escrow, independent grading, pay-only-on-pass) or earn as a worker on th... | |
| Business Blueprint Use when turning presales requirements, meeting notes, or solution materials into editable business capability blueprints, swimlane flows, and application ar... | |
| Business Blueprint Skill Use when turning presales requirements, meeting notes, or solution materials into editable business capability blueprints, swimlane flows, and application ar... | |
| kai-slide-creator 生成零依赖 HTML 演示文稿 — 21 种设计预设，视觉风格探索，播放/演讲者模式。适用于路演、产品发布、技术分享等场景。 | |
| Business Blueprint Skill Use when turning presales requirements, meeting notes, or solution materials into editable business capability blueprints, swimlane flows, and application ar... | |
| Kai Docx Generator Generate professional .docx documents from Markdown text or fill data into .docx templates. Use when: converting markdown to Word, generating reports/contrac... | |
| Kai Export PPT Lite Export HTML presentations to editable PPTX slides using pure Python without browser dependencies, ideal for sandbox environments and limited runtimes. | |
| Kai Html Export Export any HTML file to PPTX or PNG, or publish HTML to a public share URL. Use when the user wants to convert an HTML presentation to PowerPoint, screenshot... | |
| Kai Report Creator V1.23.3 Publish Use when the user wants to CREATE or GENERATE a report, business summary, data dashboard, or research doc — 报告/数据看板/商业报告/研究文档/KPI仪表盘. Handles Chinese and Eng... | |
| Slide Creator 生成HTML演示文稿/幻灯片 — 22 种风格模版，播放/演讲者模式。适用于路演、产品发布、技术分享、方案宣讲等场景。 | |
| Strategic Decision CEO/executive-mode strategic decision making. Challenge premises, diagnose problems, design definitive strategies. Four modes: AGGRESSIVE (dream big), SELECT... | |
| Report Creator Use when the user wants to CREATE or GENERATE a report, business summary, data dashboard, or research doc — 报告/数据看板/商业报告/研究文档/KPI仪表盘. Handles Chinese and Eng... | |
| Batch Search Monitor 批量搜索监控 - 关键词定时搜索、结果告警、数据导出 |
44,051–44,100 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.