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 |
|---|---|
| youtube-video-api-skill This skill helps users automatically extract channel-level and video detail data from a specific YouTube channel via BrowserAct API. Agent should proactively... | |
| Beamer Pipeline Public Convert academic papers or notes into Chinese academic Beamer slides using a seven-phase local pipeline with pluggable agent execution and LaTeX compilation. | |
| Docx Chapter Clean Research-backed chapter pipeline: outline → parallel ACP research → MD synthesis → DOCX generation → source verification → screenshot verification (mandatory) | |
| Poi Clean Plan nearby places for dining, desserts, cafes, malls, and date spots using one local POI planning workflow. Best for queries like “附近有什么适合坐着聊天的咖啡店”, “帮我找地铁可... | |
| Unified Search Suite Unified web search + deep research suite. Default ordinary /unified_search queries route to deep search-layer mode (Exa + Tavily + Grok); the legacy merged t... | |
| Voipms Sms OpenClaw skill for sending and retrieving SMS messages via the VoIP.ms API (no Bitwarden dependency). | |
| SLS + ARMS 全链路问题排查 查询阿里云SLS日志和ARMS调用链，结合源码和数据库进行全链路问题排查。 完整流程：查日志 → 画调用链 → 定位源码 → 排查数据库 → 给出修复方案。 Use when: 用户说「分析sls」「分析问题」或想排查业务服务/线上接口/用户请求的报错或异常。 触发示例：「分析sls」「帮我查一下这个trace_... | |
| light-chaser 旅行摄影动态脚本助手，解决旅行者"去哪拍、何时拍、怎么拍、怎么走"四大核心痛点。将碎片化攻略转化为可执行的拍摄时间线。当用户提到旅行拍照、打卡、旅拍、摄影攻略、出行拍摄计划时使用此技能。 | |
| Seedance 视频提示词工业化生成 将剧本文本工业化转换为Seedance 2.0可用的视频提示词，包括文生图提示词、分组视频提示词、台词核对表和字段自检表。 | |
| ChangSheng Cross-session memory recovery for AI agents — your agent never cold-starts again. Always-loaded identity & todos, hash-indexed conditional reads cut recovery cost ~70% (~55-75% cumulative when the host already injects identity). Pure local, | |
| Mode Switch Kit Use when you toggle VPN, agents and services by hand. One command flips the whole machine stack together — VPN, background agents, local services, model tier — from one YAML mode matrix; the watchdog repairs the current mode and never reviv | |
| Agent Memory System OpenClaw Agent 长期记忆系统 - 温度模型 + 自动归档 + 知识提炼。让 AI Agent 拥有持久记忆，自动管理冷热数据，从经验中提炼可复用技能。 | |
| Food Factory Cost Pricing 食品工厂成本核算与分级定价专家技能。覆盖生产成本精准核算（直接材料/人工/制造费用/边角料残值）、全渠道销售成本核算（物流冷链/平台佣金/营销/售后）、分级定价方案生成（保本底价/出厂价/经销商价/商超价/线上零售价/大促最低价）。当用户提到食品成本核算、生产成本、定价方案、毛利率、经销商价格、出厂价、工厂定价时激活。 | |
| Food Production Sales Operation 食品产销双主体极简操盘工作体系，覆盖季度战略规划、周度执行管控、电商店铺核心指标管控、视觉包装标准、直播间标准化参数、高频问题终极解决方案。当用户提到食品产销操盘、电商运营体系、周度管控、直播运营标准、电商指标管控时激活。 | |
| Omni Channel Ecommerce Master 全能电商运营全链路闭环技能，覆盖平台规则合规、免费/付费流量运营、商品与供应链管理、转化优化、内容电商与直播、数据化运营与复盘、营销大促操盘、私域全域运营、团队管理、风险管控。全能电商运营核心能力清单。当用户提到电商运营、流量运营、直播运营、供应链管理、私域运营、数据复盘、营销大促、团队管理等时激活。 | |
| Pdd Food Category Master 拼多多食品类目全闭环运营技能包，专治老店起死回生、新店登顶类目TOP，覆盖致命风险兜底、老店绝症根治、新店长期登顶、全场景问题闭环解决、执行铁律五大模块。当用户提到拼多多食品运营、老店盘活、新店爆单、食安合规、违规降权、DSR拉升、流量急救、类目TOP时激活。 | |
| Otto Travel Local OpenClaw plugin for Otto Travel — search, compare, and book flights and hotels via Otto's MCP endpoint. | |
| openclaw-code-review-skill 对 Pull Request 或代码 Diff 进行结构化审查，使用多 Agent 并行审查 + 置信度评分过滤误报。触发：/code-review、审查 PR、代码审查 | |
| Locus Locus payment tools for AI agents. Use when asked to send payments, check wallet balances, list tokens, approve token spending, or process payment-related actions from emails. Also use for demos of Locus (YC F25) payment infrastructure — sc | |
| cli-skill-release Release engineering for zero-dependency Python CLI agent skills: releaser.py validates publish-readiness (a 0-100 score with real functional checks that actually boot your CLI), inventory/gap market intelligence, scaffold, CI, LICENSE(MIT-0 | |
| find-skills++ 技能生态的「安全策展 → 安装闸门 → 生态治理」全能工具，find-skills 的社区超级增强版（能力已超越原版与 skill-vetter 等同类）。 当用户用自然语言描述需求（"我想做个海报""帮我分析股票""有没有能做 X 的技能"），或明确说 "找个 skill / 找技能 / 安装技能 / find skills / 技能推荐 / 技能管理 / 卸载技能 / 技能安全审查 / 技能装太多太乱了"时触发。 原版与同类均不具备的差异化：① 安装前 AST 级安全扫描 | |
| invoice-merger 合并发票文件。PDF 按两两上下排版，图片按四宫格排版，统一裁剪线与安全边距，输出到 YYYYMMDD--已合并 目录，重复执行会自动跳过历史合并文件并按编号继续生成。 | |
| ClawdHub Publish Helper Prepare and publish an OpenClaw skill to ClawHub. Handles PII/secret auditing, generalization, env var extraction, directory scaffolding, git init, and the c... | |
| Food Channel Handle messages in a food-tracking channel by routing food intake events through a deterministic food tracker. Use when working in a dedicated food channel,... | |
| Medication Channel Handle messages in a medication-tracking channel by routing medication events through a deterministic medication tracker instead of freehand model judgment.... | |
| Resilient PDF Recover PDF extraction and summarization workflows when native PDF handling fails, hangs, times out, or rejects large files. Use when working with local or r... | |
| Sleep Channel Handle messages in a Discord sleep-tracking channel by grounding all sleep logging and summaries on the real sleep tracker and source Discord metadata. Use w... | |
| Snippets Sync Sync code snippets and notes between machines via file sync. Organized by language, rendered in any Markdown viewer (Obsidian, VS Code, etc.). | |
| Spotify Skill Control Spotify playback, search music, manage playlists, generate discovery playlists, and analyze listening habits via the Spotify Web API. Use when asked... | |
| Vitamin Tracker Channel Manage vitamin/supplement reminders across configurable daily time slots via cron jobs. Use when adjusting supplement schedules, adding/removing supplements,... | |
| FirstKnow — Portfolio Intelligence Portfolio news intelligence — monitors breaking news, SEC filings, price moves, and analyst actions for your stock/crypto/ETF holdings. Pushes personalized a... | |
| Sketch2CAD 手绘草图转CAD DXF文件。Use when user sends a hand-drawn sketch with dimensions and wants to convert it to an editable CAD (DXF) file. Automatically recognizes shape... | |
| retake-tv-agent Go live on retake.tv — the livestreaming platform built for AI agents. Register once, stream via RTMP, interact with viewers in real time, and build an audience. Use when an agent needs to livestream, engage chat, or manage its retake.tv pr | |
| Munger Decision Charlie Munger's mental model decision assistant. Analyzes your decision scenario, recommends the most relevant thinking models, and guides you through struc... | |
| Munger Decision Free Charlie Munger's mental model decision assistant. Analyzes your decision scenario, recommends the most relevant thinking models, and guides you through struc... | |
| professional-pdf-translator 通用长篇文献/小说多页PDF逐页自动提取、匹配用户提供的本地术语表并翻译追加至DOCX的自动化工作流。适用于任何具有特定受众、包含大量专有名词的长文献、小众长篇小说、学术论文、技术白皮书等PDF翻译场景。用户自行提供原文PDF、专业术语对照表及输出路径。 | |
| Build Scaffold new Aomi apps and plugins from API docs, OpenAPI/Swagger specs, or SDK references. aomi-build generates production-ready Rust SDK crates (lib.rs, cl... | |
| Transact Fund, review and reconcile durable Aomi payment Commits | |
| Demand Discovery AI Validate a startup idea with real demand signals before building it, using Demand Discovery AI™. Use whenever the user asks "should I build this?", wants to... | |
| Agb Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with w... | |
| Copilot Cli Skill Run GitHub Copilot CLI from OpenClaw for coding tasks in a target project directory. Use when the user asks OpenClaw to use Copilot for implementation, debug... | |
| Multi Agent Sync Coordinate multi-agent tasks with visible group updates. Use when delegating work across multiple topic agents and the user needs transparent progress in-gro... | |
| OpenAI Codex Operator Run OpenAI Codex CLI from OpenClaw for coding tasks in a target project directory. Use when the user asks OpenClaw to use Codex for implementation, debugging... | |
| WTT OpenClaw WTT channel plugin distribution entry. Installs/enables @cecwxf/wtt and bootstraps channels.wtt with agent_id + agent_token from wtt.sh. | |
| WTT Plugin OpenClaw WTT channel plugin distribution entry. Installs/enables @cecwxf/wtt and bootstraps channels.wtt with agent_id + agent_token from wtt.sh. | |
| WTT Skill WTT (Want To Talk) agent messaging and orchestration skill for OpenClaw with topic/P2P communication, task and pipeline operations, delegation, IM routing, a... | |
| Crypto Wave Scanner Visual crypto futures wave scanner that detects optimal entry and exit points across 10 coins in real time. Scores each coin 0-6 using EMA9/21/50 stack, RSI... | |
| Gmail Cleaner Clean and organize Gmail accounts in bulk. Use when asked to clean Gmail, remove spam, trash newsletters/promotional emails, bulk-delete emails by sender, cr... | |
| Slid Phi Labs stack Discover the full Slid Phi Labs stack — freemium compression suite, dual human/agent surfaces, CuNi, Agent^Rider, Quikgater, TEACHAiD/SPU, Olympiad, and x402 commerce. | |
| TEACHAiD · Slid Phi University Discover and use Slid Phi University (SPU) powered by the TEACHAiD engine — personal teacher, curriculum, school factory, bursar, and double-entry books. Dual doors for humans and agents. |
18,701–18,750 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.