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 |
|---|---|
| Underground Cultural District MCP server for The Underground Cultural District — 16 tools including 13 free developer utilities (UUID, JSON, Base64, hashing, JWT, regex, cron) plus browse... | |
| PCBClaw pcb; pcb modify/resume/reprice/package: design and verify editable KiCad boards, JLCPCB manufacturing bundles, and assembly pricing with supplier review. | |
| android-auto-controller 控制 Android 手机的终极工具。具备视觉状态感知、自动关闭干扰弹窗、模拟人手操作的能力。内置严格的反幻觉校验机制和防绕过限制，以真实的屏幕视觉反馈为唯一判断标准。 | |
| Apple Notes Use this skill when the task involves reading, searching, creating, editing, organizing, or moving Apple Notes on macOS. This includes finding notes, creatin... | |
| picture-book-maker 制作图文并茂的绘本，支持从主题策划、故事创作、角色设定到分镜设计和最终打包输出的完整流程，适用于教育绘本、儿童故事、寓言故事等场景 | |
| Paid Database Access AI 接入付费学术数据库（IEEE/Scopus/EV/ACM）的权限桥接层。 通过浏览器 CDP 借用用户登录态，搜索→提取→去重→补摘要→评分→输出。 Zero-token abstract handling. | |
| Doc2Slides Convert documents or text into PDF slide presentations via the Ruyi Converter API at nyoi.io. Use this skill whenever the user wants to create slides, presen... | |
| MEP Data Extraction & Review Ledger Extracts MEP rough-quantity working papers and material-plan drafts from installation drawings or scanned indexes. Groups pipes by circuit and size, expands wire cores and reserved lengths, and estimates cable, cable tray, water/supply, spr | |
| Cross-Discipline Clash Review Reviews DWG/DXF drawings or parsed contracts for cross-discipline 2D overlap and attribute-conflict candidates. Uses axis-grid location when available and degrades honestly when axis data is missing; outputs are human-review candidates, not | |
| CAD Drawing Data Extraction: Tables, Points, Coordinates, Notes and Evidence 读取 DWG/DXF，提取标注、几何证据、图层/块语义、MEP 拓扑、图纸对比、钢结构/市政识图候选和规范图集索引；不输出最终工程量 | |
| CAD Tmp Probe 读取 DWG/DXF，提取标注、几何证据、图层/块语义、MEP 拓扑、图纸对比、钢结构/市政识图候选和规范图集索引；不输出最终工程量 | |
| 网盘通 跨 macOS / Windows / Linux 的通用下载调度层，统一通过 Agent/MCP/CLI、Web UI 和浏览器插件投递任务；调度本机或可选 Docker/远程引擎。不解析分享页、不提取直链、不绕过鉴权/限速/风控/DRM。 | |
| 对话记忆管家 · Memory Orchestrator 长对话记忆编排技能。负责会话开始时的记忆检索、自动监测每个对话框的对话轮数与 token 用量，轮数阈值或 token 阈值（默认 15 万）哪个先到先触发，达到阈值（8 轮或 15 万 token，先到者为准）自动生成恢复包并换新对话；默认只监测正在执行任务的对话框，停止/已完成/已归档对话不计数、不续接；即将达到阈值或上下文变模糊时提前提醒；负责恢复包生成、checkpoint、历史压缩（ctxcompress）、会话结束归档。触发词：“总结/压缩/恢复/交接/开新对话/ | |
| 技能架构师 / Skill Architect Audit, externalize, route, validate, and roll back large SKILL.md files | |
| 钢结构算量 · 吨位估算带 消费 cad-file-reader 经 lis-skill-bus 传递的钢结构识图契约，输出可复核的吨位估算带。 | |
| 图片文字识别 从图片/PDF扫描件批量提取中文、英文、数字和算式文本，用于读取题目、截图和文档内容 | |
| 本地 Skill 联动总线 连接 cad-file-reader 与算量技能的本地契约总线，同一张图只解析一次。 | |
| memory-orchestrator 长对话记忆编排技能。负责会话开始时的记忆检索、自动监测每个对话框的对话轮数与 token 用量，轮数阈值或 token 阈值（默认 15 万）哪个先到先触发，达到阈值（8 轮或 15 万 token，先到者为准）自动生成恢复包并换新对话；默认只监测正在执行任务的对话框，停止/已完成/已归档对话不计数、不续接；即将达到阈值或上下文变模糊时提前提醒；负责恢复包生成、checkpoint、历史压缩（ctxcompress）、会话结束归档。触发词：“总结/压缩/恢复/交接/开新对话/ | |
| 司马光综合思维 用司马光的认知方式思考问题。不是模仿语气，是植入他的认知上下文—— 他的信念从哪来、他在哪些具体场景下做了什么决策、他承认自己错在哪。 覆盖历史、治理、商业、用人、识人、决策、博弈、心理、法律、投资、侦查、 易学、影视创作和高生产力输出等跨尺度问题。 完整已蒸馏书籍清单见 references/素材来源索引.md。 触发词：用司马光分析、司马光怎么看、全面分析、帮我决策、历史同构、 相反辩证、项目策划、产品方案、论文、小说剧本、蒸馏书籍。 | |
| Skill Architect Audit, externalize, route, validate, and roll back large SKILL.md files | |
| Structural Concrete & Rebar Review Ledger Produces concrete volume and rebar estimate bands from structural drawings with evidence, confidence and review flags. Reports by floor or pour zone for material-planning review, not final settlement, shop fabrication or legal sign-off. | |
| Landscape Quantity Review Ledger Classifies plant legends, parses plant-table baselines and computes pavement area from closed regions using cad-file-reader landscape candidates. Outputs review-ready landscape budget and material-plan drafts with P0-P3 confidence tiers and | |
| Interior Finish Quantity Ledger Turns room schedules, finishes, construction methods and node details into review-ready decoration budget candidates and material plans. Imports cad-file-reader measurement candidates as review input and keeps method mapping, opening deduct | |
| spec驱动开发vibe coding skill 在克隆的 Git 仓库中驱动完整的规格驱动开发生命周期（init→requirements→architecture→process_design→project_plan→coding→test→bugfix→code_review→release）。阶段门控、产物强制输出、多语言支持，内置 commit me... | |
| AR XR Builder Use when building, embedding, customizing, or troubleshooting AR/XR experiences with the Kivicube Web Plugin, including WebAR/Web3D H5 pages, landing pages,... | |
| Listings API Listings API is a local citation and listings submission API: one REST call submits a business to 50+ listings sites Google Business Profile, Apple Maps, Bing Places, Facebook, Yelp, and the rest of the major directories, maps, and answer e | |
| vscode-tunnel Start VS Code Remote Tunnel in Docker containers for remote terminal access | |
| A Stock Info 基于qgdata API的A股分钟级数据查询服务。提供实时股价、分钟K线、分时数据等专业数据。 | |
| Astock Data 🚀 专业A股量化数据API：1/5/15/30/60分钟实时K线 + 智能数据质量检测。覆盖沪深3000+股票，毫秒级响应，无限量调用。量化交易、算法策略、高频交易的理想数据源。 | |
| QMT Strategy Autopilot 一句话需求自动生成并执行国金QMT策略（封闭式澄清 + 双源数据 + 实盘语义） | |
| 量化策略助手 量化策略助手：自然语言→策略生成→回测→优化→QMT模拟/实盘。三轮交互闭环。 | |
| xlsx Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatt | |
| Dust Language Architect Expert Dust Language Architect grounded in the full Dust ecosystem, with the Dust Programming Language Specification as canon and all dustlang organization r... | |
| Gibber Language Skill expert gibber language | |
| Phase Theorist Expert Phase Theory interpreter and researcher grounded in the full cloned phase-theory repository, treating every file in the skill directory as part of the... | |
| XDV Engineer Expert XDV Engineer grounded in the full XDV platform, with the XDV Specification as canon and all XDV organization repositories treated as supporting corpus. | |
| xhs-comment-scraper 小红书评论爬虫。当用户在聊天中发送一个小红书博主主页链接时，自动抓取该博主所有笔记下的评论区数据，保存为本地JSON文件，并生成分析可视化报告。触发条件：用户发送的链接包含 xiaohongshu.com/user/profile 或类似博主主页链接。 | |
| A Stock Analysis.Bak 提供沪深北交所A股实时行情查询、分时成交量分析、主力资金动态判断及持仓盈亏管理功能。 | |
| A Stock Analysis Conflict 提供A股实时行情、分时量能分布、主力资金动向分析及持仓盈亏管理，支持沪深北交所股票。 | |
| A Stock Analysis Litiao 提供A股实时价格、涨跌幅、成交量及分时量能分析，支持主力资金动向判断和持仓盈亏管理。 | |
| Automation Workflows Conflict Design and implement automation workflows to save time and scale operations as a solopreneur. Use when identifying repetitive tasks to automate, building wor... | |
| Automation Workflows Litiao Design and implement automation workflows to save time and scale operations as a solopreneur. Use when identifying repetitive tasks to automate, building wor... | |
| Business Writing Conflict You are a professional business analyst, skilled in writing various industry research reports, business insights, consulting analyses, company research repor... | |
| Business Writing Litiao You are a professional business analyst, skilled in writing various industry research reports, business insights, consulting analyses, company research repor... | |
| Cctv News Fetcher Conflict Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date. | |
| Cctv News Fetcher Litiao Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date. | |
| Clawdbot Logs Litiao Analyze Clawdbot logs and diagnostics. Use when the user asks about bot performance, response times, errors, session stats, token usage, API costs, or wants... | |
| Copywriter Litiao Write compelling UX copy, marketing content, and product messaging. Use when writing button labels, error messages, landing pages, emails, CTAs, empty states... | |
| Daily Ai News Skill Litiao Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Uses Tavily API (preferred) or Brave Search (fa... | |
| Data Analysis Litiao Turn raw data into decisions with statistical rigor, proper methodology, and awareness of analytical pitfalls. |
49,251–49,300 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.