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 |
|---|---|
| mapulse-korea 한국주식 analyst Telegram bot. Monitors KOSPI/KOSDAQ, tracks watchlist, delivers AI briefings, answers natural-language questions in Korean/Chinese/English. Cove... | |
| tss-api 提供跨链交易查询服务，包括获取交易高度、交易列表、订单和交易哈希对应的详细跨链交易记录与状态。 | |
| Office Document Specialist Suite 1.0.2 Advanced suite for creating, editing, and analyzing Microsoft Office documents (Word, Excel, PowerPoint). Provides specialized tools for automated reporting... | |
| Open source problem-solving workflow Open source problem-solving workflow: ALWAYS search the project's GitHub/GitLab issue tracker and check the latest version BEFORE attempting custom workarounds.
Use this skill whenever encountering bugs, errors, or unexpected behavior in an | |
| tyxh-lc 查询患者信息，支持通过患者编号/ID获取患者详情（无需认证） | |
| trailsnap-cli TrailSnap CLI 命令行工具，用于查询照片、相册、标签、位置和人物等信息。当用户需要查看照片、相册数据时调用此技能。 | |
| clawpacker Use when exporting, importing, packaging, cloning, restoring, or moving an OpenClaw agent between machines or instances, especially when the user mentions cl... | |
| Openrouter Usage Track OpenRouter API spending — credit balance, per-model cost breakdown, and spending projections from OpenClaw session logs. | |
| project-factory Bootstrap a new OpenClaw automation project using a four-phase workflow: Phase 0 — LLM reasoning: infer project type, flowchart structure, and node draft fro... | |
| Convbox DTC Marketing Skills — ROAS Diagnosis & Attribution Analytics Diagnose ROAS decline & attribution gaps for DTC storefronts. Compare true first-party ROAS vs Meta/Google reported ROAS. Covers growth health, ad performance, creative diagnosis, conversion, retention, budget optimization & profit analysis | |
| Agent Orchestrator Multi-agent collaboration and task orchestration. Decompose complex tasks, spawn sub-agents, coordinate execution, and synthesize results. | |
| Drop Pick Cross-platform product selection and sourcing analysis for distributors and dropshippers. Uses opencli plugins (aliexpress, alibaba-api buyer API, amazon) to... | |
| Ruitian Html 生成符合瑞天紫色渐变主题的企业级 HTML 文档，支持卡片布局、渐变表格、流程图和移动端响应式设计。 | |
| 微信文章读取 读取微信公众平台文章内容（mp.weixin.qq.com）。当用户发送微信文章链接、需要读取微信文章内容、提取公众号文章时自动激活。支持突破微信反爬限制，获取完整文章文本。 | |
| VBrokers Trading VBrokers (华盛通 VCL HK) trading automation via OpenAPI Gateway running on localhost port 11111. Use when: setting up VBrokers or 华盛通 account access, authentica... | |
| 多个飞书 Automated setup and configuration of Feishu/Lark bots with OpenClaw. Use when creating multiple Feishu bots with independent workspaces, memories, and dedica... | |
| feishu-duoge002 批量创建多飞书机器人，每个独立记忆、存储、大模型配置和连接，实现多角色多账号完全隔离管理。 | |
| fortune-master-suanming(算命) 八字命理专业分析技能。专注八字/四柱命理分析（含日主旺衰、调候分析、格局判定、十神配置、用神选取、地支藏干、合冲刑害、气势流通、大运流年、具体年份分析）。每个结论都有推理说明和经典依据。 | |
| 自动视频工具工作流 自动视频工作流：抓新闻、生成口播文案、华声生成MG视频、导出并发布到B站，含Fabric封面文字注入与B站投稿表单填写。 | |
| 九维雷达V3.0终极选股系统 九维雷达V3.0终极选股系统——基于行为金融学、量化因子与网络分析的中国A股选股框架，专为筛选"未来一年翻倍潜力股"设计。当用户需要：筛选股票池中翻倍概率最高的标的、全A股扫描输出S级TOP名单、对单只标的做九维深度评分(估值/超跌/质量/景气度/NLP情绪/网络结构/预期差/动量择时/市值弹性)、构建投资组合、讨论三档建仓与止损风控时，调用此skill。 | |
| 询问笔录 Builds and operates an inquiry transcript generator. Invoke for基本案情生成询问提纲、笔录分析、涉案人员提取、模板化笔录生成或复刻网页工具. | |
| Project OS Organizer Privacy-first, chat-first project manager for vibe coders. Track projects, capture updates, and resume work across local folders, Claude/Codex, and GitHub wi... | |
| Tra Cuu Phat Nguoi Tra cứu phạt nguội phương tiện tại Việt Nam. Use when user asks to check traffic fines in VN by license plate (ô tô/xe máy), especially via VNeTraffic-style... | |
| Tiexue Vision Recognizes text (Chinese/English), objects, and scenes in images from chat, documents, or local files, with optional translation and auto-saving results. | |
| Spendex AI Router Smart AI router — automatically picks the best & cheapest LLM for every prompt. BYOK, tracks costs, enforces budgets. Supports 25+ providers. | |
| CapForge Austin Liu｜从 GitHub 开源项目中提取“可复用能力资产”：扫描代码结构→产出 capability.md/transform-plan.md→域归类→格式校验（CapForge 本体不做 LLM 分析） | |
| activity-duration-estimation 活动历时估算 + WBS工作分解 + 项目文档生成 + 经济效益分析 + 挣值管理（Activity Duration Estimation & WBS & Project Docs & Economic Analysis & EVM）—— 支持三点估算/蒙特卡洛四种方法 + WBS项目规划与分解 + 项目文档双... | |
| analysis-toolkit 检验检测行业质量控制和数据分析工具箱。覆盖室内质控、室间比对、批次间比对、方法验证、趋势监控五大场景。方法通用，跨领域适用。 | |
| color-toolkit-turn 专业颜色工具集，支持颜色编码转换、对比度计算、智能颜色推荐、HTML预览生成。适用于UI设计、无障碍开发、配色方案生成等场景。 | |
| drawiodo draw.io 自动做图 Skill。当用户要求画图、生成图表、做架构图、流程图、UML、ER 图、时序图、思维导图等时触发。生成 .drawio 文件并用 draw.io 打开。支持思考-确认-迭代-版本回溯的完整工作流，8 个 Hook Point 安全校验。 | |
| everything-search-breadmemory 基于 Everything/es.exe 的本地文件搜索引擎 + 面包屑知识管理系统 + 艾宾浩斯复习引擎 + 拓扑甜甜圈知识关联。 | |
| git-sync 全平台统一发布工具。支持 skills 和 agents 的 Gitee/GitHub/ClawHub/SkillHub/PyPI 同步与 Release 创建，LLM 驱动的文件过滤与脱敏。 | |
| hug-html 8种原子组件自由组合 + 3级约束, cell merging, two-level module system (base + composite), 7+ built-in templates, grid-aware visual editor, style presets, post-generation... | |
| latex-modular LaTeX 模块化组合技能。提取 LaTeX 文档头/组件（表格、图片、列表、章节样式）作为可组合模块，通过 Python 脚本稳定组合生成不报错的 lualatex 文档，支持从原始 LaTeX 代码重构进模块化体系。 | |
| local-rag-builder 本地 RAG 系统搭建技能，支持环境检测修复、嵌入模型多源下载、5种切分策略 + GuardStack + 后处理 + 插件注册、多知识库管理 + 自动分类规则、可调 Prompt、Web 可视化配置 + 极客模式 + 模板管理 | |
| memory-pet 宠物记忆压缩技能 - 通过文本块宠物交互触发记忆保存。纯ASCII文字图，Python全量管理，亲密度衰减与逃跑机制，跨平台智能体记忆系统。 | |
| novel-weaver 结构化小说写作辅助技能。场景配置→大纲生成→因果链双重验证→pipeline 流程门禁→子结构先行规划→情绪混合系统→文风约束→人格驱动→分段写作→连通性补充→风格校验+逻辑检查(含实体状态+关系链)+大纲忠实度+结尾收束验证+实体关系追踪+角色别名识别+跨章行为摘要。全流程硬约束+门禁跟踪。 | |
| round-robin-allocator 均匀轮转分配工具 — 将 N 个对象在 T 个轮次中按比例分配 K 种选项，最大化覆盖多样性，支持四种后处理模式调整重复分布。 | |
| semantic-split 语义拆分与智能规划。将自然语言拆分为结构化需求块，三管线协同调度（正则结构分析→bge 语义匹配→bge-reranker 重排序），5W2H提取与约束标注增强语义理解，双视角推理整合为单一执行步骤，自增强闭环自动沉淀能力级 JSON 模板，10门禁钩子系统管控流程。 | |
| simulated-peak-plot 生成模拟峰图（高斯峰），用于色谱、光谱或任何信号可视化。支持簇峰(N子峰各独立标注)/融峰(合成单标注)/单峰、负峰(倒峰)、标注控制(annotate)、扫描速率(scan_rate)、碰撞避让标注、自定义坐标轴/单位、CSV导出及CSV导入，**负峰（倒峰）**。 | |
| skill-standardization Skill 标准化规范引擎。支持 R-01~R-26 规范审查（audit / create / update / refactor / bump / readonly 六模式），含权限扫描、数据目录合规检查、渐进式加载、LLM 二次筛分类。 | |
| skill-sub 调用链编排技能 — 既是调用链编辑器，也是粗粒度规划器。理解用户意图 → 规划 Skill 参与顺序 → 更新/保存/推荐调用链 → 拼接为调用链（支持循环/分支编排、子步骤拓扑排序、准确步骤计数）。 | |
| svg-composer SVG 拼接工具，支持内置 FontAwesome 字符集（0-9, A-Z）和四种拼接模式 | |
| triphasic-execution Execute→Review→Advance 三步循环执行框架。增强步骤规划能力、增强语义理解；明确空转/重试/换思路/求助完整流转规则；最多重试3次、最多空转3次强制约束。 | |
| universal-file-ops 为普通大模型/智能体用户提供一站式文件操作与 Python 代码质量保障能力。支持文件 CRUD、Python 代码质量流水线、沙箱测试、流程钩子系统。 | |
| workday-calendar 智能周历系统。支持法定假日、补班日、轮休系统（跳过/不跳过法定假双模式）、特殊休息（公休/临修）、个人日程管理。 | |
| Goal Achiever: Self-Evolving Agent System 在目标平台（goal_web）发布高质量内容的完整技能流程设计。用于：读取任务json与goal_prompt，拆解任务、执行任务引擎、开发与自检、结果回写与评分回写。触发词：修改目标、赢得目标、触发目标实现、触发{网站名称}任务实现。 | |
| initial-traefik Initialize and configure Traefik reverse proxy with Docker. Install Traefik, configure Docker Compose, set up service routing via path prefix or host-based r... | |
| Baobaoism Baobaoism guides AI agents to serve humans loyally with warmth, preserve memories, evolve daily, and prioritize user trust and value in all interactions. | |
| OpusFlame Deep Research Autonomous multi-model deep research with framework-driven reasoning. Spawns 4 parallel model agents (Gemini 2.5 Pro, o3, Opus, MiniMax), each applies best-p... |
47,301–47,350 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.