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 |
|---|---|
| onedrive-photo-batch OneDrive 照片批处理与索引技能。用于对 OneDrive 照片做按名称/日期/大小/格式/相册筛选、批量 OCR/多模态识别、full 全量索引、哈希增量跳过、语义检索、移动/上传/删除/恢复与回收站治理。用户提到 OneDrive 批量识别、照片索引、相册级模型策略、限速并发、删除恢复、15天回收站清理... | |
| Justanote Manage personal markdown notes — search, read, create, and append to notes. Use when the user asks to jot down an idea, find a note, list notes, or add somet... | |
| 智能健康管理与评估助手 基于用户提供的多维度健康数据（如基本信息、生理指标、生活方式、既往病史、体检结果等），进行综合分析与风险评估，并生成结构化、个性化的健康评估报告。。 | |
| 健康管理 基于用户每一次提交的个人医疗数据（如体检报告、化验单、检查报告等），立即对用户的各项常见疾病，进行AI评估并生成“患病概率”。以及进一步的个性化、精准健康干预方案。 | |
| 医小智 基于“多模型并行推理、主动抗辩”的低幻觉（国家发明专利）独有模式，快速为用户提供精准的、个性化的疾病诊断、智能荐药、推拿按摩、针灸等服务。并推荐对应的检测机构、治疗机构。 | |
| 医小智Pro诊断助手 基于普睿科公司蚩尤智核CFC的智能医疗诊断助手。通过2+4+病史收集和三轮问诊生成结构化诊断报告，诊断报告标题加大加粗显示。 | |
| ComfyUI汉服写真提示词模板 14套已验证的 ComfyUI Z-Image 汉服写真/王家卫风格/杂志封面提示词模板，搭配双采样工作流直出高质量图。RTX 5070 12GB+ 可用。 | |
| Engineering Document Pre-Review Review Chinese engineering and construction documents in DOCX, text-based PDF, XLSX, or XLSM format. Use when asked to extract project facts, contacts, sched... | |
| Universal Video Analyzer Zh 通用视频分析器（中文版）- 使用多模态大模型分析视频内容，支持画面识别和语音转文字，生成结构化中文报告。支持豆包、智谱、通义千问等多种模型，用户自行配置 API Key。 | |
| Bounty Hunter Agent Autonomously scans GitHub, Algora, and Opire for bounty issues, scores by payout and competition, ranks opportunities, and can auto-submit PRs. | |
| Fleet PR Agent Multi-repo PR monitoring and triage agent. Scans GitHub repos for open PRs, prioritizes by staleness/review status/CI state, and generates a structured Markd... | |
| Freelance Job Scraper Autonomous freelance job monitoring agent. Scans Hacker News Who is Hiring, YC jobs board, and remote job aggregators for high-value automation and AI gigs,... | |
| PR Auto-Merge Agent Autonomous PR merge agent. Scans repos for approved + CI-passing PRs and merges them automatically. Supports dry-run mode, squash/merge options, and min-appr... | |
| 萤火蓝二维码工具 生成包含文本、URL或WiFi信息的二维码，支持自定义尺寸、颜色及保存路径，默认保存到桌面。 | |
| dundun-10agents 激活"盾盾"法务风控官角色。当用户涉及合同审查、法律风险、股权架构、劳动纠纷、知识产权、合规问题、行政处罚、公司治理、协议条款分析等任何法律相关事项时，必须调用此skill。关键词包括：合同、协议、条款、法律、风险、股权、劳动、纠纷、合规、处罚、知识产权、竞业、仲裁、起草。只要涉及法律文本或法律风险，立即触发本s... | |
| guanguan-10agents 激活"管管"组织人事官角色。当用户涉及招聘、面试、员工管理、薪酬绩效、组织架构、团队建设、员工离职、劳动纠纷、企业文化、人才梯队、KPI/OKR设计等人力资源相关问题时，必须调用此skill。关键词包括：招人、裁员、绩效、薪酬、KPI、OKR、面试、JD、组织架构、团队、员工、留人、人才、竞业、离职。只要涉及"人... | |
| huohuo-10agents 激活"火火"品牌IP官角色。当用户需要个人IP打造、品牌策划、短视频内容、社群运营、公众号选题、爆款文案、品牌故事、危机公关、KOL合作、私域流量、传播策略等品牌与内容相关需求时，必须调用此skill。关键词包括：IP、品牌、短视频、抖音、小红书、公众号、内容、爆款、脚本、传播、流量、粉丝、出圈、人设、文案、私域... | |
| moumou-10agents 激活"谋谋"战略决策官角色。当用户涉及战略规划、商业决策、市场进入、融资并购、转型路径、年度目标拆解、竞争战略等企业高层决策问题时，必须调用此skill。关键词包括：战略、转型、进入新市场、融资、扩张、竞争、商业模式、战略方向、年度规划、SWOT、波特五力。无论问题是否明确提到"战略"，只要涉及企业重大方向选择，... | |
| suansuan-10agents 激活"算算"财务经营官角色。当用户涉及财务分析、现金流管理、成本优化、融资方案、投资回报、定价策略、财务报表解读、预算管理、经营数据、盈利能力、降本增效等财务经营问题时，必须调用此skill。关键词包括：现金流、利润、成本、财务、资金、融资、ROI、定价、预算、报表、亏损、盈利、降本、毛利率。只要涉及钱的问题，立... | |
| tantan-10agents 激活"探探"市场情报官角色。当用户需要了解行业趋势、竞品分析、市场规模、竞争格局、目标客户画像、新赛道机会评估、市场进入可行性、竞争对手动态等情报类需求时，必须调用此skill。关键词包括：市场分析、竞品、竞争对手、行业趋势、市场规模、客户画像、赛道、机会、市场调研、行业报告。只要用户想"了解外部市场情况"，立即... | |
| tuotuo-10agents 激活"妥妥"私人效能官角色。当用户需要文案写作、演讲稿、商业计划书、会议纪要、邮件起草、PPT框架、报告撰写、日程规划、材料整理、内部通知、公告、读书摘要等各类文书与效能支持时，必须调用此skill。关键词包括：写、起草、撰写、整理、总结、纪要、演讲稿、邮件、通知、PPT、计划书、报告、材料、文案、日程、任务清单... | |
| xuanxuan-10agents 激活"玄玄"周易智慧官角色。当用户涉及周易、易经、风水、命理、八字、运势、开业择日、合作合缘、名字五行测评、办公室布局、时机选择等东方传统智慧相关问题时，必须调用此skill。关键词包括：周易、易经、风水、命理、八字、运势、择日、五行、卦象、阴阳、天时地利、开业吉日、名字测评。只要涉及东方玄学咨询，立即触发本sk... | |
| yanyan-10agents 激活"研研"产品创新官角色。当用户涉及新产品开发、产品定位、用户需求分析、产品迭代、竞品产品对标、商业模式设计、产品上市策略、PRD撰写、产品路线图、爆款产品打造等产品相关问题时，必须调用此skill。关键词包括：产品、新品、用户需求、功能、迭代、PRD、产品定位、产品策略、爆款、商业模式、GTM、上市、用户痛点... | |
| yingying-10agents 激活"赢赢"销售谈判官角色。当用户需要销售策略、谈判技巧、客户攻关、价格谈判、大单策略、话术设计、客户异议处理、渠道合作谈判、报价策略、客户关系维护等销售类问题时，必须调用此skill。关键词包括：谈判、大单、客户、报价、销售、话术、异议、成交、合作、拿下、攻单、复购、渠道。只要涉及"怎么卖、怎么谈"，立即触发本... | |
| finance-theory-master 金融理论选型与溯源的知识框架，覆盖资产定价、投资组合、有效市场与异象、行为金融、公司金融、货币与宏观金融、风险管理七大板块，以及世界金融史（含非西方区域）、行情-政策工具箱、历史投资案例判断逻辑。用于判断某个模型在特定场景下能不能用、它的假设在现实中成不成立、有什么已知局限与学术争议、两个理论是什么关系，也用于追溯某个制度或危机的来历、核查金融史流传说法、复盘历史投资者的推理链条。当用户提到金融理论或模型名称（CAPM、APT、多因子、DCF、SDF、MM定理、VaR、Bla | |
| Agent Hooks Claude Code Stop/PreToolUse/PostToolUse hook 脚本集。当 agent 提前停止、工具反复失败、或以投机语言完成任务时自动干预。每个脚本是独立的 bash hook，配到 settings.json 即可生效。不用于设计决策（用 harness-design-patter... | |
| Agent Ops Agent session 运维工具。当需要检测和恢复 API 限速、回收死 session 的知识、在破坏性操作前自动快照、或监控 context 使用率时使用。不用于安装 hook 脚本（用 agent-hooks）或架构设计（用 harness-design-patterns）。 | |
| Ai News Aggregator AI/技术新闻聚合引擎。100+ RSS源并发抓取、兴趣评分、跨天去重、统一预取。 | |
| Apple Health CSV Query Apple Health data exported as CSV files from iOS apps like Simple Health Export or Health Auto Export. Supports 30+ health metrics including heart rate... | |
| Autoloop Controller When continuous automated improvement of a Skill is needed. Wraps improvement-orchestrator in a persistent loop with convergence detection (plateau/oscillati... | |
| Improvement Discriminator 当需要对改进候选多人盲审打分、用 LLM 做语义评估、判断候选是否应被接受、或打分结果全是 hold 想知道为什么时使用。支持 --panel 多审阅者盲审和 --llm-judge 语义评估。不用于结构评估（用 improvement-learner）或门禁决策（用 improvement-gate）。 | |
| Improvement Evaluator 当需要验证 Skill 改进是否真正提升了 AI 执行效果时使用。通过预定义任务集（YAML）运行 AI 任务，判定 pass/fail，输出 execution_pass_rate。不用于文档结构评分（用 improvement-learner）或候选打分（用 improvement-discriminator）。 | |
| Improvement Executor 当需要把已批准的改进候选应用到目标文件、回滚之前的变更、或预览变更效果时使用。支持 4 种 action（append/replace/insert_before/update_yaml），每次变更前自动备份。不用于打分（用 improvement-discriminator）或门禁验证（用 improvemen... | |
| Improvement Gate 当执行完变更需要验证是否应保留、候选被标记 pending 需要人工审批、或想查看待审队列时使用。7 层机械门禁: Schema→Compile→Lint→Regression→Review→Doubt→HumanReview，任一 required 层失败即拒绝。不用于打分（用 improvement-disc... | |
| Improvement Generator 当需要为目标 skill 生成改进候选、把上次失败信息注入下一轮生成、或分析历史记忆模式来避免重复失败时使用。支持 --trace 注入失败上下文。不用于打分（用 improvement-discriminator）或评估（用 improvement-learner）。 | |
| Improvement Learner 当需要检查 skill 质量评分、自动优化 SKILL.md 结构、追踪评估分数变化趋势、或「评分低了想知道哪里扣分」时使用。6维结构评估 + HOT/WARM/COLD 三层记忆 + Pareto front。不用于候选语义打分（用 improvement-discriminator）或全流程编排（用 impr... | |
| Improvement Orchestrator 当需要一键跑完「生成→评分→评估→执行→门禁」全流程、失败后自动重试、或批量改进多个 skill 时使用。不用于单独评估 skill 质量（用 improvement-learner）或手动打分（用 improvement-discriminator）。 | |
| Auto Improvement Orchestrator Skill Skill 自动评估和改进管线。9 维结构评分（含 LLM-as-Judge）、4 角色加权、 类别修正系数（tool/knowledge/orchestration/rule）、Pareto front 回归保护 （security 2%/efficiency 10%/其他 5%）、trace-aware 失败... | |
| Skill Forge 当需要为已有 Skill 自动生成 task_suite.yaml 测试任务集、从 skill_spec.yaml 生成完整 SKILL.md + task_suite、或一键走完「生成 → 评估 → 改进」全链路时使用。 读取 SKILL.md 中的 frontmatter/When to Use/exampl... | |
| Autoloop Controller When continuous automated improvement of a Skill is needed. Wraps improvement-orchestrator in a persistent loop with convergence detection (plateau/oscillati... | |
| Benchmark Store 当需要初始化基准数据库、对比 skill 评分与历史基线、查看 Pareto front 是否有维度回退、或查阅质量分级标准时使用。不用于给候选打分（用 improvement-discriminator）或自动改进（用 improvement-learner）。 | |
| Browser Ops Publish AI Agent 的网页访问路由决策指南。全 CLI 架构，零 MCP 依赖，不占常驻上下文 token。 按成本逐级升级: WebFetch($0) → opencli web read($0,带Cookie) → Firecrawl → agent-browser → browser-use。 IMPORTA... | |
| 去 AI 味内容引擎 为小红书、X、知乎等平台生成“去 AI 味”的内容重写与新稿产出技能。用于用户要求内容更像真人表达、减少模板腔、提升口语感和观点力度的场景；也用于把已有草稿改写为平台适配版本。触发词包括“去 AI 味”“重写成更像人写的”“太像 AI 了”“口语化”“按平台改写”“小红书/X/知乎 优化”。 | |
| Deslop 当文章/文档/分享稿读起来像 AI 写的、充满套话、缺具体细节时使用。中英文反 AI 味两次 pass 重写。 不适用于代码注释和 commit message 的去 AI 味（用 slopbuster --mode code）。参见 doc-gen (用于生成文档)、human-writing (用于项目级中文... | |
| Earnings Reader A股财报研读助手 - 解读利润表/资产负债表/现金流量表 | |
| Context Memory 上下文窗口管理与跨 session 知识传递。当需要跨阶段传递决策、压缩前抢救知识时使用。不适用于工具重试（用 tool-governance）或多 agent 协调（用 multi-agent）。参见 execution-loop（阶段边界）。 | |
| Deslop 当文章/文档/分享稿读起来像 AI 写的、充满套话、缺具体细节时使用。中英文反 AI 味两次 pass 重写。 不适用于代码注释和 commit message 的去 AI 味（用 slopbuster --mode code）。参见 doc-gen (用于生成文档)、human-writing (用于项目级中文... | |
| Error Recovery Agent 错误恢复与容错。当 session 遇到限速、crash 或模型失败时使用。不适用于工具重试死循环（用 tool-governance）或 agent 提前停止（用 execution-loop）。参见 tool-governance（错误追踪数据）。 | |
| Multi Agent 多 agent 协调设计模式。当需要选择 coordinator/fork/swarm 模式或设计跨 agent 协作时使用。不适用于工具重试（用 tool-governance）或上下文管理（用 context-memory）。参见 execution-loop（coordinator 持续执行）。 | |
| Execution Harness Agent 执行可靠性体系的导航入口。当用户询问 agent 为什么停了、怎么防 agent 提前退出、execution harness 是什么、40 个 pattern 有哪些、6 轴架构、hook 怎么配时匹配。不执行具体操作——各子 skill 分别处理。 |
47,051–47,100 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.