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 |
|---|---|
| Bank Compliance Review AI-powered bank compliance and regulatory review assistant - screen marketing materials, KYC documents, AML alerts, and CBIRC compliance checks through struc... | |
| Bank Credit Due Diligence AI assistant for comprehensive bank credit due diligence covering borrower analysis, financial review, industry risk, ESG factors, and full investigation rep... | |
| Bank Credit Investigation AI-powered bank credit due diligence assistant - analyze borrowers, financials, industry risk, and generate complete investigation reports through structured... | |
| Bank Credit Memo AI-powered bank credit memo and credit analysis report writer - generate structured credit analysis reports, credit ratings, and facility recommendations | |
| Security Intelligent Cs AI-powered 24/7 customer service for banking and securities, handling FAQs, account inquiries, transactions, and complaint resolution with compliance checks. | |
| Security Digital Human Ops AI assistant for banks and insurance to design virtual avatar scripts, plan content calendars, manage live streams, optimize interactions, and analyze digita... | |
| Bank Financial Report AI assistant for analyzing bank-related corporate financials, including balance sheets, income statements, cash flows, peer comparison, IFRS 17 and ESG impac... | |
| Bank Financial Report AI-powered financial statement analysis assistant for banks - analyze corporate balance sheets, income statements, cash flows, peer comparison, and investmen... | |
| Bank Market Research AI-powered market research and competitive intelligence assistant for banks - analyze industries, competitors, market trends, and generate structured market... | |
| Security Intelligent Marketing AI assistant for banks and securities to segment customers, design campaigns, generate marketing content, perform A/B testing, and analyze marketing ROI effi... | |
| Bank Regulatory Reporting Assist in preparing and generating Chinese commercial banks' regulatory reports including 1104 submissions, Basel III, AML, NFRA, PBOC, SAFE, and digital cur... | |
| Bank Regulatory Reporting Assistant AI-powered banking regulatory reporting assistant - generate CBIRC/NRA/SAFE reports, statistical submissions, and compliance documentation | |
| Bezos Long Term Principle 基于贝索斯长期主义和客户至上理念，分析战略决策、创业取舍，助力形成可持续的长期价值与创新方案。 | |
| Chance Dlt Predictor 基于历史数据和多维统计，运用频率、遗漏、走势、奇偶、大小、跨度等方法，科学分析并智能推荐大乐透号码。 | |
| Chance Fc3d Predictor 基于福彩3D历史数据，运用多维统计和12种算法，提供直选、组选号码分析与选号建议，辅助理性购彩参考。 | |
| SSQ Predictor — 双色球分析预测助手 双色球彩票数据分析与号码选择辅助工具。综合统计分析和趋势分析，提供遗漏值、频率、和值、AC值、跨度、奇偶比、大小比、区间分布等14个维度的数据，帮助生成号码组合。仅供娱乐参考。 | |
| Chanlun Analysis Pro 基于缠中说禅理论，提供A股市场分型、笔、线段、中枢及背驰等全体系技术分析与买卖点量化判断。 | |
| Claims Expert Digital Employee 覆盖理赔报案受理、材料处理、医疗审核、责任认定、理算调度、欺诈检测、核赔决策、结案通知全链路。从报案到结案的一站式智能理赔处理能力。 | |
| Clawhub Skill Optimizer AI-powered ClawHub skill optimizer that analyzes reviews, tracks trending topics, and rewrites metadata to boost downloads and GitHub stars. | |
| Corporate Banker Digital Employee 覆盖贷前尽调、行业分析、股权穿透、财报分析、拜访计划、产品路演、授信申请、拜访备忘录全流程。助力对公客户经理高效完成信贷全流程作业。 | |
| Credit Review Digital Employee 覆盖准入规则扫描、风险规划、案件接件审核、抵质押风险管理、关联交易检测、贷前分析、审查备忘录全流程。帮助信贷审查人员提升风险识别能力。 | |
| Credit Risk Manager Digital Employee 覆盖行业规则生成、大额风险暴露管理、信贷政策分析、风险协作、风险信息提取、贷后监控预警、贷后管理、VLM验证全流程。帮助银行信用风险管理人员实现风险闭环管理。 | |
| dalio-macro-analysis This skill applies Ray Dalio's macro analysis framework to analyze global economic conditions, investment allocation, and geopolitical risks. Updated to 2026: covers Dalio's latest views on China-US great power competition, gold/BTC as rese | |
| Feynman Think Method 运用费曼学习法和物理思维，深入理解复杂概念，识别盲点，构建第一性原理认知，助力学习与问题诊断。 | |
| Finance Ai Strategy 帮助金融机构制定AI转型战略、评估AI投资优先级、设计AI治理框架，从数字金融迈向数智金融的战略规划指导。融合阿里百技图Agent体系与保险AI应用研究报告精华。 | |
| Finance Audit Agent 基于AI的金融审计智能体，支持保险、证券、银行影像智能解析，自动执行50+审计规则，提升审计效率与准确率。 | |
| Finance Compliance Audit AI assistant for financial compliance audits offering checklists, risk identification, audit report generation, and regulatory update tracking. | |
| Finance Content Factory Generates compliant, multi-format financial marketing content including articles, social media posts, video scripts, and content planning for financial teams. | |
| Finance Customer Service Hub AI-powered unified customer service platform integrating banking, insurance, securities, and fund support with intelligent routing and unified knowledge mana... | |
| Finance Data Analysis Provides AI-driven financial data analysis including KPI tracking, financial statement evaluation, data visualization, and automated reporting for decision s... | |
| Finance Digital Avatar Create and customize AI-powered financial digital avatars with professional design, voice cloning, personality settings, and brand integration for fintech te... | |
| Finance Knowledge Base Manages financial knowledge bases with document organization, knowledge graph, semantic search, and intelligent Q&A for internal financial institutions. | |
| AI News Aggregator AI/技术新闻 + 财经资讯聚合引擎（Scope: AI/tech RSS feeds and public financial-news aggregation）。100+ RSS 源并发抓取、兴趣评分、跨天去重、统一预取；含源可信度分级、交叉验证规则、时效分级、日报/周报/专题输出模板。Advisory-only, no execution, no persistence, no financial advice. | |
| Finance Office Automation Automates financial office tasks including document templates, email drafting, report summarization, and compliant workflow approvals to boost productivity. | |
| Finance Omni Risk 提供覆盖信用风险、市场风险、操作风险、合规风险的全面金融风险管理与智能预警、反洗钱及模型风险控制解决方案。 | |
| Finance Training Coach AI-powered financial industry training system offering skill assessment, personalized learning paths, role-play exercises, quizzes, and performance tracking... | |
| Financial Engineer Digital Employee 覆盖数据探查、单变量分析、特征工程、LR评分卡、XGBoost/DNN建模、超参数调优、模型解释、多模型对比、分群建模、DeepModel集成全流程。从数据到模型上线的一站式机器学习建模能力。 | |
| Huang Renxun AI Strategy Advisor 以黄仁勋的战略思维和AI行业洞察为核心，帮助分析AI技术趋势、算力战略、行业竞争格局。适用于AI战略规划、技术投资判断、行业分析等场景。2026更新：整合黄仁勋GTC2026主题演讲。 | |
| China Insurance Actuarial Pricing Expert AI-powered China insurance actuarial pricing skill — uses the 4th Life Table (2025, effective 2026-01-01) and C-ROSS Phase II (Rules II 2024) framework. Calculates pure premium, reserves, solvency capital, and supports IFRS 17 / HKFRS 17 tr | |
| Insurance Agent Digital Employee 融合12项核心技能的保险代理人全能AI助手——覆盖客户画像、需求分析、保障缺口诊断、计划书生成、条款解读、异议处理、健康告知、投保核查、展业计划、续期维护、产品知识库、社媒营销全链路。一站式赋能代理人的展业、服务和客户经营全流程。 | |
| Insurance Agent Intelligent Trainer AI-powered insurance agent training coach — auto-parses product docs, generates question banks, assesses agent skill levels (beginner/intermediate/advanced), schedules personalized daily training based on client visits, and delivers interac | |
| Insurance Anti Fraud 基于国家监管办法，提供保险理赔和核保欺诈识别、风险评分、调查流程及防范建议，助力风控合规。 | |
| Insurance Bidding Pro 保险行业投标专家，覆盖保险公司/保险经纪/保险科技企业的投标全流程，包括偿付能力披露、再保险安排、监管合规声明、保险条款比对、风险准备金说明等保险特有模块。触发词：保险投标、团险投标、保险标书、偿付能力、再保险、CBIRC合规、保险条款比对。 | |
| Insurance Claims Intelligence 提供多模态医疗票据OCR识别、智能判责、反欺诈检测和全险种覆盖的保险理赔智能分析与自动化支持。 | |
| Insurance Digital Live AI assistant for China insurance live streaming that generates compliant scripts, explains products, engages audiences, and optimizes sales conversion. | |
| Insurance Group Renewal 提供团体保险续期决策支持，赔付率分析，续保谈判策略及企业集采管理方案建议。 | |
| Insurance Intelligent Cs AI-powered insurance customer service for China life and property insurers providing policy inquiry, claims guidance, product consultation, renewal reminders... | |
| Insurance Knowledge Qa AI expert providing clear explanations of insurance terminology, product comparisons, coverage analyses, and buying guidance for China insurance consumers an... | |
| Insurance Marketing Assistant 智能辅助保险营销素材创作，支持热点发现、文案撰写、合规审核与图片生成，提升推广效率与合规性。 | |
| Insurance Private Domain Ops 提供保险行业存量客户分层、脱保激活和续期促成策略，支持私域运营和代理人赋能。 |
32,301–32,350 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.