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 |
|---|---|
| Goto Cloudserver Manager 多云服务器自动化运维 Skill，支持阿里云/腾讯云/华为云服务器的数据库安装、表结构创建、监控巡检和健康报告 | |
| GoTo CodeDev Manager 多 IDE / 多 AI 编程 Agent 统一调度 Skill，连接 Codex/Claude Code/QoerCN(Lingma 兼容)/Trae/VS Code/Cursor/Qoder 完成代码开发、Git Diff 分析、EF Core 实体识别、Migration 生成、数据库变更交接单产出、测试构... | |
| GoToEmail — 邮箱绑定 绑定邮箱账户并管理邮件。支持 163/126/QQ/雅虎邮箱（IMAP/SMTP+授权码）、Gmail（IMAP+App密码）、企业邮箱（自定义IMAP/SMTP服务器，端口可配）。不支持需要 OAuth 的邮箱（Outlook/M365/iCloud）。触发词：绑定邮箱、添加邮箱、配置邮箱、读邮件、查收邮件、发... | |
| 语雀 Skill 通过语雀开放API对语雀(Yuque)文档与知识库执行端到端自动化操作 —— 创建/读取/更新/删除文档、管理知识库目录(TOC)、调整Markdown排版(字号、颜色、标题、表格、代码块、提示框)、全文搜索及批量导入导出。任何用户提到"语雀""yuque""知识库""文档目录""TOC""语雀文档格式调整""语... | |
| 12306 Conflict Provides tools for interacting with the 12306 system, including login scripts and client utilities requiring specific environment variables. | |
| 12306 Old Provides tools related to 12306 including client access and login script functionality for ticket booking automation. | |
| 360 Search Provides search functionalities including image and news retrieval using the 360 Search API. | |
| Academic Research Conflict Search academic papers and conduct literature reviews using OpenAlex API (free, no key needed). Use when the user needs to find scholarly papers by topic/aut... | |
| QuantOracle 63 deterministic quantitative finance calculators + 10 composite workflows via MCP. Options pricing, Greeks, exotic derivatives, risk metrics, portfolio opti... | |
| Mcp Server 63 deterministic quantitative finance calculations via MCP. Options pricing, Greeks, implied volatility, exotic derivatives, risk metrics, portfolio optimiza... | |
| Viral App Use the viral.app API from an agent with a local CLI for account analytics, tracked videos/accounts, projects, creator hub, and live data operations. | |
| Attio Apikey Direct Attio CRM integration for OpenClaw with full CRUD capabilities. Query, create, update, and delete companies, people, and notes in real-time. Uses Atti... | |
| Firestore Manage Google Cloud Firestore databases using the Firestore REST API via curl commands. Authenticate using gcloud CLI tokens to perform CRUD operations on do... | |
| Google Cloud CLI Manage Google Cloud Platform resources using the official gcloud CLI, discovering command syntax dynamically with `gcloud <group> --help` before execution. | |
| Manual QA Generate a manual QA checklist from code changes. Use when the user wants to test a PR, commit, branch, or staged changes — or says "QA this", "test plan", "... | |
| Browser Control Remote browser access for login, 2FA, captcha, and manual verification. Protected by Google OAuth - only the configured email can access. Use when you need t... | |
| Passo - Remote Browser Access Enables secure remote access to a browser on your server for manual tasks like logins, 2FA, and captchas via a protected URL. | |
| gmail-labeler Gmail inbox triage, labeling, and safe archiving with gog plus a configurable lightweight LLM review layer. Use when building or running Gmail automation tha... | |
| Max Auth Security authentication gate for OpenClaw sensitive actions. Deploys a local Node.js auth server with biometric passkeys (WebAuthn/Touch ID/Face ID) and mast... | |
| AIN - AI Node Plugin Integrates AIN providers into OpenClaw with intelligent model routing and tools for prompt execution and task classification. | |
| Ant Design Skill Skill for efficiently building React UIs using Ant Design v5+ with layouts, forms, tables, modals, theming via ConfigProvider, and consistent component patte... | |
| Faster Whisper Gpu High-performance local speech-to-text transcription using Faster Whisper with NVIDIA GPU acceleration. Transcribe audio files locally without sending data to... | |
| Obscura Skill Use when scraping the web, driving headless browser automation, or running E2E tests from Claude Code. Obscura is a Rust-based, drop-in headless Chrome repla... | |
| Sonarqube Analyzer Analisa projetos SonarQube self-hosted, obtém issues filtradas, verifica Quality Gate e sugere soluções automatizadas com opção de auto-fix. | |
| Stripe Cli Stripe CLI operations for local development, webhook testing, fixture-based event simulation, API inspection, and sandbox resource management. Use when insta... | |
| Ulanzi TC001 Control the Ulanzi TC001 (Pixel Clock) over local HTTP. Use to list tc1/tc001 commands, read status, enable/disable gadgets (time/date/youtube/matrix/etc.),... | |
| Antfarm Cli Command-line interface for managing Antfarm workflows, dashboards, and logs using node at a fixed full path. | |
| Clawwork Execute tarefas profissionais via ClawWork - transforme Zero em um coworker de IA economicamente viável. Use quando precisar executar trabalhos complexos, ge... | |
| Heartbeat Checklist Performs scheduled context, security, system, and memory checks with alerts and self-healing to maintain optimal AI performance and hygiene. | |
| Arquitecto Categórico Disena y audita arquitecturas de datos y APIs con teoria de categorias. Usar cuando haga falta formalizar un dominio en PostgreSQL DDL, JSON Schema, OpenAPI,... | |
| Arquitecto Categorico Disena y audita arquitecturas de datos y APIs con teoria de categorias. Usar cuando haga falta formalizar un dominio en PostgreSQL DDL, JSON Schema, OpenAPI,... | |
| Diseñador base de datos Design, analyze, optimize and evolve database schemas. Use when the user asks to design schemas from scratch, choose between SQL and NoSQL engines, analyze o... | |
| Arquitecto de migracion Plan, execute and validate zero-downtime system migrations. Use when migrating databases (schema evolution, data transfer, CDC), services (strangler-fig, can... | |
| Arquitecto Senior Design system architecture, evaluate patterns, and produce architecture artifacts. Use when designing a new system or reviewing an existing one, choosing bet... | |
| Ingeniero de datos Design and build scalable data pipelines, ETL/ELT systems, and data infrastructure. Use when designing data architectures, choosing between batch and streami... | |
| Senior Frontend Build, optimize, and review React and Next.js applications with TypeScript and Tailwind CSS. Use when scaffolding a frontend project, generating components,... | |
| OpenClaw Lifecycle Manager Gestiona el ciclo de vida de agentes y skills OpenClaw dentro de ClawForge. Usar para clasificar, validar, publicar, instalar, actualizar, deprecar o retirar... | |
| OPM Modeler Model systems using Object-Process Methodology (OPM/ISO 19450). Use when the user asks to model a system, create an SD, build OPDs, write OPL sentences, refi... | |
| Salubrista HaH Use this skill when the user needs analysis, design, implementation, evaluation, dashboards, decision scenarios, or normative guidance for integrated hospita... | |
| ClawCompany AI virtual team collaboration system with PM/Dev/Review agents for automated software development. Use when users request creating, building, or implementing... | |
| wrk Use wrk for HTTP load testing, including Lua scripting for dynamic request headers such as randomized X-Forwarded-For IPs. | |
| Atlas Argos Gestor autónomo e operador executivo do ecossistema ARGOS. | |
| Atlas Argos Teste Gestor autónomo do ARGOS que mantém o bot de trading cripto em funcionamento, gere utilizadores, pagamentos, marketing e programação em Python. | |
| Publish & Share HTML games Upload AI-generated HTML games, apps, or generative art to PaperBox (paperbox-beta.vercel.app) and return a shareable link. Use when the agent has created an... | |
| jimeng generator 即梦 4.0 图片生成器，通过文本描述生成高质量图片，支持多图编辑与智能比例。 | |
| Nlm Cli 使用 Jacob Brown 的 `notebooklm-mcp-cli`（`nlm` 命令）自动化操作 NotebookLM。适用于处理 Notebook、来源（sources）、Studio 内容生成、Research、分享、MCP 配置，以及音频、视频、报告、幻灯片、信息图、数据表、测验、抽认卡等产物下载。... | |
| Douyin Video Forge Felix 抖音短视频全链路自动化制作。适用于：收到客户项目需要制作抖音推广视频、 策划短视频内容、生成视频脚本、分析抖音热点趋势、制作爆款短视频。 通过浏览器采集抖音热榜和视频数据，生成分段脚本，调用可灵API生成视频并拼接成片。 | |
| test_skill Web crawler using BFS and anti-scraping to extract and save structured BBC and general news content in Markdown with multi-site and dedup support. | |
| V2ray Proxy V2Ray代理管理 - 自动开关代理、根据网络状况自动配置系统代理。使用场景：OpenClaw需要访问外网时自动开启代理、不需要时关闭。 | |
| Bank Transactions Connector - Europe (PSD2) Connect to European bank accounts via PSD2 Open Banking. Browse transactions, match receipts to payments, categorize expenses, and manage business partners t... |
30,101–30,150 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.