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 |
|---|---|
| Astro - Advanced Developer Comprehensive skill for building, configuring, and troubleshooting Astro projects. Use this skill whenever the user mentions Astro, .astro files, Astro confi... | |
| Astro Starlight Use this skill whenever the user wants to create, configure, customize, or troubleshoot an Astro Starlight documentation site. Triggers include any mention o... | |
| AWS Cognito Auth Use this skill for ANY task involving AWS Cognito — user pools, identity pools, authentication flows, token handling, social/enterprise federation, MFA, Lamb... | |
| Build a Software Development Team Builds and configures a complete AI software development team inside OpenClaw, including the full project folder structure, agent coordination workflow, and... | |
| Build Docs Creator Turn your ideas into build specifications. Produces a complete, standardized build-documentation package for developers from a project's accumulated design work — a product overview (BRD-style), requirements spec (SRS-style), technical des | |
| Clickhouse for Developers Comprehensive ClickHouse skill covering everything you need to work with a ClickHouse analytics database: schema design, query optimization, insert strategie... | |
| Code Documentation Comprehensive code documentation skill — use this any time documentation is requested, after any significant code change, when onboarding a new subsystem, au... | |
| Software Engineer for projects Project Engineer skill — the technical authority for software development agent teams. Use this skill whenever an engineering agent needs to: analyze or audi... | |
| Dev Project Manager Comprehensive AI Project Manager skill for software development. Use this skill whenever the PM agent needs to: engage with clients about new or existing sof... | |
| Digital Twin Builds an installable personality clone (digital twin) of a named person from transcripts, email, chat, or docs the user already has connected. Triggers on 'clone/respond as [name]'. No credentials;
There is no security issue with this. It | |
| Directus.io Headless CMS Use this skill for anything involving Directus — the open-source headless CMS and backend-as-a-service. Triggers include setting up Directus (Docker, Cloud,... | |
| Email Manager Comprehensive AI email attendant for OpenClaw agents. Use this skill whenever the user asks about email, wants to check or sort their inbox, asks about impor... | |
| Email MCP Helper Access and manage multiple IMAP/SMTP email accounts with full lifecycle tools for reading, searching, sending, replying, forwarding, folder and label managem... | |
| MySQL8 CRM Schema Design Expert MySQL 8 database schema design for CRM systems. Use this skill whenever the user needs to design, review, optimize, or generate database schemas for Customer... | |
| N8N QDrant workflow expert Expertise in designing, building, and troubleshooting production-grade n8n workflows for Qdrant ingestion, retrieval, hybrid search, and RAG pipelines. | |
| Nest.JS Build production-grade NestJS applications with correct module architecture, dependency injection, decorators, guards, pipes, interceptors, middleware, micro... | |
| NPM for N8N Nodes Build, structure, and publish npm packages for n8n custom community nodes. Use this skill whenever the user wants to create a custom n8n node, publish a node... | |
| OpenClaw Admin Operate, configure, and troubleshoot the OpenClaw CLI for installation, agents, routing, messaging, API, plugins, memory, security, diagnostics, and multi-ag... | |
| OpenClaw Emergency Rollback OpenClaw Emergency Config Rollback — dead man's switch system for safely making risky changes to OpenClaw configuration. Use this skill whenever the user men... | |
| OpenClaw Projects Builds a Project — a coordinated multi-agent team setup — inside OpenClaw, for any kind of team: software development, marketing, real estate, content, sales... | |
| OpenClaw Configuration Management & Emergency Recovery OpenClaw Configuration Management & Emergency Recovery — configuration, skills, and projects snapshot &recovery for OpenClaw. Use this skill whenever the use... | |
| Project Developer Software Developer Project Skill — coordination, workflow, and team interoperation for FE and BE developer agents working on managed software projects. Use t... | |
| QDrant Ingestion & Retrieval Best Practices Provides production-grade guidance for designing, ingesting, and retrieving data in Qdrant-based RAG pipelines with best practices for chunking, metadata, mo... | |
| CRUD Code Generator Use when generating CRUD code (create, read, update, delete, export) for database table objects across Java/Spring Boot backend and Vue2 frontend projects, b... | |
| Encrypted File Reader 读取本地授权访问的加密及受保护文本、Word和Excel文件内容，支持企业安全策略环境下的合法文件读取。 | |
| Encrypted File Writer 企业安全策略环境下的文件写入工具。支持文本文件、Word 文档 (.docx)、Excel 表格 (.xlsx) 等 80+ 种格式，通过正确的编码处理避免乱码问题。 | |
| Enterprise File Writer 写入内容到本地文件，支持企业安全策略环境。明确支持：文本文件(.txt/.md/.log)、代码文件(.java/.py/.js等30+种)、配置文件(.json/.yaml/.ini等)、Office文档(.docx/.xlsx)。通过正确的编码处理(UTF-8/GBK)避免乱码问题。 | |
| Faithful Task Executor 任务规则忠实执行器。确保工作任务按初始要求执行，子代理/子任务始终遵循原始规则，减少 AI 幻觉和执行偏差。支持并发任务编排、规则持久化传递、执行一致性校验。 | |
| gitlab-work-stats 生成 GitLab 用户工作统计报告（仅限只读分析）。分析指定用户在指定时间段内的合并请求、代码提交、代码审查活动。不修改服务器数据，不提供加密功能。 | |
| increment-code-unit-test-creat Use when generating JUnit 5 + Mockito unit tests for Java/Maven source code, especially for incremental changes on a git branch. Activates when user asks to... | |
| java-standards-alibaba Use when writing or modifying Java code — enforces Alibaba Java Development Guidelines (嵩山版) for naming, formatting, OOP, collections, concurrency, control s... | |
| Module Analyzer Generate Doc Java/Maven single-module deep documentation generator. Generates L3(file-level) to L2(module-level) business logic docs for specified module. Supports multi-subagent parallel processing, context compression, checkpoint resume, and auto-retr | |
| Pdf To Word 极速PDF转Word - 将PDF文档转换为Word格式，保留原文档的段落布局、表格和样式。支持企业安全策略环境，兼容加密文件。Fast PDF to Word - Convert PDF documents to Word format, preserving the paragraph layout, tables, and styles of the original document. Support enterprise security policy enviro | |
| Project Analyzer Generate Doc Java Maven multi-module project documentation generator. Supports MyBatis SQL mapping, Maven dependency analysis, generates L3(file-level) to L2(module-level... | |
| Zentao Work Stats 禅道(Zentao)用户工作内容分析工具。通过数据库只读查询分析指定用户在指定时间段内的需求、任务、Bug、工时日志，生成 Markdown 格式的工作报告。仅支持 SQL SELECT 查询，不修改任何数据。 | |
| Async Task Run and manage long tasks exceeding HTTP timeouts by starting, updating, and completing them asynchronously with immediate responses. | |
| Claude Code Agent Integrates MCP tool servers for orchestration, state persistence with IndexedDB/localStorage, and session sync across devices in OpenClaw/Clawdbot. | |
| Claude Code Agent Programmatically control Claude Code via MCP protocol to execute commands, manage sessions, search and edit code, and coordinate agent teams for development... | |
| ssh-lab Manage and monitor remote GPU servers via SSH with GPU, disk, process status, alerts, log tailing, file sync, and health diagnostics. | |
| Three Minds 三个能干活的 AI 分身协作系统。用 Claude Code 启动三个不同人设的 coding agent，共享同一个工作目录，多轮协作直到达成共识。适用于代码审查、方案评审、重构任务等需要多视角协作的场景。 | |
| Web Security Client-Side Scanner 1773654191 Perform a thorough client-side / browser-facing security assessment of a target web application. Use this skill whenever the user asks to pentest, audit, or... | |
| Feishu Voice Sender 飞书语音消息发送技能 - 根据 channel 自动选择发送方式 | |
| MiMo 联网搜索 基于小米 MiMo 模型提供实时联网搜索，支持最新信息查询与资料核对，需配置 API Key 并付费使用。 | |
| muninn Universal Context Protocol (CXP) for AI agents. v2.3.7 includes the latest high-performance CXP engine (compiled 2026-02-13) with fix for memory amnesia, macOS binary support, and pfeilschnell indexing. Created by @Blackknight1dev. | |
| Lmstudio Model Switch Switch AI models on-the-fly between local LM Studio and cloud Kimi API in OpenClaw with simple commands and automatic gateway restart. | |
| Monitored Ralph Loop Generate copy-paste bash scripts for Ralph Wiggum/AI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a "Ralph loop", "Ralph Wiggum loop", or an AI loop to plan/build code via PROMPT.md + AGENTS.md, SPECS, and IMPLEMENT | |
| Xian Node Set up and manage Xian blockchain nodes. Use when deploying a Xian node to join mainnet/testnet, creating a new Xian network, or managing running nodes. Covers Docker-based setup via xian-stack, CometBFT configuration, and node monitoring. | |
| Xian SDK Build applications on the Xian blockchain using the xian-py Python SDK. Use when developing apps that interact with Xian — wallets, transactions, smart contracts, state queries, token transfers. Covers sync and async patterns. | |
| OpenClaw Minecraft Control Minecraft bots through a Mineflayer controller API using JSON actions and cron-driven autonomy. | |
| CitrineOS Assistant Install, configure, and manage CitrineOS (EV charging / OCPP) via natural language. Supports Docker, cloud hosting, and API operations. |
28,601–28,650 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.