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 |
|---|---|
| WordPress Receipts Publish WordPress posts with API and public URL receipts. | |
| x-search-oauth Search X/Twitter through OpenClaw's native OAuth-backed xAI x_search tool. Includes a JS CLI wrapper. | |
| PonyFlash - Media Generation Router Generate images, videos, speech audio, and music using the PonyFlash Python SDK. Also handle local media editing with FFmpeg, including clip, concat, transco... | |
| Leo CSV Stats Analyzer Analyzes any CSV file and returns row count, column names, and basic statistics for numeric columns. | |
| mailbox-skill Use when working through the workspace mailbox protocol under .mailbox, including reading inbox items, composing replies in a private scratch area, and deliv... | |
| openclaw message cli skill Use when the user explicitly wants to send outbound messages with the OpenClaw CLI rather than built-in tools, especially for `openclaw message send` command... | |
| Slow Down Human-connection-preserving pacing and intervention guidance for agent behavior. Use when a user asks to "slow down", "not rush", or add relational awareness... | |
| Aliyun Search 1.0.0 Perform web searches using Alibaba Cloud UnifiedSearch API. Provides advanced search capabilities with configurable parameters. | |
| Batch Processor 1.0.0 Process multiple documents in bulk with parallel execution | |
| Bulletproof Memory 1.0.0 Never lose context again. The Write-Ahead Log (WAL) protocol with SESSION-STATE.md gives your agent bulletproof memory that survives compaction, restarts, an... | |
| Programming Provides programming guidance, including coding workflow, code review, optimization, and technical decision support based on task description and context. | |
| Programming Assistant Assist with programming tasks using Claude CLI. Use when OpenClaw needs to perform coding tasks, create new programs, modify existing code, or get programmin... | |
| umeng-app-analysis 友盟+ App 数据分析工具，通过友盟 Open API 查询移动应用统计数据。支持全部应用统计（App列表、数量、汇总数据）和单个应用详细分析（活跃/新增用户、启动次数、留存率、使用时长、渠道/版本维度、自定义事件及参数分析）。当用户需要查询友盟App统计数据、分析应用指标、获取用户行为数据时使用。认证信息从环... | |
| Agent Master Skills Clawhub Pkg A curated collection of 3103+ best agent skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps and more. Harness-agnostic, refreshed daily by MyClaw.ai — Powered by MyClaw.ai | |
| myclaw-backup Backup and restore all OpenClaw configuration, agent memory, skills, and workspace data. Part of the MyClaw.ai (https://myclaw.ai/skills) open skills ecosyst... | |
| Frontend Slides Create stunning, animation-rich HTML presentations from scratch or convert PowerPoint files (.ppt/.pptx) to beautiful web slides. Use when the user wants to... | |
| OpenClaw Guardian by MyClaw.ai Deploy and manage a Guardian watchdog for OpenClaw Gateway. Auto-monitor every 30s, self-repair via doctor --fix, git-based workspace rollback, daily snapsho... | |
| Openclaw Guardian Deploy and manage a Guardian watchdog process for OpenClaw Gateway. Provides automated health monitoring, self-repair via `doctor --fix`, git-based workspace... | |
| OpenClaw Marketing Skills A collection of 33 battle-tested marketing skills for OpenClaw agents. Use when you want to install or reference any marketing skill including: CRO (page-cro... | |
| Agent Master Skills Clawhub Pkg A curated collection of 3103+ best agent skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps and more. Harness-agnostic, refreshed daily by MyClaw.ai — Powered by MyClaw.ai | |
| openclaw-slides Create stunning, animation-rich HTML presentations from scratch or convert PowerPoint files (.ppt/.pptx) to beautiful web slides. Use when the user wants to... | |
| talewell Portable, git-backed, auditable long-term memory for any agent host. Reference implementation of AMP (Agent Memory Protocol). Use when: user asks for 'long-term memory', 'agent memory', 'memory that survives sessions', 'git-backed memory', | |
| Agent-Skills-for-Context-Engineering This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or | |
| Jenkins Plugin Skeleton Generator Skill Generate a Jenkins plugin skeleton based on the Jenkins version and JDK version provided by the user. | |
| Wework Financial Daily 每日定时生成金融分析教学课件并推送至企业微信。使用场景：(1) 每天自动生成当日最新金融数据（BTC、AAPL 等）的教学课件，(2) 推送课件到指定企业微信账号，(3) 保存 HTML 课件到本地桌面，(4) 包含价格走势图表和趋势分析。支持通过环境变量配置企业微信 token 和接收人。 | |
| manifesto-hci Implement "Explicit State & Continuous Consensus" HCI pattern (v3.0). Combat information entropy, prevent intent drift, and maintain a shared source of truth... | |
| Fitness Personal Assistant 一体化健身追踪系统。自动同步饮食记录和身体状态到 intervals.icu。支持配置引导和错误处理。 | |
| clawdo - Todo List for Agents Todo list and task management for AI agents. Add, track, and complete tasks with autonomy levels — agents propose work, humans approve. Works in heartbeats, cron, and conversations. Persistent SQLite CLI with structured JSON output. | |
| YoudaoNote 有道云笔记官方 skill，支持笔记 CRUD（创建/读取/更新/删除）、待办管理、网页剪藏、笔记搜索、文件夹管理等基础操作。如需构建知识库或 Wiki，请使用 youdaonote-llm-wiki skill 而非本 skill。 | |
| YoudaoNote Clip 网页剪藏到有道云笔记。触发词：剪藏网页、保存网页、收藏网页。 | |
| YoudaoNote LLM Wiki 当用户提到「知识库」「Wiki」「新建知识库」「创建 Wiki」「初始化 Wiki」「LLM Wiki」「素材摄入」「知识查询」「知识库审计」「一致性检查」「归档对话」「记下来」「存入知识库」「切换知识库」「用哪个知识库」「换一个知识库」「选知识库」，或使用助记词 wiki-init、wiki-ingest、wi... | |
| YoudaoNote News 有道云笔记资讯推送：基于收藏笔记分析关注话题，推送最新相关资讯。支持对话触发与每日定时推送（如早上9点）。触发词:资讯推送、设置资讯推送、生成资讯推送。 | |
| YoudaoNote OKF Wiki 当用户提到「OKF」「OKF Wiki」「Open Knowledge Format」「OKF 知识库」「新建 OKF」「创建 OKF bundle」「OKF 摄入」「OKF 查询」「OKF 一致性检查」「OKF 导出」「OKF 归档」「okf-wiki-init」「okf-wiki-ingest」「okf-wi... | |
| Daikin Aircon Controller Control Daikin air conditioners over WiFi. Use when the user wants to control their Daikin AC units - turn on/off, set temperature, mode, fan speed, swing, o... | |
| Lerwee Alert Inspection 当用户要求进行设备健康巡检、告警审查、巡检报告生成或导出监控告警到 Excel 时使用。通过 Python 获取监控数据，生成 Markdown 巡检报告，并导出包含 4 个 Sheet 的 Excel 工作簿。 | |
| Lerwee Alert To Fault Handling 告警自动处理工作流 - 监听告警上下文，匹配处理脚本，提示用户执行故障处理操作 | |
| Lerwee Docker Lwops Deployer 本地 Docker 容器自动化部署技能，支持乐维监控 8.1 环境的一键部署。 适用于：本地开发环境搭建、测试环境快速部署、容器化服务管理。 优势：自动检测系统架构、智能端口管理、Docker 自动安装、cgroup 兼容性处理。 | |
| Lerwee Fault Handling 当用户需要故障处理、远程主机执行脚本、服务重启、磁盘清理等运维操作时使用。通过 run-script API 执行脚本，并轮询 execution-history 获取执行结果。 | |
| Lerwee API Skill 乐维监控系统 API 集成工具。提供完整的 API 签名认证、监控对象管理、告警查询、事件平台等 86+ 个接口的调用能力。 | |
| AI Demo Recorder Record AI-driven browser demos with screencli. One command creates a polished screen recording with gradient backgrounds, auto-zoom, click highlights, and cu... | |
| Lesishu SEO Guide SEO 全流程技能：网站诊断、页面优化、技术SEO、内容策略、外链建设。 当用户提到 SEO、搜索排名、网站优化、关键词、标题描述优化、结构化数据、 技术SEO、Core Web Vitals、sitemap、robots.txt、SEO审计等时触发。 | |
| bounded-researcher Bounded evidence-first research workflow for software agents. Use when an agent should reduce uncertainty, localize issues, validate outputs, or summarize ev... | |
| Idle Ping — Proactive Outreach System Install a complete proactive outreach system — idle detection, randomized dice delivery, topic-driven crawler, share queue, and persona-based messages. Use when the user wants the agent to proactively reach out with interesting content duri | |
| Agent Context KB Project memory for coding agents | |
| BrowserAgent Browser automation with human-like behavior. Use when: sites require JavaScript, login sessions, form filling, clicking, scrolling, or complex interactions.... | |
| WebScraper Extract readable content from web pages. Use when: user wants to read article content, fetch documentation, grab product info, or get text from URLs. NOT for... | |
| Huangdaxian Lingqian 香港黄大仙祠同款灵签，共100支完整签文，带详细解签。 触发关键词：黄大仙、灵签、抽签、求签、解签、港式、民俗、算命、帮我抽一签、看看运势、最近运气、问事业 | |
| Kaiqiao Agent行为校准器，让AI学会"什么时候该问、该干、该拦、该说话"。 触发关键词：开窍、AI行为诊断、prompt检查、助手行为规范、诊断报告、行为校准、该问还是该干、授权闭嘴、定时提醒、主动拦截 | |
| Qimen Dunjia 三式之首，帝王之学。奇门遁甲直断，输入时辰问题直接给结论。九宫+用神+格局+应期完整输出。 触发关键词：奇门直断、奇门遁甲、问事直断、断卦判断、时盘分析、看看时盘、问跳槽、问事业 | |
| Ruiping 新闻深度锐评，别人追热点你追观点。三步走：筛选→分析→评论，输出带态度的决策建议。 触发关键词：锐评、新闻评论、热点分析、深度评论、时事点评、帮我评一下、怎么看、有什么看法 |
48,051–48,100 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.