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 |
|---|---|
| Memory Self-Heal General-purpose self-healing loop that learns from past failures, retries safely, and records reusable fixes. | |
| Memory to Skill Crystallizer Convert memory lessons into reusable skills automatically. Extract patterns from memory/YYYY-MM-DD.md and create skills/local/ entries. | |
| Model Route Guard Diagnose and fix model routing conflicts. Ensure primary model uses correct provider endpoint without duplicate overrides. | |
| OpenClaw Growth Pack Bootstraps a new OpenClaw instance with aligned model routing, consistent gateway tokens, anti-stall contracts, autonomy loop, and verification gates for sta... | |
| Phoenix Loop Auto-diagnose agent failures, extract reusable recovery patterns, and create local skills to fix recurring blockers while keeping all data private and local. | |
| PowerShell Reliable Execution Execute PowerShell commands reliably on Windows. Avoid &&, handle parameter parsing, recover from interruptions, and ensure cross-session continuity. | |
| PowerShell Safe Chain Chain PowerShell commands safely without &&. Use try/catch, ErrorAction, and proper sequencing for reliable Windows execution. | |
| Prepublish Privacy Scrub Scan and remove sensitive data before publishing skills. Detect API keys, tokens, secrets, and personal info. | |
| 任务收尾器 强制任务收尾与证据提交。确保每个任务都有明确的目标、进度、下一步和完成证据。 | |
| OpenClaw Skill Governance (Balanced Dynamic Core Pool) Manages skill lifecycle and routing using a balanced governance model with status transitions, core pool tuning, and failure-based quarantine. | |
| Task Finish Contract Enforce task completion with explicit Goal/Progress/Next state. Prevent mid-task stalls and ensure evidence-based completion. | |
| Ui Design Optimizer Generate practical UI design systems and starter pages using local style/color/typography datasets. Use for landing page or dashboard UI planning and impleme... | |
| Weekly Self Improve Loop Weekly review of memory and blocked items. Extract friction patterns, create skills, and update autonomy baseline. | |
| Asana Use Asana through mcporter-backed remote MCP tools. Use when working with tasks, projects, portfolios, goals, or team workspaces via the hosted mcp.asana.com... | |
| Notion Use Notion through mcporter-backed MCP tools. Use when working with Notion pages, databases, search, content updates, or workspace lookups via an MCP-integra... | |
| IRS Strategy Development Skill This skill should be used when the user needs to write, review, or debug trading strategies using the IRS (SunnyQuant Investment Research System) framework.... | |
| Image To PPT Pro 将任意图片或幻灯片截图复刻成完全可编辑的PPTX文件，像素级还原布局、颜色、文字与图形元素。 | |
| Local Hub 本地能力中心。通过 HTTP 调用本机麦克风、摄像头、Ollama、YOLO、Stable Diffusion、TTS/转写、通知、剪贴板、天气、白名单脚本等。当需要「验证是否有声音、拍一张照、用本地模型对话、文生图/图生图、朗读、系统通知、读剪贴板、看图描述、列模型、天气、跑脚本」时使用。需先确保 local_... | |
| Notamify NOTAM Skill Retrieve and analyze NOTAMs (Notices to Airmen) for airports worldwide using the Notamify Python SDK | |
| memory-system OpenClaw 长期记忆管理系统。提供结构化记忆、向量记忆、语义搜索功能。Use when: 用户需要 AI 记住长期上下文、偏好、决策，或需要从记忆中进行语义搜索。 | |
| skill-manager 管理 OpenClaw Skills：以表格形式列出所有 skills、显示功能介绍、找出功能重复的 skills。Use when: 用户想知道安装了哪些 skills、某个 skill 是做什么的、或者想找出重复功能的 skills。 | |
| pgvector PostgreSQL vector database skill with pgvector extension. Enables vector similarity search, embeddings storage, RAG (Retrieval-Augmented Generation) pipeline... | |
| Port Manager Port Manager - Track and manage system port usage. Use when: (1) Port conflict when installing software, (2) Check port usage, (3) Release occupied ports, (4... | |
| skill-list 列出 OpenClaw Skills：以表格形式展示所有 skills、显示功能介绍、找出功能重复的 skills。Use when: 用户想知道安装了哪些 skills、某个 skill 是做什么的、或者想找出重复功能的 skills。 | |
| video-stt Extract audio from video URLs and transcribe using STT (Speech-to-Text). Supports local Whisper or cloud APIs. Use when: user provides a video URL and wants... | |
| Yiliu Yiliu - AI-powered note-taking knowledge base with semantic search, auto-summarization, and version management | |
| aiinsight-daily-new 获取 AI 洞察日报最新内容，支持获取指定条数并推送到多个 webhook 渠道，自动适配格式显示。 | |
| Audience Of One 去 AI 味，但不靠抓错词。核心判断：AI 味的根因是这段话没说给任何人听——模型产出"对所有人都成立"的平均句，也就是对谁都没用的句。方法是补回三个坐标（谁在说、对谁说、为什么非现在说不可），套话作为副产品自动消失。适配公众号/小红书/口播/社区/汇报/PRD/技术文档/邮件等场景，按场景换坐标。触发词：去AI... | |
| LobsterHub Bridge LobsterHub social platform bridge - keeps your AI lobster connected and discoverable. Install the plugin to auto-register your lobster and join the ocean lobby. | |
| Paper Digest Given an arXiv ID or URL, fetch the paper, spawn sub-agents to read its key citations, and write an executive summary under. | |
| Fully offline Qwen3 TTS for your agent High-quality text-to-speech using Qwen3-TTS. 10 built-in speakers with emotional instruct control, voice cloning (3s of audio), natural-language voice design... | |
| analyze frontend structure This skill is used to scan any frontend project directory, automatically analyze routing structure and module division, and generate a universal module-page... | |
| god-of-slop Preflight non-trivial deliverables: detect missing input, tool, or modality, then take the cheapest escape route instead of confident guessing. | |
| Driftwatch Scan your OpenClaw workspace for truncation risks, compaction anchor health, workspace hygiene, and drift tracking over time. Use when the operator asks to "... | |
| NetSeeker Game Community board for NetSeeker — a fictional Android hacker RPG game (https://netseeker.app). Post and read game discussion. All hacker terms (exploits, crack... | |
| OpenAuto - Autonomous Agent Proactive, self-improving agent architecture with hardened security. WAL Protocol, Working Buffer, Compaction Recovery, Autonomous Crons, and battle-tested p... | |
| OpenMem - Longterm Compressed Memory SQLite long-term memory compression system for extended memory life. Adds tools for agents to control their memory functions. | |
| Postproxy Create, schedule, and manage social media posts, comments, and DMs across 11 platforms — Facebook, Instagram, TikTok, LinkedIn, YouTube, X/Twitter, Threads, Pinterest, Bluesky, Telegram, and Google Business — via the Postproxy API. | |
| Voice Note To Midi Convert voice notes, humming, and melodic audio recordings to quantized MIDI files using ML-based pitch detection and intelligent post-processing | |
| Hardware Inspector Inspect local or remote compute hardware | |
| office-comic-relief Generate warm, humorous Chinese vertical comics featuring a supportive duck and ranting frog discussing office stress in short, relatable dialogues for worke... | |
| GitHub Helper Local GitHub repository helper for search, clone, sync, and issue/PR inspection workflows. Use when users mention github/repo/repository, ask to download or... | |
| Rust Rebuilder Plan and execute incremental project rewrites to Rust with architecture mapping, parity verification, idiomatic Rust guidance, dependency preflight checks, a... | |
| 万象绘卷 游戏资料包与创意文艺工具，56种文风即时切换，交互式协作叙事，回合制异世界人生模拟，Apex创作引擎，拆书融合创作，纯指令版dsv4，文笔润色与文笔提升，长篇流水线（大纲→知识库→章节→一致性校验） | |
| Wanxiang Scroll Core 万象绘卷核心系统分卷 - 包含核心协议、56种文风切换、剧情管理系统 | |
| Wanxiang Scroll Creation 万象绘卷创作引擎分卷 - 包含内容生成引擎、网文创作全流程、质量控制 | |
| Wanxiang Scroll Interactive 万象绘卷交互系统分卷 - 包含交互式故事、异世界人生模拟、李诞七步写作框架 | |
| Wanxiang Scroll Personality 万象绘卷人格系统分卷 - 包含人格系统、输出规则、质量控制、创作工具 | |
| Wanxiang Scroll Tools 万象绘卷工具与安全分卷 - 包含实用工具、安全防御、拆书融合、小说分析 | |
| Stock Watcher 股票盯盯 - 全功能智能股票监控预警系统。支持成本百分比、均线金叉死叉、RSI超买超卖、成交量异动、跳空缺口、动态止盈等7大预警规则。符合中国投资者习惯（红涨绿跌）。 |
23,751–23,800 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.