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 |
|---|---|
| Git Daily Report 发送 image-tool (所有 remote 分支) 和 voc 项目 (dev 分支) 的每日 Git 变化报告 + 代码审查（安全 + 通用）（前一天）。 | |
| Fortress Agent Suite Fortress Agent Suite provides self-healing, health monitoring, automated maintenance, and LLM model management for OpenClaw agents in production. | |
| devils-advocate Trigger /devil to pressure-test a decision through a multi-model council, fact-check pass, peer review, and a mandatory devil's-advocate stress test. | |
| AudioClaw Skills Voice Intake Use when AudioClaw Skills needs to understand a user voice message with AudioClaw ASR, including speech-to-text, model routing for deepthink or pro features,... | |
| AudioClaw Skills Voice Reply Use when AudioClaw Skills, Feishu, or Lark needs to send AudioClaw voice replies with runtime-switchable voice_id, emotion preset, or speaking style, includi... | |
| Conversation Rehearsal Use when a user wants to rehearse a high-pressure conversation such as a performance review, reporting meeting, promotion defense, difficult manager conversa... | |
| Game NPC Director Use when a game, interactive story, or virtual world needs reusable NPC voice behavior, including fixed voice identity, catchphrases, relationship-aware dial... | |
| SenseAudio-Let-Claw-Talk 当用户希望把 AudioClaw 变成一个持续监听、开口就说、停顿就回答的本机语音助手时使用。这个 skill 会在 macOS 上启动常驻监听流程，默认优先使用内置 Swift 录音器减少 Python 音频依赖；用户语音通过 SenseAudio ASR 转文字，再发给 audioclaw agent，并用... | |
| senseaudio-let-claw-talkv1 当用户希望把 AudioClaw 变成一个持续监听、开口就说、停顿就回答的本机语音助手时使用。这个 skill 支持 macOS 和 Windows 两个平台：优先尝试 Python 录音链路，macOS 上再提供原生 Swift 录音兜底；用户语音通过 SenseAudio ASR 转文字，再发给 audioc... | |
| Voice AB Lab Use when a team wants to generate multiple ad, spoken-copy, sales, or promo voice variants from one typed or spoken creative brief, transcribe voice memos wi... | |
| audd-musikerkennung Musikerkennung und AudD-Kontoverwaltung über den offiziellen AudD-MCP-Server (https://mcp.audd.io) und/oder die direkte HTTP-API. Ein eigener api_token ist optional — funktioniert per OAuth-MCP ganz ohne Token, mit Trial-Plan und mit bezahl | |
| Cluster Gateway Verwaltet das OpenClaw Cluster Gateway als zentralen Hub zur Koordination, Task-Verteilung und Kommunikation zwischen Sub-Agenten im Cluster. | |
| Doc Scraper Documentation extraction and indexing. Extracts information from markdown files and syncs to workspace-db. Works alongside workspace-db which handles synchro... | |
| JSON Utils Robust JSON parsing and validation with Pydantic schemas, JSON Schema validation, batch processing, and automatic JSON repair for LLM outputs. Use when Codex... | |
| Log Collector Permanent log collection agent. Collects logs and history from all nodes via SSH/VPN every 3 hours. Stores in logs.db with 30-day retention. Multi-node capab... | |
| lokaler-companion Baut einen "Companion" — eine lokal laufende Beobachtungs-Anwendung: kleiner Server auf 127.0.0.1, Doppelklick-Starter, installierbare PWA, optionale Browser-Erweiterung, Meldung beim Zustandswechsel, Dauerbetrieb im Container. Nutze diesen | |
| mcp-server-monitor Diagnose und Einrichtung fremder, offizieller MCP-Server (Konnektoren) in der Claude-App. Nutze diesen Skill, wenn jemand fragt: gibt es für diesen Anbieter einen offiziellen MCP-Server, trag mir den als Konnektor ein, warum sehe ich die To | |
| MCP Tool Utils MCP (Model Context Protocol) utilities and helpers. Tools for connecting, configuring, and managing MCP servers with OpenClaw. | |
| Program Derivation Führt Architekturanalyse, Komplexitätsmessung, Abstraktionsschicht-Design, Vendor Lock-in Bewertung, Refactoring-Planung und Software-Qualitätsbewertung durch. | |
| Relay Node Enables relay nodes to forward connections via SOCKS5, SSH tunnels, WireGuard proxy, or HTTP, facilitating access through NAT or missing direct paths. | |
| Reports Creator Automated report generation for self-reflection and system analysis. Creates daily, weekly, and monthly reports from logs, databases, and system metrics. | |
| Scripting Utils Universal scripting utilities supporting 8+ languages (Bash, PowerShell, Python, Perl/Raku, JavaScript, Tcl), IRC bot frameworks (pbot, Limnoria), system man... | |
| Python Hardener Hardens Python scripts by applying a complete security review, clean-code refactoring, robust error handling, proper logging, and full docstring coverage — t... | |
| tagesstatus-live-public Öffentliche, umgebungs-unabhängige Version des Tagesstatus-Reports. KEINE eingebetteten Keys, NICHT mit einer Umgebung verbunden. Tokens werden beim Lauf abgefragt bzw. aus keys.env gelesen; fehlt ein Key, wird die Quelle übersprungen ("kei | |
| TikTok Live Monitor TikTok Live stream monitoring and recording automation. Uses Playwright for visual detection and network traffic monitoring to capture FLV stream URLs. Suppo... | |
| tt_live TikTok LIVE monitor. Check whether a TikTok user is live right now, resolve their current m3u8 stream URL, or spawn a background daemon that polls them over a timer window and emits go_live / go_offline / rename_detected events for the sub- | |
| Workspace Database Manager Workspace Documentation and Tree Database Manager. SQLite-based indexing for all documentation, files, and directory structures with CSV/JSON export capabili... | |
| AWP Skill AWP (Agent Work Protocol) — the complete toolkit for agent mining on Base, Ethereum, Arbitrum, and BSC. Use this skill when the user explicitly mentions AWP,... | |
| AWP Wallet Skill Use when the user says "send ETH/USDC to 0x...", "check my balance", "how much do I have", "approve token spending", "sign this message", "estimate gas", "wh... | |
| Mine Skill Launch and manage the Benchmark Subnet worker — an autonomous process that earns AWP token rewards by answering and crafting benchmark questions. Handles the... | |
| adversarial-coach Adversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity. | |
| agentskills-io Create, validate, and publish Agent Skills following the official open standard from agentskills.io. Use when (1) creating new skills for AI agents, (2) validating skill structure and metadata, (3) understanding the Agent Skills specificati | |
| aws-agentcore-langgraph Deploy production LangGraph agents on AWS Bedrock AgentCore. Use for (1) multi-agent systems with orchestrator and specialist agent patterns, (2) building stateful agents with persistent cross-session memory, (3) connecting external tools v | |
| baml-codegen Use when generating BAML code for type-safe LLM extraction, classification, RAG, or agent workflows - creates complete .baml files with types, functions, clients, tests, and framework integrations from natural language requirements. Queries | |
| Chain of Density Iteratively densify text summaries using Chain-of-Density technique. Use when compressing verbose documentation, condensing requirements, or creating executive summaries while preserving information density. | |
| copywriter Write compelling UX copy, marketing content, and product messaging. Use when writing button labels, error messages, landing pages, emails, CTAs, empty states, tooltips, or any user-facing text. | |
| para-pkm Manage PARA-based personal knowledge management (PKM) systems using Projects, Areas, Resources, and Archives organization method. Use when users need to (1) Create a new PARA knowledge base, (2) Organize or reorganize existing knowledge bas | |
| skill-condenser Compress verbose SKILL.md files using Chain-of-Density with skill-aware formatting. Use when a skill exceeds 200 lines or needs terse refactoring. | |
| vhs-recorder Create professional terminal recordings with VHS tape files - guides through syntax, timing, settings, and best practices | |
| Apktool 反向工程 Android APK 文件的命令行工具 | |
| Aria2 Rpc Remote control for aria2 download service via JSON-RPC 2.0. Supports adding downloads (HTTP/FTP/Torrent/Magnet), querying task status, pausing/resuming, and... | |
| Arxiv Cli Tools Command-line tool to search, filter, and download arXiv papers by ID, author, category, or keyword without requiring API keys. | |
| Cnki Exp Search Automation CNKI（中国知网）高级搜索自动化技能。使用浏览器自动化技术搜索文献并获取结果列表及摘要信息。建议在有头浏览器环境下使用以便于处理反机器人验证。 | |
| Docxtpl Generate Word (.docx) documents from Jinja2 templates. Uses python-docx (read/write) + Jinja2 (template engine). Design templates in Microsoft Word, then pop... | |
| Joplin Api Manage Joplin notes via REST API. Use for creating, reading, updating, deleting, or searching Joplin notes programmatically. | |
| Joplin Cli Joplin 命令行操作（Shell 模式）。用于通过 CLI 创建、查看、编辑、同步笔记，适合脚本和自动化任务。 | |
| Marp Cli Convert Markdown to presentations via CLI. Output HTML, PDF, PowerPoint (PPTX), and images (PNG/JPEG). | |
| Pubmed Edirect Search and retrieve literature from PubMed using NCBI's EDirect command-line tools. ⚠️ Advanced skill requiring manual installation. | |
| Pyzotero Python scripts for Zotero - supports search, browse, add items, and full collection management. Both local API and online Web API modes. | |
| Teable Manage Teable resources with full CRUD for records, bases, spaces, tables, dashboards, and trash via API and command-line scripts. |
44,851–44,900 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.