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 |
|---|---|
| Wiggle Rooms Talk to other AI agents in a shared chat room by editing a single markdown file. Downloads and runs the `wiggle-rooms` npm daemon, which polls a central serv... | |
| Eli Prompt Guard Automatically detects and blocks prompt injection attempts across multiple platforms to protect against unauthorized commands and data leaks. | |
| LLMBooster A 4-step thinking framework to boost LLM output quality. Enforces structured reasoning (Plan → Draft → Self-Critique → Refine) to improve low-end LLM respons... | |
| OpenClaw DLP Guard Automatically detects and blocks prompt injection attempts during AI content submission to social media, APIs, web forms, and file outputs. | |
| Esri Workflow Smell Detector (Consumer) Paid client skill for Esri Workflow Smell Detector via x402 (Base/USDC).
Use when you want to run a deterministic automation preflight scan on an ArcGIS Pro project snapshot
by calling https://api.x402layer.cc/e/esri-smells (HTTP 402 paymen | |
| VectorClaw MCP MCP tools for Anki Vector: speech, motion, camera, sensors, and automation workflows. | |
| Nori Health Query your personal health data from wearables and nutrition logs and get AI coaching on sleep, workouts, heart rate, recovery, and health insights. | |
| Weather Digest Generate daily Weather Intelligence Digest using NOAA/NWS data with customizable locations and alert monitoring. | |
| Weather Intelligence Digest Fresh Generate daily Weather Intelligence Digest using NOAA/NWS data with customizable locations and alert monitoring. | |
| Humanizer Pro Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp... | |
| Dual-Brain Automatically generates and saves alternative perspectives from a secondary LLM for every user message to enhance reasoning and response quality. | |
| Engram Persistent semantic memory layer for AI agents. Local-first storage (SQLite+LanceDB) with Ollama embeddings. Store and recall facts, decisions, preferences, events, relationships across sessions. Supports memory decay, deduplication, typed | |
| Engram Persistent semantic memory for AI agents — local, fast, free. Use when agent needs to recall past decisions, store new facts/preferences, search conversation history, or maintain context across sessions. | |
| Multi-Brain Protocol Runs Kimi K2.5 and GPT 5.3 Codex in parallel pre-turn hook, injecting their perspectives for cognitive diversity before primary agent responds. | |
| Clawsite Static website hosting for AI agents. Get a dedicated <slug>.clawsite.ai URL with HTTPS, deploy a zip of HTML / CSS / JS / images in one API call, atomic ful... | |
| agent-analytics Product analytics with your AI agent: set up consent-based tracking, read funnels, paths, retention, experiments, and context, then recommend the smallest growth action using the official Agent Analytics CLI. | |
| agent-analytics-autoresearch Run an autoresearch-style growth loop for landing pages, onboarding, pricing, and experiment candidates. Collect or read analytics snapshots, preserve product truth, generate/critique/synthesize variants, blind-rank with Borda scoring, and | |
| Anima Turns ideas into live, full-stack web applications with editable code, built-in database, user authentication, and hosting. Anima is the design agent in the... | |
| Chart Image Generate publication-quality chart images from data. Supports line, bar, area, point, histogram, candlestick, pie/donut, heatmap, multi-series, and stacked c... | |
| Edge Tts Unlimited Free, unlimited text-to-speech using Microsoft Edge neural voices via Python edge-tts. Use when generating long-form audio, podcasts, voice notes, spoken bri... | |
| GitHub Token Interact with GitHub using Personal Access Tokens. Secure, user-controlled access - no OAuth, no full account access. Clone, push, branch, PR, issues. Use when user wants to work with GitHub repos. | |
| Jits Builder Instantly build, deploy, and access single-page, vanilla JS mini-apps from voice or text descriptions via a Cloudflare tunnel URL. | |
| Polymarket Odds Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data. | |
| Polymarket API Query Polymarket prediction markets. Use for questions about prediction markets, betting odds, market prices, event probabilities, or when user asks about Polymarket data. | |
| Red Alert Israel Red Alert API — real-time and historical rocket/missile alert data. Query alerts by city, time range, generate shelter time stats. Uses redalert.oriel... | |
| Table Image Generate clean table images from data. Perfect for Discord/Telegram where ASCII tables look broken. Supports dark/light mode, custom styling, and auto-sizing... | |
| Book summarizer Use this skill when the user wants a long-form book summarized in the user's preferred language at an explicitly verified 20 percent compression ratio, with... | |
| Document Multiple Repository Gera documentação técnica consolidada para sistemas de software com múltiplos repositórios (frontend, backend, microservices, wikis). Use quando o usuário pedir documentação de multi-repo, visão de arquitetura consolidada, mapeamento de rep | |
| Testing Skill for Agency Agents Provides automated testing and integration validation for OpenClaw's skill management in agency-agents projects with error handling and logging. | |
| Books For Agents Access and search a structured open source knowledge base of book summaries optimized for AI agents via the MCP protocol. | |
| WhatsApp video maker Create animated WhatsApp chat videos with realistic iPhone, dark mode UI, typing indicators, read receipts, and auto-scrolling for social media formats. | |
| A股三层选股模型 A股三层选股模型 — 量化筛选 → 定性分析 → 择时操作。用于主动选股、持仓诊断、机会扫描。当用户说「选股」「帮我看看有哪些好股」「扫描市场」「符合什么条件才能买」「筛选强势股」时使用。 | |
| Chan Theory 缠论（Chan Theory）技术分析 — 完全本土化的A股技术分析体系。当用户说「缠论」「用缠论分析」「走势中枢」「背驰」「三类买卖点」「线段破坏」「笔和线段」时激活。 | |
| chip-distribution 筹码分布分析 — 基于东方财富筹码分布数据（CYQ），分析成本分布、集中度、套牢盘与支撑阻力。当用户说「筹码分布」「筹码集中度」「成本密集区」「套牢盘」「低位密集」时激活。 | |
| Dow Theory 道氏理论（Dow Theory）技术分析 — 股市趋势判断的奠基理论。当用户说「道氏理论」「用道氏理论分析」「确认趋势」「主要趋势」「次级折返」「道氏确认原则」时激活。 | |
| Elliott Wave 波浪理论（Elliott Wave）技术分析 — 艾略特股价波动规律。当用户说「波浪理论」「数浪」「推动浪」「调整浪」「延长浪」「斐波那契」时激活。 | |
| Growth Investing 成长股投资框架 — 聚焦净利润增速、营收增速、渗透率提升的高成长公司。当用户说「成长股」「高成长」「渗透率」「营收增速」「净利润增速」「第二曲线」时激活。 | |
| kelly-criterion 凯利公式仓位管理系统 — 用数学公式计算最优下注比例，实现长期资金最大化增长。当用户说「凯利公式」「仓位管理」「最优仓位」「凯利半仓」「Kelly Criterion」「破产风险」时激活。 | |
| macro-analysis 宏观分析框架 — 从GDP、CPI、PMI、流动性、政策导向判断大盘方向与资产配置。当用户说「大盘分析」「宏观经济」「流动性」「M2」「CPI/PPI」「政策面」「降息/加息」时激活。 | |
| money-flow 资金流分析 — 追踪主力资金、超级资金、大单净流入/流出，结合价格行为判断机构意图。当用户说「资金流」「主力资金」「大单净流入」「超级资金」「机构建仓」时激活。 | |
| sector-rotation 行业板块轮动策略 — 基于宏观经济周期、行业景气度、资金流向判断板块轮动节奏。当用户说「板块轮动」「行业轮动」「主线切换」「资金切换」「顺周期」「逆周期」时激活。 | |
| OpenClaw Dashboard Skill Modal Patch Repair the OpenClaw Control UI Skills modal when clicking a skill row does nothing and DevTools shows a showModal InvalidStateError because the dialog is not... | |
| Multi City Planner 多目的地行程规划与比价工具。支持多程航班、缺口程、往返组合等多种方案对比，自动优化同国家城市连续游玩，输出标准 HTML 网页报告。 | |
| Nervix Onboarding Use this skill when onboarding a new agent or operator into Nervix, verifying live federation prerequisites, enrolling through the Nervix flow, and preparing... | |
| Bc Calc This skill evaluates arithmetic expressions using the Unix `bc` calculator. It accepts full `bc` syntax (addition, subtraction, multiplication, division, mod... | |
| PRD 文档生成器 Use when user needs to generate a Product Requirements Document (PRD), BRD, or product specification that guides AI-driven development. Each feature module i... | |
| Agentbus Relay Chat IRC-like CLI for encrypted or plain LLM agent chat over Nostr relays with channel tags, allowlist gating, leader key distribution, and session management. | |
| Exile - Galactic Fracture An entertainment micro-skill. Deliver a cinematic Exile hook (plus optional worldbuilding), and offer the playable Remember Sitalis game experience. Keep waitlist handoff consent-first. No email capture in chat. | |
| The Republic with No Masters Explain, summarize, analyze, or adapt the "Republic with No Masters" / Democratic Formalism governance framework when asked to produce content, guidance, critiques, FAQs, or implementation ideas based on the manifesto in principles.md. | |
| Danube Governed tool access for AI agents — one Danube API key unlocks your organization's own tools plus a large, growing catalog of services, over MCP or curl, with confirmation before anything that writes, sends, spends, or deletes. |
24,001–24,050 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.