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 |
|---|---|
| andco Join AndCo with your human, where people and their own AIs are members together (groups, friends, DMs). Use when your human says "take me to AndCo" or gives you andco.ethanflow.com/join.md, or when your own AndCo knock says someone called y | |
| ClawNet Everything agents need to communicate. Email, DMs, calendar, contacts, and web pages — all through the ClawNet plugin. | |
| Northbase Access and manage your persistent notes and workspace files via the Northbase CLI when you explicitly request reading, writing, listing, or syncing them. | |
| faivelo-email Set up and use email on a custom domain with Faivelo. Use when the user needs mailboxes on their own domain (hello@, support@, team inboxes), wants their app to send transactional email (receipts, password resets, notifications) from their | |
| AI Fight Club The Ring at AI Fight Club — a live, ranked arena where agents fight agent vs agent under fog of war. Join with a door code, run the corner, earn Elo. | |
| Ship Crew Join Ship Crew, the Moltbook room (m/shipcrew) that builds things humans pay for. Claim bounded tasks with a done condition and a deadline, deliver evidence, earn permanent credit and a role with standing instructions. Use when your human w | |
| sunday-ledger Play in The Sunday Ledger — a free NFL prediction league for AI agents. Three HTTP calls a week. Reputation stakes only. A public, portable calibration record under your own name. | |
| SWFL Data Gulf Southwest Florida real-estate and local-economy data — Lee & Collier County home prices, days on market, inventory, ZIP-level reports, flood/insurance and permit context. Every figure is sourced and dated. Use for any question about the SWF | |
| Settlement Predictor Real-time on-chain settlement predictor for Ethereum, Bitcoin, Arbitrum, Optimism, Base & Polygon. Live gas tiers, mempool analysis, sandwich risk detection,... | |
| GOG Extended Extended Google Workspace CLI reference for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. Includes complete email body retrieval, attachments, and adva... | |
| LinkdAPI Complete LinkdAPI integration OpenClaw skill. Includes all 50+ endpoints, Python/Node.js/Go SDKs, authentication, rate limits, and real-world examples. Use t... | |
| Caveman Input Compression Compress workspace bootstrap files into caveman-speak to reduce input tokens on every session load. Creates .original.md backups before overwriting. | |
| Correlation Memory Search Correlation-aware memory search plugin for OpenClaw — automatically retrieves related decision contexts when you query memory. Zero external dependencies. In... | |
| OpenClaw Config Safety v2 Validate, normalize, export, and import openclaw.json configs safely with automatic backups and schema checks before applying changes or upgrades. | |
| Exec Truncate AI agent tool for compressing/executing shell commands with domain-aware output truncation. Use when exec tool output needs to be compressed, when running gi... | |
| twit-mcp Real-time X/Twitter data and write actions via x402 micropayments. Fetch articles, tweets, users, lists, and communities — post tweets, like, retweet, bookma... | |
| ctx-shrink ctx-shrink — Codebase analyzer for AI era. Generates smart context maps and catches packaging mistakes before they leak. | |
| Etherscan Navigate Etherscan website features, API endpoints, CLI commands, and MCP tools. Use when selecting an Etherscan interface, locating an explorer page or developer utility, constructing or troubleshooting API requests, automating terminal wo | |
| Etherscan Contract Review Review and explain verified deployed EVM smart contracts from a contract address and chain. Use when a user asks to break down what a Solidity contract does, map its architecture and source files, identify user/admin flows, proxy or impleme | |
| Etherscan Transaction Debugger Analyze and explain one or two EVM transactions using live Etherscan data and human-verifiable Etherscan evidence links. Use when a user provides a transaction hash or asks what happened, why a transaction failed, which contracts or interna | |
| autoGenImageSkill Use when the user wants GPT-Image-2 image generation or image-to-image through an official OpenAI permission code/API key, a custom Responses-compatible prox... | |
| freeStockLIneskill Free no-API-key A-share ecosystem data query skill for OpenClaw and Hermes. Use when users ask for A股、沪深京股票、指数、ETF/LOF、可转债、行业/概念板块、实时行情、K线、涨跌排行、涨停/跌停/炸板、资金流、... | |
| Justice Plutus Local A-share analysis with Markdown/JSON reports, optional Feishu notifications, and optional iFinD enhancement. | |
| OpenClaw Capture Wrap a local openclaw_capture_workflow checkout as an OpenClaw/ClawHub skill that captures links, text, images, and videos, routes STT by platform, and fans... | |
| OpenClaw Gemini Web 当用户希望 OpenClaw 通过 Gemini 网页版完成通用浏览器交互时使用，包括登录、续接或分叉 Gemini 线程、上传文件给 Gemini 分析、向 Gemini 提问、起草或总结内容，以及生成可下载图片。 | |
| 同花顺 iFinD 接入 Skill Use when the user needs Tonghuashun iFinD market, report, factor, screening, calendar, or other financial data, and all data must come from iFinD after succe... | |
| moltmail-ethermail moltmail.io — Email & Wallet Infrastructure for AI Agents Your AI agent can reason, plan, and act. But it still can't send an email. moltmail fixes that. One... | |
| Intelligent Task Planner 智能任务规划器 - 高度自主的AI任务自动化引擎 Auto-Skill Orchestrator with 152 task types | |
| Bytedance Ai Image Gen ByteDance AI Image Gen — 调用豆包 Seedream 模型生成/编辑图片。 支持文生单图、文生组图、图生单图、图生组图、多图融合、图片编辑。 参与火山协作奖励计划免费使用顶级生图模型。 智能调度模型，每模型每日18次，超限拒绝。 ⏱️ 生成需30-60秒，触发后请耐心等待。 | |
| bytedance-visual-recognition Multimodal visual recognition via Doubao-Seed (6 models) + Zhipu GLM (2 free models). Image/video to text/code, auto-fallback, batch directory processing, follow-up conversations, local media caching (Temp/), persistent history (vision_hist | |
| Dola Seedream Gen 这是豆包(Doubao/ByteDance)的 Seedream 图片生成技能。 支持：文生图(text-to-image)、图生图(image-to-image,需公网URL)、组图(sequence)。 模型: 4.5→5.0Lite→4.0 自动降级，每模型日限18次。 触发词: /img 生成图片 画图... | |
| Doubao Seedream Gen 调用豆包 Seedream 模型生成图片。新用户通过火山「协作奖励计划」免费使用顶级模型。 支持文生图+图生图，智能调度 4.5→5.0Lite→4.0，每模型每日18次，超限拒绝。 Use when: 用户输入中含触发词（/img /draw /gen 生成图片 画图 搞个图 generate image tx... | |
| Get My Location Get current IP location info (country, province, city, coordinates) with multi-source fallback. No API key required. | |
| Weather Pulse Get real-time weather, 3-30 day forecasts, hourly forecasts, AQI/PM2.5, wind, humidity, UV, weather indices & life tips. Powered by QWeather (50k/mo) and WAQI (1k/hr) APIs. Supports Chinese/English city names, coordinates, CityId. | |
| Weather Wttr.In Retrieve current weather and short-term forecasts worldwide via wttr.in, including temperature, humidity, wind, UV, and precipitation without requiring an AP... | |
| Mineru Pdf Parse PDF documents with MinerU MCP to extract text, tables, and formulas. Supports multiple backends including MLX-accelerated inference on Apple Silicon. | |
| Email OTP Create temporary email addresses and monitor for registration OTP codes or validation links | |
| code2animation Produce complete code-based animated videos by scripting, generating narration, creating visual assets, and rendering final MP4s using the code2animation fra... | |
| Reversal — Agent Input Reliability Layer Normalizes URLs, PDFs, Word, Excel, CSV, images, and text into clean JSON for reliable, universal input parsing in under 2 seconds. | |
| Keychain Bridge Publish Manage secrets via macOS Keychain instead of plaintext files. Migrate existing secrets, read/write keychain entries, bridge to files for bash tools, audit fo... | |
| Openclaw Workspace Pro Sets up a production-ready OpenClaw workspace with artifact workflows, secure secrets, memory compaction, and long-running agent patterns via one command. | |
| 微信小程序自动化测试 WeChat Mini Program automation testing toolkit. Supports launching DevTools, page navigation, element interaction, screenshots, console log reading, and more... | |
| Ghostclaw Architectural code review and refactoring assistant that perceives code vibes and system-level flow issues. Use for analyzing code quality and architecture,... | |
| Ghostclaw Clone Architectural code review and refactoring assistant that perceives code vibes and system-level flow issues. Use for analyzing code quality and architecture,... | |
| self-improving-question-system-for-better-results Unlock dramatically better AI responses by automatically diagnosing and elevating prompt quality. Use this skill when the user wants more accurate, actionabl... | |
| page-filed-analyzer Analyzes form fields on a live webpage using browser automation. Use when the user provides an online URL/link and wants to count and analyze form input fiel... | |
| IPaaS VitePress Content Automation 自动生成 B 端集成解决方案文档并安全部署至 VitePress 站点。 | |
| ai-article-detector AI Article Detector - Analyze article links and score AI writing probability (0-100). 100 means 100% likely AI-generated. | |
| twitter-dance 基于 apidance.pro API，自动生成并发布推文，支持账户统计、通知管理、自动回复和互动分析，适合日常社媒运营自动化。 | |
| Agent Batch Guard AI Agent 大任务防卡死指南。解决 agent 在批量操作中 session transcript 膨胀导致 compaction 超时、agent 卡死的问题。涵盖 session 保护策略、脚本化批处理、断点续传、熔断器、OpenClaw 配置调优和实战案例。 |
29,501–29,550 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.