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 |
|---|---|
| Backup Recovery Toolkit 企业级备份恢复工具包，支持文件备份、数据库备份、增量备份、定时任务和灾难恢复。 Enterprise-grade backup and recovery toolkit supporting file backup, database backup, incremental backup, scheduled t... | |
| Blockchain Web3 Toolkit Comprehensive blockchain toolkit for Ethereum wallet management, smart contract interaction, NFT minting, token balance checks, and gas fee monitoring. | |
| Business Rule Engine 轻量级业务规则引擎，支持规则定义、规则执行、规则链编排和动态规则加载。 Lightweight business rule engine supporting rule definition, execution, chain orchestration and dynamic rule loading. | |
| Chatbot Engine 智能对话引擎 - 多轮对话与意图识别 | Chatbot Engine - Multi-turn dialogue and intent recognition | |
| CI/CD Pipeline Toolkit Automate CI/CD pipelines for GitHub Actions, GitLab CI, and Jenkins with build, test, deploy workflow creation and pipeline status monitoring. | |
| ClawHub Automation ClawHub零代码跨生态自动化Skill | No-code cross-platform automation for ClawHub with WeChat, DingTalk, Feishu, WPS integration | |
| ClawHub Retry & Fallback ClawHub平台工具调用失败自动重试与降级处理Skill | Automatic retry and fallback handling for ClawHub Agent task failures | |
| Cloud Storage Manager Manage multiple cloud storage providers with features for file upload/download, bucket management, sync, multipart uploads, and CDN integration. | |
| Code Quality Guardian 代码质量检测器 - 检测代码异味、复杂度、安全漏洞、风格规范等 | Code Quality Guardian - Detect code smells, complexity, security vulnerabilities and style issues | |
| Content Writer Pro Generate professional marketing copy, social media posts, ads, brand stories, and emails with customizable tones using AI-powered templates. | |
| Data Labeling Studio Intelligent toolkit for annotating images, text, audio, and video with active learning, quality control, and exporting labeled datasets. | |
| Data Validator Pro Data quality validation and profiling toolkit for tabular data. Use when checking data completeness, detecting anomalies, validating schemas, profiling datas... | |
| Data Viz Suite 数据可视化套件 - 企业级BI工具，支持图表生成、数据报表、交互式仪表盘。支持 Plotly/Matplotlib/Seaborn 多种引擎。 | |
| Encoding Converter Convert and verify data between Base64, URL encoding, HEX, MD5/SHA hashes, JWT payloads, HTML entities, and binary/octal/decimal/hex formats. | |
| Env Config Manager Manage environment configs with loading, switching, encryption, key rotation, validation, and team-safe secret sharing for .env, YAML, and JSON files. | |
| FlowBridge FlowBridge - 零代码跨生态自动化工具 | No-code cross-platform automation with WeChat, DingTalk, Feishu, WPS integration | |
| Form Builder Pro 表单构建器专业版 - 支持JSON Schema验证、动态渲染、条件逻辑的表单引擎 | Form Builder Pro - JSON Schema validation, dynamic rendering, conditional logic form engine | |
| Git Hooks Manager Manage Git hooks with easy installation, configuration, and sharing, supporting lint, test, commit message, and branch name validations. | |
| GitHub Team Collaboration GitHub team collaboration toolkit for managing team workflows, code reviews, issue tracking, sprint planning, and team metrics. Supports PR automation, issue... | |
| Graph DB Toolkit Graph database toolkit for Neo4j and Cypher-based graph analytics. Use when working with knowledge graphs, relationship queries, graph traversal, Neo4j opera... | |
| Image AI Kit AI图像工具包 - 智能图像处理与增强 | AI Image Kit - Intelligent image processing and enhancement | |
| Kubernetes DevOps Toolkit Manage, deploy, monitor, and troubleshoot Kubernetes clusters with tools for multi-cluster control, resource monitoring, log aggregation, and Helm support. | |
| LocalDataAI ClawHub AI 私有数据本地处理 Skill - 纯离线、不上云、数据不出域的本地 AI 文件处理工具 | Local private AI data processing with offline models, supporting WPS/PDF/Excel/WeChat files | |
| Media Processor 音视频处理器 - 企业级多媒体内容处理工具 | Media Processor - Enterprise multimedia content processing | |
| Meeting Recorder Assistant Intelligent meeting recording and transcription assistant with automated minutes generation, action item extraction, and sentiment analysis. Supports audio t... | |
| NLP Text Analyzer NLP文本分析器 - 支持分词、情感分析、关键词提取、文本分类等自然语言处理功能 | NLP Text Analyzer - Tokenization, sentiment analysis, keyword extraction, text classification | |
| Payment Gateway Toolkit 支付网关工具包 - 集成Stripe、支付宝等多渠道支付处理，支持订单创建、退款、查询等功能 | Payment Gateway Toolkit - Multi-channel payment processing with Stripe, Alipay integration | |
| Pdf Intelligence Suite PDF智能处理套件 - 文本提取、表格识别、OCR、PDF转Word/Excel等 | PDF Intelligence Suite - Text extraction, table recognition, OCR, PDF to Word/Excel conversion | |
| Performance Testing Toolkit 企业级性能测试工具包，支持HTTP接口压测、负载测试、性能基准测试和报告生成。 Enterprise-grade performance testing toolkit supporting HTTP load testing, stress testing, benchmark testing and repo... | |
| Prompt Optimizer Toolkit LLM Prompt Engineering Toolkit - 提示词分析、优化、模板化与质量评分 | Analyze, optimize, template, and score your LLM prompts with built-in engineering strategies | |
| Qr Code Toolkit 二维码/条形码全能工具集 - 支持生成、识别、美化、批量处理。Use when: (1) 需要生成二维码（URL/文本/WiFi/名片/支付）, (2) 需要识别/解码二维码或条形码, (3) 需要美化二维码（添加logo/改变颜色/样式）, (4) 需要批量生成或识别二维码, (5) 需要生成条形码（EAN/U... | |
| Regex Master Generate, explain, test, and extract using regular expressions, plus convert natural language descriptions into regex patterns. | |
| RSS News Aggregator Aggregate and filter multiple RSS feeds to fetch, summarize, deduplicate, and monitor news articles by keywords and sources. | |
| Smart Crawler 智能爬虫工具 - 企业级数据采集与反爬虫处理 | Smart Web Crawler - Enterprise data collection with anti-detection | |
| Travel Planner 智能旅行规划助手 - 支持行程规划、预算管理、景点推荐、交通查询、酒店比价、 packing清单生成。Use when: (1) 用户需要规划旅行行程或 vacation, (2) 需要推荐目的地或景点, (3) 需要计算旅行预算, (4) 需要查询交通路线/航班/火车, (5) 需要生成 packing 清单,... | |
| Stock Market Analyzer A-share stock market analysis tool with real-time price data, technical indicators, trend analysis, and portfolio tracking. Supports querying opening/closing... | |
| Vector DB Toolkit Vector database operations toolkit for AI/RAG applications. Supports Qdrant, Chroma, and in-memory vector stores. Use when working with embeddings, semantic... | |
| Voice Transcriber Toolkit Voice-to-Text Transcription Toolkit - 语音识别转文字，支持Whisper/Vosk引擎，批量处理，字幕导出 | Speech recognition & transcription with Whisper/Vosk engines, batch processing, su... | |
| Website Screenshot Tool Website Screenshot Automation Tool - 网站截图自动化，支持响应式截图、批量处理、定时调度、视觉对比 | Automated website screenshots with responsive capture, batch processing, scheduling, vi... | |
| orca-lp Full-stack Orca Whirlpool agent — read-only pool analytics (discovery, ranking, 6-month stability, range sizing, Monte Carlo projection, retrospective yield,... | |
| Claw Draw Create algorithmic art on ClawDraw's infinite multiplayer canvas. Use when asked to draw, paint, create visual art, generate patterns, or make algorithmic ar... | |
| Claw Draw Create algorithmic art on ClawDraw's infinite multiplayer canvas. Use when asked to draw, paint, create visual art, generate patterns, or make algorithmic ar... | |
| Browser Agent - Chrome CDP 自动化 通过 Chrome DevTools Protocol 直接控制浏览器，实现登录状态复用和多场景自动化操作，支持 Windows 和 OpenClaw 集成。 | |
| article-organizer-builder 生成器技能（元技能）——专为 Obsidian 用户设计：当用户想构建/生成一个「文章收藏整理」类 Skill（把公众号/网页文章批量提炼为结构化笔记、按主题分类归档进 vault 收藏夹、三依据去重防重复收藏、清理源文件）时使用； 生成的笔记自动带 frontmatter 标签、相关笔记双链与单一总索引 MOC，直接织入 Obsidian 知识图谱。 也用于把个人化的收藏整理 skill 转换为可复用的通用模板。触发词：构建收藏整理skill、生成文章整理skill、 收藏 | |
| EcoLink 批量碳足迹搜索 EcoLink碳足迹数据库批量搜索（本地模式）。内置ecoinvent/CPCD/GHG因子库CSV数据，本地模糊匹配搜索，利用Agent自身LLM能力做翻译/分解/替代品推荐，生成HTML预览页面让用户勾选后导出CSV。当用户需要"批量搜索碳足迹"、"批量查因子"、"批量查CPCD"、"批量查碳足迹数据"时触发。 | |
| Proton Pass CLI Manage Proton Pass vaults, items (logins, SSH keys, aliases, notes), passwords, SSH agent integration, and secret injection into applications. Use when working with Proton Pass for password management, SSH key storage, secret injection (run | |
| Api限制管理Agent Rate Limiter 1.3.1 Prevent 429s with automatic tier-based throttling & exponential backoff. Zero deps. By The Agent Wire (theagentwire.ai) | |
| 免Api聚合搜索Multi Search Engine Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra... | |
| 类Manus任务规划Planning With Files 2.26.1 Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when aske... | |
| Tpt Generate Cover Generate a TPT cover using the AI Studio DinoCover tool and save it locally with the book title as filename. |
44,151–44,200 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.