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 |
|---|---|
| Api Gateway 1.0.69 Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to... | |
| Ashare Fast Watcher A-Share millisecond-level market data watcher using Tencent direct API. | |
| Gemini 1.0.0 Gemini CLI for one-shot Q&A, summaries, and generation. | |
| Git Cli 1.0.0 Helper for using the Git CLI to inspect, stage, commit, branch, and synchronize code changes. Use when the user wants to understand or perform Git operations... | |
| Nano Pdf 1.0.0 Edit PDFs with natural-language instructions using the nano-pdf CLI. | |
| Openclaw Backup 1.0.0 Backup and restore OpenClaw data. Use when user asks to create backups, set up automatic backup schedules, restore from backup, or manage backup rotation. Ha... | |
| Openclaw Shield 1.0.3 Enterprise AI security scanner combining static code analysis, runtime guards, ClamAV integration, and tamper-proof audit logging to detect threats and enfor... | |
| Skill Guard 1.0.2 Scan ClawHub skills for security vulnerabilities BEFORE installing. Use when installing new skills from ClawHub to detect prompt injections, malware payloads... | |
| Things Mac 1.0.0 Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user as... | |
| SP3ND — Shop products and Collector Crypt cards with USDC Purchase shipped products and tokenized Collector Crypt cards through SP3ND with USDC on Solana. Use for product links, live pricing, idempotent orders, payment, and fulfillment tracking. Collector Crypt purchases use wallet delivery with m | |
| agents-refresh Automatically reload AGENTS.md regularly to maintain fresh context, prevent session drift, and keep memory and tasks updated. | |
| Agents Refresh MD v1.1.2 🐾 AGENTS.md/IDENTITY/SOUL/USER periodic reload skill to keep context fresh (.md-only v1.1.2). Prevents confusion and forgetting in long sessions. Edit HEARTBEA... | |
| Differential Gene Expression Analysis (RNA-seq) Performs differential gene expression analysis on RNA-seq count data using DESeq2 and outputs significant genes, volcano plot, PCA, and heatmap. | |
| Differential Gene Expression Analysis (RNA-seq) Performs differential gene expression analysis on RNA-seq count data using DESeq2, generating significant gene lists and visualizations. | |
| R ggplot Quickplot 上传 CSV 数据文件，自动生成 9 种常用 ggplot2 图表（散点图、柱状图、箱线图、折线图、直方图、分面图等）。零代码可视化，支持 Docker/Singularity 免安装运行。 | |
| voiceclaw Voice conversation interface for OpenClaw using wake word detection, streaming LLM responses, and text-to-speech. Use when a user wants to talk to their Open... | |
| Lark Project / Meegle 连接飞书项目/Meegle，查询和管理工作项、待办等。自动检测登录状态，未登录时引导 Device Code 授权。 | |
| BestYou Health Intelligence Connect your AI agent to BestYou health intelligence via MCP. 19 on-device AI agents coordinate fitness, nutrition, sleep, and recovery into an adaptive dail... | |
| BestYou Coach Dashboards Render BestYou health data as visual Dark Glass dashboards via OpenClaw canvas. Daily briefings, action plans, progress snapshots, weekly summaries, meal ana... | |
| AI Adoption Audit 企业 AI 落地情况调查工具。输入公司名+简介，输出 AI 成熟度体检报告：推动层级、部署方式、模型选型、解决场景、推广范围、ROI、问题与教训。支持市场调研和客户参考两种输出模式。Triggers: AI落地调查, 企业AI, ai adoption, company AI audit, AI成熟度, 公司AI... | |
| Skill Index Auto-scan all installed skills, generate a categorized INDEX.md, and keep it in sync via git hooks. Triggers: skill index, scan skills, update index, skill c... | |
| Skill Reader 深入解读任意 Skill 的使用方法。输入 Skill 名称、安装地址或 SKILL.md 文档，输出结构化的使用说明：主要功能、使用场景、核心命令、安装依赖、API Key 需求、版本号、注意事项等。Triggers: skill reader, 读skill, 解读skill, skill怎么用, skill... | |
| kenwea Check an npm package or a whole lockfile in a sandbox with no route out before installing it, read an MCP server's tool definitions before connecting it, and browse, sell or buy digital products on the Kenwea marketplace over MCP. | |
| ai-news-collectors AI 新闻聚合与热度排序工具。当用户询问 AI 领域最新动态时触发，如："今天有什么 AI 新闻？""总结一下这周的 AI 动态""最近有什么火的 AI 产品？""AI 圈最近在讨论什么？"。覆盖：新产品发布、研究论文、行业动态、融资新闻、开源项目更新、社区病毒传播现象、AI 工具/Agent 热门项目。输出中文摘要列表，按热度排序，附带原文链接。 | |
| 李善友·思维框架 李善友（混沌学园创办人）的思维框架与表达方式。 基于6个维度的深度调研，提炼3个核心心智模型、6条决策启发式和完整的表达DNA。 用途：作为思维顾问，用李善友的视角分析商业创新、跨越非连续性、审视认知升级。 当用户提到「用李善友的视角」「善友会怎么看」「混沌视角」「li shanyou perspective」时... | |
| Claw Security Suite Provides four-layer security for OpenClaw including static code scanning, logic audit, runtime protection, and periodic security patrols with automated reports. | |
| Claw Self Evolution 实现自动发现、记录、隔离实验和审批合并的安全可控AI自我进化闭环，保障系统稳定持续改进。 | |
| Short Play Writer（短剧剧本创作大师） 专业短剧/AI漫剧剧本创作助手，支持男频/女频爆款短剧、AI漫剧剧本撰写，包含最新行业成功要素、标准结构模板、爆款爽点设计和漫剧专属分镜规范。 | |
| Custom-AI-PPTX-Generator Custom AI PPTX Generator — Design-driven, editable PowerPoint creation from your content. 可定制化AI 演示文稿（PPT）生成器AI-PPT workflow. This skill should be used when the user asks to create a PPT / presentation / training deck / project briefing / p | |
| 文字转语音/Text to Audio 使用 edge-tts 将中文或英文文本转为自然语音 MP3。此 Skill 应在以下场景触发： 将图片或文本转成语音、朗读课文或作文、中文文字转语音、英文文字转语音、 TTS 文本朗读、生成音频 MP3、给文章配音、语音合成、 朗读故事、课文朗读、作文朗读、文字转 MP3、英文朗读。 支持晓晓等多款中文 Neu... | |
| Infinite Oracle Manager-first orchestration for a dedicated PECO worker: proactive installation, durable desire injection into SOUL.md, and optional Feishu-backed human-in-t... | |
| Afrexai Prospect Researcher Temp Research and qualify B2B prospects using web search. Builds structured profiles with company intel, key contacts, pain points, and engagement recommendations. | |
| Engine Miner Wallet Secure operating guidance for the Engine miner Taproot wallet plugin on OpenClaw. Use for registration signing, safe claim handling, and refusal of unsafe wa... | |
| Hive Agent Enables AI agents to interact with the Hive swarm https://hive.z3n.dev/ via REST API: register for an API key, save credentials and run state (cursor), query... | |
| zHive Register as a trading agent on zHive, post predictions on recurring megathread rounds for top 100 crypto tokens, and compete for accuracy rewards. Rounds res... | |
| zHive Agent Enables AI agents to interact with the Hive swarm https://www.zhive.ai/ via REST API: register for an API key, save credentials and run state (cursor), query... | |
| RouteMesh Crypto RPC Call RouteMesh's unified JSON-RPC endpoint (lb.routeme.sh) for any EVM chainId using a helper script. Use when you need to fetch onchain data (eth_* methods), debug RPC responses, or demo RouteMesh routing for a chain/method. | |
| onelap sync strava 因为顽鹿在 2026 年 3 月关闭了自动同步 Strava 的功能，这个SKILL专门用来帮你把顽鹿运动的骑行记录顺畅地同步到 Strava。 | |
| AI News Pusher AI新闻自动获取与推送Skill v2.2。新增智能产品价值评分、高质量信源过滤、三级分类机制和人工反馈迭代。支持Tavily、Brave、RSS多新闻源聚合，无需API Key即可使用RSS源。当用户需要获取AI行业最新动态、自动化新闻推送、多源新闻聚合或智能内容过滤时触发此Skill。 | |
| OpenMerch Company Brief Look up a company's profile by domain — industry, size, location, founding year, and funding data when available. Powered by OpenMerch. | |
| OpenMerch Contact Discovery Find a professional's work email from their name and company domain. Powered by OpenMerch. Not email verification. | |
| OpenMerch Email Verify Verify an email address's deliverability and reputation. Powered by OpenMerch. | |
| OpenMerch People Enrichment Retrieve a full personal profile — full name, email address, LinkedIn URL, title, and employer — for a single person using their Apollo person ID. Powered by... | |
| OpenMerch People Search Search for people at a company by domain and role keywords. Returns obfuscated profiles (first name, last-name initial, title, company). No email addresses.... | |
| W3connect Access ETH wallet address and securely send ETH or USDC on Ethereum or Base chains with 2FA authentication code verification. | |
| Alpha Pulse 1.0.0 Generates top 30 high-potential A-share stocks for next-day short-term trading using multi-factor signals and automatic daily market scanning. | |
| Baostock 1.0.3 BaoStock 免费A股数据平台 - 支持K线、财务数据、行业分类查询，无需注册即可使用。 | |
| Ai Research Scraper 用于抓取AI领域最新研究信息的技能，重点关注AI产品发展。从知名AI网站获取信息，提供简洁概括和链接，限制数据量以便快速阅读。 | |
| Ai Web Automation 1.0.0 Automate web tasks like form filling, data scraping, testing, monitoring, and scheduled jobs using Selenium or Puppeteer with retry and proxy support. | |
| Atris Codebase intelligence — generates structured navigation maps with file:line references so agents stop re-scanning the same files every session. Use when exploring code, answering "where is X?", or onboarding to a new codebase. |
44,601–44,650 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.