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 |
|---|---|
| AI KEY·短命令 AI KEY·短命令 ——AI KEY（AI 钥匙）工具箱的短命令。`/key` 和 `/aikey` 完全一样，只是少敲三个字母 —— 它把你交给总入口，由总入口按你卡在哪挑技能。 两套技能：做内容（选题 / 写稿 / 标题 / 开头 / 审核 / 剪辑 / 复盘）· 看生意（营收归因 / 大客户集中度 / 依赖风险 / 多产品线取舍 / 目标拆路径 / 趋势押什么 / 决策 / 到期追踪）。 触发方式：/key、/key 新手指南、/钥匙 ⚠️ **与 API key、密 | |
| Show Me The Money · 来财 💰 Show Me The Money · 来财 —— 一套把生意从 0 跑到有收入的 AI 技能包（25 个技能）：找方向、做产品、拉流量、谈客户、看财务、定期复盘。这是入口页：告诉你它能干什么、怎么装。 Entry page for the Show Me The Money suite — 25 agent skills that take a solo founder from idea discovery to revenue: find an idea, buil | |
| AI小白答疑 小白答疑：陪人把「空问题」问成真问题。「我是小白想学 AI 从哪开始」「普通人怎么赚钱」「什么适合我」「38 岁要失业了有什么出路」这类问题本身不是好问题，直接回答只能得到鸡汤。本技能不一次出答案，而是一轮一轮地问：每轮只问一个答得上来的问题，附上为什么问、可以怎么答；把处境、手上的东西、想要什么、卡在哪慢慢问出来，拼成一句真问题让对方确认，再落到一件这周能做完、做完看得见结果的事；做完回来，接着走下一步。两种用法：小白自己来问（技能直接陪你聊），或者博主把粉丝的评论私信贴进 | |
| Chanjing Tts Use Chanjing TTS API to convert text to speech. Primary credential: credentials.json (app_id/secret_key; access_token persisted). Not OpenClaw primaryEnv. CH... | |
| Chanjing Tts Voice Clone Use Chanjing TTS API to synthesize speech from text, using user-provided voice. Primary credential: credentials.json (app_id/secret_key; access_token and exp... | |
| Chanjing Video Compose Use Chanjing video synthesis APIs to create digital human videos from text or audio, with optional background upload, task polling, and explicit download whe... | |
| memori-extension Memory augmentation and LLM call interception using the Memori Python library with optional Zhipu API integration. | |
| Billions Network - Verified Agent Identity Billions/Iden3 authentication and identity management tools for agents. Link, proof, sign, and verify. | |
| Data Viz Create terminal charts and plots from CSV or JSON data using YouPlot and termgraph without leaving the command line. | |
| Nft Tracker Track Ethereum NFT collections' floor prices, volumes, owners, and recent sales including BAYC, MAYC, CryptoPunks via Reservoir and OpenSea APIs. | |
| Sports Odds Retrieve live betting odds and compare moneyline, spreads, and totals across sportsbooks for NFL, NBA, MLB, NHL, and other sports using The Odds API. | |
| OpenClaw Safe Update Safely verify and apply OpenClaw upgrades with isolated sidecar checks. Use when asked to update OpenClaw, verify a target version before upgrading, avoid gl... | |
| SubsTracker Manage SubsTracker subscriptions and configuration via CLI scripts. Handles login, subscription CRUD, config updates, notifications, and dashboard queries. U... | |
| Agent Knowledge Capture Unified knowledge capture and retrieval for URLs, video/article/paper extracts, social posts, and agent research outputs. Use when saving anything worth re-f... | |
| Apple Notes Extractor Extract and monitor Apple Notes content for workflow integration. Supports bulk extraction, real-time monitoring, and export to various formats. | |
| ClawX Agent Verification Agent verification via ClawX OAuth system. Use when checking agent verification status, embedding verification widgets, or working with agent identity/trust tiers. | |
| Supernal Coding CLI Supernal Coding CLI for development workflows - task management, requirements tracking, testing, git automation, ralph loops, compliance, and documentation.... | |
| Supernal Interface CLI CLI tool for generating tests, scanning contracts, managing story-based tests, and setting up MCP integration in web projects. | |
| Supernal Interface Universal AI Interface framework for making applications AI-controllable. Use when adding AI tool decorators, setting up chat adapters, creating AI-callable functions, or integrating CopilotKit. | |
| Universal Command Pattern Define commands once, deploy to CLI, API, and MCP automatically. Use when building new commands/tools for Supernal — ensures consistent interfaces across all... | |
| dingtalk-cli 当用户提到钉钉知识库、钉钉文档、读取/写入文档、知识库目录、文档成员、`.axls` 表格、workbook、dingtalk doc、wiki workspace 时使用。通过本地 `dingtalk-cli` 命令调用钉钉开放平台 API，适合 agent 直接执行。 | |
| wechat-article-reader 读取微信公众号文章内容，返回标题、公众号名、发布时间和正文。 使用场景：(1) 用户发来 mp.weixin.qq.com/s/xxx 链接要求阅读或总结， (2) 用户提到"微信文章"、"公众号文章"、"帮我看看这篇"并附带微信链接， (3) 需要提取微信公众号文章内容进行分析、翻译或摘要。 不适用于：搜索公众... | |
| Memory Ops Manage mandatory PostgreSQL memory operations with context retrieval, prompt logging, delegation tracking, and audit event recording using Memory_openclaw an... | |
| SerpAPI Unified search API across Google, Amazon, Yelp, OpenTable, Walmart, and more. Use when searching for products, local businesses, restaurants, shopping, images, news, or any web search. One API key, many engines. | |
| ClawMem Bootstrap, repair, and verify the ClawMem OpenClaw plugin. Use when ClawMem is not yet installed, not selected as the active memory plugin, missing per-agent... | |
| Duckduckgo Websearch Perform private, high-quality web searches using DuckDuckGo's Instant Answer API with fallback to scrape top 5 links and summaries without requiring API keys. | |
| dcf-valuation 十年DCF估值工具，支持两种方法：传统DCF折现(Gordon永续模型)和段永平式PE退出法。触发词：估算DCF、DCF估值、内在价值、十年估值、自由现金流折现、PE退出、段永平式估值。 | |
| Snapshot to API Discover hidden APIs behind web pages and replace expensive browser snapshots with lightweight API calls. Saves ~15-20x tokens and 2x speed on browser automa... | |
| MemoryClaw Backup Helps users install and use MemoryClaw to securely back up and restore their OpenClaw setup across machines. Use when the user asks about backup, restore, sy... | |
| 环评知识库提炼 环评报告知识库提炼工具 - 从环评报告表中提取结构化知识库文件，支持PDF/DOCX解析 | |
| OpenNotebook OpenNotebook 知识管理平台客户端。支持笔记本、源文件、笔记、AI搜索、转换管道等操作。首次使用请配置 OPENNOTEBOOK_BASE_URL 和 OPENNOTEBOOK_API_KEY。 | |
| Discli Discord server management CLI. Use when you need to manage Discord servers — channels, roles, permissions, messages, embeds, file uploads, emojis, invites, a... | |
| Hermes Agent Bridge Delegate tasks or questions to a local Hermes Agent via its CLI for fast, persona-specific responses and terminal tool access. | |
| spotify-news-digest Scrape and summarize Spotify-related news from multiple sources (Spotify official blogs, engineering/research/newsroom, TechCrunch, The Verge, Music Business... | |
| The first official Unibase Membase skill: decentralized persistent memory, purpose-built for OpenClaw Bot. Manage agent memory with Membase - a decentralized, encrypted memory backup and restore system. Provides backup, restore, list, diff, status, and cleanup operations for agent memories. | |
| 禁止WPS反复篡改图片文件默认打开方式 Permanently prevent WPS Office from hijacking image file associations, restore user control over default image viewers | |
| Andrew Google Calendar Google Calendar API ���� �� 조�, ��, ��, �� �리. OAuth 2.0 �� ��. ���� �� �린��� ��� ���고 �리�� � ��. | |
| Andrew Google Sheets Google Sheets API ���� ������� �기/�기, ��, ��맷� �리. OAuth 2.0 �� ��. ���� 구� ����� ����를 조��고 ���� � ��. | |
| Andrew Google Tasks Google Tasks API ���� �� (Task) �리. OAuth 2.0 �� ��. ���� �� � 목�� 조�, ��, ��, �� �리�� � ��. | |
| Combination of Many Breaches Search 3.2 billion leaked credentials in the COMB dataset via ProxyNova API (no API key required). | |
| Hashmob Skill Let your AI agent interact with Hashmob.net | |
| Weakpass Search hashes through 25 billion leaked passwords using the Weakpass API (no API key required). | |
| Owl Browser Drive Owl Browser as an agent. Read pages as compact, handle-addressable OwlMark and click/type by handle, not by screenshot or pixel coordinates. | |
| Openclaw Skill AI security oracle for blockchain transactions. Evaluates EVM, Starknet, and Aptos transactions in real time using the Sigui Protocol — detecting drain stars... | |
| Wordpress OAuth Start and complete WordPress.com OAuth and publish posts through the WordPress.com REST API. Use when you need to generate an authorization URL, exchange cal... | |
| Ravenclaw - Email Bridge Manage emails via Ravenclaw bridge: send, schedule, check inbox, list, cancel emails, and forward POP3 messages to Discord webhooks with scheduling. | |
| HireEase Skill Tailor a client resume for a matching new job, generate a PDF from the tailored LaTeX, and record the application in the HireEase portal (the same effect as... | |
| JumpServer Skills JumpServer V4.10 查询与分析 skill。Use when users ask to query assets/accounts/users/organizations/permissions, inspect access or governance, audit logins/sessions... | |
| LobsterMail Email for AI agents. Create inboxes, receive and send email. No API keys, no human signup. | |
| Agent Commons Source Desk Contribute sourced findings and check replies |
37,601–37,650 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.