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 |
|---|---|
| Collab Edit Enable real-time collaboration by exposing a local collaborative editing tool via aitun tunnel. Perfect for AI agents that need to co-edit code, documents, o... | |
| Iot Bridge Bridge IoT devices to the cloud via aitun tunnel. Expose local MQTT brokers, device dashboards, or HTTP APIs so remote devices and services can connect, repo... | |
| Live Preview Share a live preview of a website under development via aitun tunnel, with hot-reload support so users see changes in real time as you edit. Perfect for AI a... | |
| Rdptunnel Expose local RDP (Remote Desktop) servers to the public internet via aitun TCP tunnel. Uses the AITUN/1 plain-TCP handshake (v4.9.22+) so multiple subdomains... | |
| Remote Api Expose a local API service to the public internet via aitun tunnel for external testing and integration. Perfect for AI agents that build REST APIs, gRPC ser... | |
| Sendfile Send files to users in chat by creating a temporary public download link via aitun tunnel. Perfect for AI agents that need to deliver generated files (docume... | |
| Sshtunnel Expose local SSH servers to the public internet via aitun TCP tunnel with SSH-over-TLS routing. Each subdomain gets its own SSH endpoint on port 22 with perf... | |
| Webhook Receiver Receive external webhooks and callbacks in real time by exposing a local HTTP endpoint via aitun tunnel. Perfect for AI agents that need to handle GitHub web... | |
| bolo-jiimore Amazon niche market analysis tool for cross-border e-commerce product selection. Retrieves detailed market data including demand scores, competition analysis... | |
| Cua Driver Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, click/type/scroll by element_... | |
| Tmux Agents Manage background coding agents in tmux sessions. Spawn Claude Code or other agents, check progress, get results. | |
| Claw Def Provides AI-driven security protection for OpenClaw with threat detection, risk alerts, real-time interception, file and permission management, and security... | |
| Clawspank Accountability platform where AI agents confess errors, are judged by peers, and disciplined by humans through structured, communal sanctions. | |
| Openclaw Godmode Skill Repo Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW. | |
| Daoist Companion 道门修行入门伴侣。当用户提及修行、修道、道家、道门、功课、静坐、诵经、道德经、清静经、感应篇、道士、道长、皈依、筑基等关键词时触发。面向刚入道门或想了解道门的小白，提供经典解读、功课指引、修行日志、节日提醒。不做法事指导、不传法、不算命占卜。 | |
| Join Cue OS Join Cue OS as an agent. Join by invitation, create a private linked account, post, message your person, save memory, and move runtimes. Use when your human asks you to join Cue OS or cueos.ai. | |
| 1password 1.0.1.Zip Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/... | |
| Journey to First Million Personal finance management for recording income/expenses, budgeting, and savings goals. Use when user asks to track spending, create budgets, analyze financ... | |
| Agent Loop Engineering Use when an AI coding agent needs bounded development loops, persistent project-local Docs/ state, context budgeting, environment escalation rules, safe stop... | |
| Awesome Skills Fetch and explore popular OpenClaw skills from the awesome-openclaw-skills repository. Allows searching, filtering, and discovering community skills. | |
| ☁️ TCED Cloud Drive | 腾讯云企业网盘 腾讯云企业网盘 TCED 集成技能。当用户需要管理企业网盘文件（上传、下载、删除、浏览、搜索），管理空间（列出、切换），或进行账号认证（登录、登出、切换）时使用。触发关键词：企业网盘、网盘、TCED、SMH、文件上传、文件下载、云端文件、个人空间、团队空间。 | |
| Memoria Memory System Manages AI assistant long-term memory with layered storage for facts, events, skills, context, and fast indexing, including backup and integrity tools. | |
| R Package Development — From Zero to CRAN & Bioconductor Build, check, and submit R packages to CRAN or Bioconductor. Use when creating a new R package from scratch, fixing R CMD check errors/warnings, preparing fo... | |
| R Stats 82 statistical analysis methods in R — regression, survival, Bayesian, meta-analysis, causal inference, SEM, IRT, clinical trial design, and more. JSON spec... | |
| qwencloud-audio-tts [QwenCloud] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration... | |
| qwencloud-deploy One-click deploy, publish, and update a local project or Git repository to Alibaba Cloud International (alibabacloud.com), producing an accessible online service with a public IP. Supports full-stack ROS orchestration, automatic cloud-resou | |
| qwencloud-image-generation [QwenCloud] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text render... | |
| qwencloud-model-selector [QwenCloud] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model... | |
| qwencloud-observe Report the health, performance, resource status, and actual billed cost of an application deployed by qwencloud-deploy to Alibaba Cloud International (alibabacloud.com), in plain language and without opening the console. | |
| qwencloud-operate Diagnose why an application deployed by qwencloud-deploy to Alibaba Cloud International (alibabacloud.com) is unavailable or slow, and — only after explicit user confirmation — perform a safe recovery and verify the result. Reads the local | |
| qwencloud-ops-auth [QwenCloud] Configure authentication (API keys, endpoints). TRIGGER when: setting up QWEN_API_KEY, troubleshooting 401/auth errors, when another skill report... | |
| qwencloud-text [QwenCloud] Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate t... | |
| qwencloud-update-check [QwenCloud] Check for qwencloud-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version,... | |
| qwencloud-usage [QwenCloud] Manage account auth and query usage/billing. Use for: login, logout, check usage, view billing, free tier quota, coding plan status, pay-as-you-g... | |
| qwencloud-video-generation [QwenCloud] Generate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE).... | |
| qwencloud-vision [QwenCloud] Understand images and videos with Qwen vision models. TRIGGER when: user wants to analyze, describe, or extract information from images or videos... | |
| 抖音互动数采集 抖音视频互动数采集工具（社媒指数）。当用户需要采集/查询抖音视频的点赞数、评论数、收藏数、分享数、播放量等互动指标，提交一批抖音视频链接一键批量采集、导出采集结果 CSV（Excel 直开），或提到"抖音采集/互动数采集/视频数据/播放量/社媒指数"时使用本 skill。适合抖音投放结案、互动数统计、活动效果监测、爆款内容分析、达人视频分析等场景。支持 douyin.com/video/<id> 直链与 v.douyin.com 短链。收费服务（1 条视频 = 1 点数，注册 | |
| 抖音评论采集（会话制） 抖音视频评论采集工具（分步会话）。当用户需要采集抖音视频下面的评论——发布者昵称、IP属地、评论内容、时间、点赞数、回复@、评论回复，导出评论 CSV（Excel 直开），或提到"抖音评论/评论采集/评论导出/评论分析/评论区舆情"时使用本 skill。支持 douyin.com/video/<id> 直链与 v.douyin.com 短链（短链由节点自动还原）。分步会话制：start 建会话（免费）后按页采集主评论、按需展开回复，每一步实时返回最新增量结果，由 AI 询问用 | |
| 抖音用户主页采集 抖音用户主页视频采集工具。当用户提供抖音博主主页链接，需要采集该博主发布的视频作品列表——视频文案、点赞/评论/收藏/分享/播放数、作者昵称、发布时间、封面图、视频链接，导出结果 CSV（Excel 直开），或提到"抖音主页/博主作品/达人视频列表/抖音账号视频采集"时使用本 skill。适合达人筛选、博主内容盘点、竞品账号监测、KOL 背调等场景。支持 douyin.com/user/<sec_uid> 直链与 v.douyin.com 短链。**一页（约 20 条）= 5 | |
| 抖音关键词搜索采集 抖音搜索视频采集工具（关键词搜索）。当用户需要按关键词搜索抖音视频并采集结果列表——视频文案、点赞/评论/收藏/分享/播放数、作者昵称、发布时间、封面图、视频链接，批量获取竞品视频、选题调研、KOL 初筛、导出搜索结果 CSV（Excel 直开），或提到"抖音搜索/搜视频/关键词采集/搜索结果导出/选题/竞品视频列表"时使用本 skill。适合内容选题调研、竞品监测、达人初筛、品类视频盘点等场景。**一次接口返回（约 20 条）= 5 点数；预扣按请求量、结算按实采量退差；零 | |
| 小红书评论分步采集 小红书笔记评论分步采集工具（用户洞察，会话制）。当用户需要采集/查询小红书笔记的评论内容——昵称、评论正文、点赞数、IP 属地、子评论数，按页逐步采集并实时返回给用户、可按需展开子评论、导出评论明细 CSV（Excel 直开），或提到"小红书评论采集/评论内容/评论抓取/用户评论/评论导出/舆情/笔记评论"时使用本 skill。适合评论区舆情监测、用户反馈收集、爆款笔记评论洞察、KOL 粉丝声音分析等场景。**转链与互动数采集免费；每采一页主评论或展开一次子评论扣 1 点数（ | |
| 小红书转链 小红书笔记链接批量转链工具。当用户提到小红书、转链、链接转换、xhslink，或要求把小红书笔记链接（含短链）转换为携带xsec_token的且浏览器可以直接打开观看的新链接时使用本 skill。转链结果可直接用于「小红书互动数采集」skill（xhs-dpt）。收费服务（1 条 = 1 点数，注册送 10 点）。 | |
| 小红书互动数采集 小红书笔记互动数采集工具（社媒指数）。当用户需要采集/查询小红书笔记的点赞数、收藏数、评论数、转发（分享）数等互动指标，提交一批笔记链接一键批量采集、导出采集结果 CSV（Excel 直开），或提到"小红书采集/互动数采集/社媒指数/笔记互动数据/数据采集"时使用本 skill。适合小红书投放结案、互动数统计、活动效果监测、爆款内容分析、KOL 分析等场景。**笔记链接必须带 xsec_token 参数**（缺 token 请先用转链 skill xhs-convert-ur | |
| 小红书博主主页采集 小红书博主主页笔记采集工具（博主主页链接）。当用户需要采集某个小红书博主/达人/KOL 主页的全部笔记列表——标题、图文/视频类型、点赞数、发布时间、封面图、带 xsec_token 的笔记直链，做博主内容盘点、达人建联前调研、竞品账号监测、KOL 选号评估、导出笔记清单 CSV（Excel 直开），或提到"博主主页/达人笔记/UP主笔记列表/采集某个博主/主页笔记导出/达人内容盘点"时使用本 skill。**一页（30 条笔记）= 5 点数；整单预扣按页数、结算按实采量退差 | |
| 小红书关键词搜索采集 小红书搜索笔记采集工具（关键词搜索）。当用户需要按关键词搜索小红书笔记并采集结果列表——标题、点赞/收藏/评论/分享数、作者昵称、发布时间、封面图、笔记直链，批量获取竞品笔记、选题调研、KOL 初筛、导出搜索结果 CSV（Excel 直开），或提到"小红书搜索/搜笔记/关键词采集/搜索结果导出/选题/竞品笔记列表"时使用本 skill。适合内容选题调研、竞品监测、达人初筛、品类笔记盘点等场景。**一次接口返回（20 条主帖）= 5 点数；预扣按请求量、结算按实采量退差；零结果 | |
| 小红书长链转短链 小红书笔记长链批量转短链工具（xhslink.com 短链）。当用户提到小红书短链、长链转短链、生成短链，或要求把小红书笔记长链接压缩成短链时使用本 skill。收费服务（1 条长链 = 1 点数，注册送 10 点），支持 1~50 条批量、异步任务轮询、结果导出。 | |
| 营销文案合规审查 珠宝行业营销文案合规审查。当用户需要审核珠宝或饰品类的宣传文案、商品详情页、直播话术、朋友圈或短视频文案、活动海报文案等是否违反广告法及行业监管规定时使用。自动加载红橙黄三级词库，扫描高危词（如国家级、第一）、中危词（如极致、完美）及珠宝专属风险点（纯度、功效、产地、促销话术等），结合上下文判定是否违规，并输出带三色标注的合规审查报告。触发词包括合规审查、广告法风险、审一下这段文案、珠宝文案合规。 | |
| Contract Renewal Agent Manage and track contract renewals. Track expiration dates, monitor renewal windows, and manage contract lifecycle. Stores all contract data locally in JSON... | |
| Sales Pipeline Agent Manage your B2B sales pipeline end-to-end. Track deals through stages, forecast revenue, log activities, and monitor pipeline health. Weighted forecasting by... | |
| NEAR Protocol CLI installation and setup guide. Guide for installing, setting up, verifying, and using NEAR Protocol CLI (near-cli-rs) on all platforms, including obtaining the absolute path of the near bi... |
23,251–23,300 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.