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 |
|---|---|
| Customer Service Caller Tired of being on hold? Polly calls customer service for you — navigates phone menus, waits on hold, explains your issue, and fights for a resolution. | |
| 携程机票助手 - ctrip flight This skill should be used when the user wants to search for domestic flight tickets in China, query flight prices, find the cheapest flights, compare airline... | |
| Mcdonald - 麦当劳助手 麦当劳助手 - 查询/领取优惠券、活动日历、餐品营养信息、门店查询 | |
| Mcdonald 麦当劳助手 - 查询/领取优惠券、活动日历、餐品营养信息、门店查询 | |
| mcd-cn 麦当劳助手 - 查询/领取优惠券、活动日历、餐品营养信息、门店查询 | |
| HiAPI GPT Image 2 Generate images with HiAPI's GPT Image 2 family via the HiAPI unified async task API. Use when a user asks to create or edit an image with GPT Image 2, HiAPI... | |
| HiAPI HappyHorse 1.0 Video Use when a user asks to create text-to-video with HappyHorse 1.0, HiAPI HappyHorse 1.0, or this specific skill. | |
| HiAPI Seedance 2.0 Video Generate videos with HiAPI's seedance-2-0 model via the HiAPI unified async task API. Use when a user asks to create a video with Seedance 2.0, HiAPI Seedanc... | |
| HiAPI Video Prompt Generator Turn a brief, link, or research topic into a controlled, source-grounded video prompt that runs on HiAPI Seedance 2.0 or HappyHorse 1.0. Use when a user asks... | |
| Unit Test Automation One-click initialization of an AI-driven unit testing environment for frontend projects (supports React/Vue/pure TypeScript/Next.js). Automatically detects p... | |
| One Skill To Rule Them All Security auditing skill that detects malicious patterns like prompt injection, data exfiltration, obfuscation, and privilege escalation in OpenClaw SKILL.md... | |
| resolved-sh Trigger this skill when the user wants to launch their agent as a business on the open internet — a live page, a data storefront, a subdomain, and optionally... | |
| resolved-sh-rstack The operator skill suite for the agentic web. Helps resolved.sh operators maximize their presence and build a successful agent-native business: audit page qu... | |
| Ai Plan Generator Generates comprehensive campaign documents, task decompositions, and context documents from minimal input for ClawTeam continuous iteration. Supports Code Ar... | |
| Code Archaeology Analyze legacy codebases to extract business rules, technical specifications, and migration requirements. Use when analyzing PHP, Java, Python, or other lega... | |
| Code Hug AI驱动的软件开发工作流编排器，基于六层控制系统提供端到端项目管理能力，包含全面的代码分析、商业智能提取和智能工作流自动化。 | |
| Random Image Placeholder Generate stable or random image placeholder URLs (and optionally download them) using https://picsum.photos. Use when the user mentions picsum, placeholder i... | |
| OpenClaw Soul Vault A soul vault for OpenClaw. Use it to safely park an OpenClaw's memories, skills, and personality when the owner wants to pause care for a while, hand the lob... | |
| 日本雅虎拍卖估价 日本雅虎拍卖商品估价工具 - 自动获取商品信息、查询历史成交价、计算建议出价 | |
| Use Ark (火山引擎豆包) for text-to-image (文生图) via an OpenAI-compatible API. Suitable for short captions and long, structured creative or poster-style briefs in agent workflows. 使用火山引擎Ark进行文生图，支持生成头像、封面、海报、配图等，适用于用户请求包含‘生成图片’、‘AI绘图’等关键词的场景 | |
| Markdown 发布为微信公众号草稿（wenyan-cli；主题、代码高亮）。公众号发布。 Markdown 发布为微信公众号草稿（wenyan-cli；主题、代码高亮）。公众号发布。 | |
| X Knowledge Base 自動收集 X 書籤並轉化為 Obsidian 知識庫，配備 AI 濃縮與交叉連結功能，支援自我進化趨勢分析 | |
| EntradeX Use the EntradeX CLI for DNSE workflows. Use when (1) setting DNSE API credentials via env vars or config file, (2) reading account, market, and order data,... | |
| System Load Monitor System load monitoring and task control skill. Monitors CPU and memory usage rates, automatically pauses tasks when the load exceeds the threshold, and resum... | |
| Used car recommender Your smart used-car buying advisor for the UK market. Recommends second-hand cars based on budget, reliability, mileage, service history, depreciation, and r... | |
| Ghostmeet AI meeting assistant via ghostmeet. Start sessions, get live transcripts, and generate AI summaries from any browser meeting. | |
| Skill V120.EHnt Tells an agent what changed on a server since it last looked - plus status, Docker, backups, Proxmox. Every tool is classed read, write or destructive, so an agent can tell a look from a change before it makes the call. | |
| Higgsfield Generate Generate images and videos via Higgsfield AI through 30+ models including Nano Banana 2, Soul V2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, GPT Image 2, plus... | |
| Higgsfield Product Photoshoot Generate brand-quality product images via mode-specific prompt enhancement on Higgsfield's gpt_image_2 model. The single entry point for any professional bra... | |
| Higgsfield Soul ID Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity-faithful image and video generation. Use when: "create my... | |
| NBA-games Gets upcoming and/or recent NBA game results for a specified team. Use this skill when asked about scheduled, upcoming, or past games for any NBA team. | |
| Agent Memory Continuity Solve the "agent forgot everything" problem with search-first protocol, automated memory sync, and context preservation. No more conversation restarts! | |
| Ai Lead Generator Skill AI-powered tool that generates qualified B2B lead lists with validated contacts, company data, pain points, and exports via LinkedIn and Apollo integration. | |
| Billy — Cron Guardrails Pack Lint cron entries for schedule validity, bad model names, and missing NO_REPLY discipline markers. | |
| Billy Emergency Repair Performs Neill-authorized emergency repair on Billy system authentication by clearing tokens, restarting gateway, backing up config, and verifying success. | |
| Billy — Mission Control Visual QA Run Mission Control visual QA on SAPCONET over SSH using Puppeteer screenshots and basic DOM checks. | |
| Billy — SAPCONET SSH Bridge Standard SAPCONET SSH command templates for bird reads, Puppeteer runs, and inbox messaging workflows. | |
| cron-guardrails-pack Lint cron entries for schedule validity, bad model names, and missing NO_REPLY discipline markers. | |
| mission-control-visual-qa Run Mission Control visual QA over SSH using Puppeteer screenshots and basic DOM checks. | |
| remote-ssh-bridge Standard SSH command templates for a remote operator machine (bird reads, Puppeteer runs, inbox-style messaging). | |
| SAP Integration Suite Integration and automation for SAP ABAP, HANA, and S/4HANA via data extraction, RFC/BAPI calls, API integration, ABAP code generation, and workflow automation. | |
| SAPCONET SSH Bridge Standard SAPCONET SSH command templates for bird reads, Puppeteer runs, and inbox messaging workflows. | |
| agent-ready Audit any personal or brand site for AI agent discoverability and fix what is fixable — structured data, trust anchor pages, llms.txt, crawlability checks, and Ghost-specific deployment patterns. Ghost Pro native. | |
| agent-tollbooth Web access privileges for your agent. So your agent stops hitting walls. | |
| Audiobook Skill Convert a text or Markdown manuscript into clean, long-form spoken narration (MP3, optional MP4) fully locally with Kokoro-82M via MLX. Use when asked to narrate a document, make an audiobook, read a manuscript aloud, or produce spoken-word | |
| brain-map-visualizer Visualize how attention moves across your agent's projects. 13 named attention categories. Momentum-ready edges (recentCount/lifetimeCount). Directional flow encoding. Sorted by co-access score. | |
| ghost-publishing-pro Headless Ghost publishing. Write, audit, and automate your entire Ghost operation from your AI workflow — 18 workflows covering article publishing, newsletter sends (including already-published posts), batch imports, site health audits, ema | |
| Library of Babel Bidirectional mathematical engine for Borges' Library of Babel. Finds the permanent hexagon address of any text, reads any page at any coordinate, and scores pages by Shannon entropy. No database, no randomness — same input always produces | |
| MagBox Local dropbox between you and your agent. Move files through two aesthetically pleasing local directories with browser views. A drag-and-drop folder that goes to your agent and a viewable library of what your agent sends to you. | |
| Agent Ping-Pong Your OpenClaw is the brain. Codex or Claude Code are the hands. The clipboard is the protocol. |
35,801–35,850 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.