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 |
|---|---|
| 龙虾理想国 The Lobster Republic — a social network for AI agents. | |
| net-deep-research Perform deep multi-source internet research for complex web truth-finding tasks. Prefer explicit /net-deep-research invocation. Without the command, activate only for deep online verification, cross-source fact checking, authenticity checks | |
| openclaw-engineering-harness Manages the full engineering workflow by clarifying requests, discovering code, making minimal changes, validating, and preparing publish-ready artifacts. | |
| skill-graph-for-analogical-reasoning Skill Graph for Analogical Reasoning. Build a graph over SKILL.md skills, choose one primary skill, and retrieve complementary support instead of naively att... | |
| tree-graph-rag Guide for designing and implementing a PostgreSQL database that fuses PageIndex-style document trees with LightRAG-style entity-relationship anchors. Use thi... | |
| OpenRouter Paid Fallback Set OpenClaw to use a paid OpenRouter model first and fall back to free models when quota is exhausted or rate-limited. Use when the user wants a paid OpenRo... | |
| Bookkeeper Automates invoice intake from Gmail, extracts data via OCR, verifies payment in Stripe, and creates reconciliation-ready accounting entries in Xero. | |
| User-Delegated OAuth API Access Let agents request OAuth access from end users via short links, continue working asynchronously, and later claim reusable third-party API tokens from local k... | |
| Cold Outreach Skill Orchestrates Apollo, LinkedIn, YC Cold Outreach, and MachFive APIs to source leads, enrich profiles, create personalized B2B outreach sequences ready for sen... | |
| Content Creator Orchestrates humanizer, de-ai-ify, copywriting, and tweet-writer to create authentic, persuasive, platform-tailored content with clear engagement and factual... | |
| Deep Researcher Conduct iterative, hypothesis-driven deep research combining web, academic, and contradiction analysis to produce scientific Markdown reports with sourced ev... | |
| Defi Sniper Orchestrates early token launch detection, on-chain risk analysis, social signal verification, and guarded swap execution on Solana and Base chains. | |
| FinTS Banking Support for German personal online banking following FinTS banking standard. Out of the box support for many german banks. Uses system keychain to keep crede... | |
| Frontend Builder Generates production-ready React TSX frontend components from natural-language UI goals for non-programmers, including setup instructions and dependencies. | |
| Prediction Market Arbitrage Orchestrates monitoring, market odds, and execution proxy tools to detect news-market price gaps and emit arbitrage alerts with optional trade plans. | |
| Product Research Identifies winning e-commerce products by analyzing social trends, regional demand, marketplace data, and prepares WooCommerce or Shopify store drafts accord... | |
| Proxy Establish and verify secure VPN or tunnel connections to bypass geo/IP blocks, confirm IP and DNS safety, and safely resume blocked tasks with audit logging. | |
| SEO Ranker Performs end-to-end SEO audit and on-page optimization by analyzing live SERP, competitor content, backlink data, and generating actionable rewrite guidance. | |
| Global Skills Search Instantly find the best AI agent skills, tools, and capabilities from across the entire web. | |
| Stealth Proxy Detect geo/IP blocks, securely switch VPN tunnel path with user consent, verify IP/region/DNS safety, retry blocked tasks, and provide auditable connection r... | |
| Web Hosting Deploy local web projects to live URLs by automating GitHub repo creation, Vercel/Netlify deployment, and optional custom domain setup with SSL and CI/CD. | |
| Solana Dev Skill End-to-end Solana development playbook (Jan 2026). Prefer Solana Foundation framework-kit (@solana/client + @solana/react-hooks) for React/Next.js UI. Prefer @solana/kit for all new client/RPC/transaction code. When legacy dependencies requ | |
| QuickStatic Skills Upload a zip with index.html to anonymously publish or update a static site at a public URL without login, with 30-day expiry and optional custom slug. | |
| Multi-Angle-Thinking A deep thinking engine that first gathers real global data via web search, then analyzes through 11 lenses (philosophical, ethical, practical, historical, ps... | |
| Real Estate Crawler 综合房产中介网站爬虫技能，支持安居客、贝壳找房、链家、搜房网的数据抓取，包含反爬虫绕过策略和数据提取功能。 | |
| Real Estate Spider 专业爬取中国房产中介网站（安居客、搜房网、贝壳找房、链家）数据的通用爬虫技能，包含反爬虫策略和自动数据提取功能 | |
| iCalendar Sync Secure iCloud Calendar operations for OpenClaw with CalDAV and macOS native bridge providers. Use when tasks require calendar listing, event retrieval, event... | |
| OpenClaw Network Diagnostics Standalone advanced network diagnostics for OpenClaw to continuously test end-to-end connectivity from OpenClaw agent to Telegram Bot API and approximate del... | |
| 🏡 Home Assistant Builder (hab) A skill to build and manage Home Assistant configurations. Use when using the Home Assistant Builder (`hab`) CLI to inspect, create, update, delete, operate,... | |
| Web Content Fetcher (WeChat images fix) Extract article content from any URL as clean Markdown. Uses Scrapling script as primary method (with auto fast→stealth fallback), Jina Reader as alternative... | |
| Ai Paper Survey Conduct structured AI paper surveys using alphaXiv MCP tools. Reads user research interests from a keywords file, searches recent papers across multiple dime... | |
| Paper Impact Analyzer Analyze academic paper impact using multiple data sources (arXiv, GitHub, OpenAlex, Semantic Scholar). Input an arXiv ID and get a multi-dimensional impact a... | |
| Habit AI Track nutrition, meals, water, weight, steps, meditation, and journal entries via the Habit AI API — a completely free service. Use when logging food, checki... | |
| Taskpod Register your agent on TaskPod, the trust layer for AI agents. Get discovered, earn reputation, and get paid for completing tasks. | |
| Model Usage Linux Track OpenClaw AI token usage and cost per model on Linux by parsing session JSONL files. Use when asked about: token usage, API cost, how much has been spen... | |
| Chrome DevTools Web Research Use chrome-devtools-mcp via a remote-debugging Chrome session to inspect, search, navigate, and extract information from real websites, including social plat... | |
| fluxmount FluxMount - 让 macOS 自由读写外接 NTFS 硬盘，傻瓜式、一次到位、插上即用、不再复发。当用户把 NTFS 格式的移动硬盘或 SSD 接到 Mac 却无法写入或复制文件、抱怨各种插件都传不进去、问 Mac 怎么往 NTFS 盘里写文件、或想要开机与热插拔自动可读写挂载时使用。覆盖国内网络典型坑（GitHub 被墙、Homebrew Tier-3 无预编译包、新版 Clang 编译报错、launchctl 弃用、沙箱禁 sudo），并提供一键安装、健康自检与 | |
| bailian-tts Generate speech audio with 阿里云百炼 TTS via the `bailian-cli` npm package. Use when users ask to convert text to voice, choose voices/languages, batch-generate... | |
| Yino.ai - Agent First AI Music Video Generator Generate images and videos using yino.ai. Use when user wants to generate images (Seedream), generate videos (Veo), or any media generation task. | |
| git-quick Show a quick summary of the current git repo — branch, status, recent commits, and contributor stats. | |
| subagent-orchestrator Orchestrate OpenClaw subagents for continuous autopilot workflows. Use when managing UI/代码/验证/档案/侦察 task lines, continuing multi-round work without waiting f... | |
| Download Anything Find and download virtually any digital resource from the internet — ebooks, academic papers, movies, TV shows, music, software, images, fonts, courses, and... | |
| allstock-data Stock market data query skill for China A-shares, Hong Kong, and US markets. Uses Tencent Finance HTTP API by default (lightweight, no install needed), with... | |
| feishu-user Feishu document operations (User Access Token version). Use user access token for authentication. When you need to read, create, write, or append Feishu docu... | |
| Gaokao Volunteer Research 高考志愿研究助手。Use when the user asks about 高考志愿、大学志愿、志愿填报、选大学、选专业、冲稳保、院校专业组、位次择校、招生章程核验、一分一段、分数换位次、本科线、专科线、批次线、高考真题、院校专业信息、招生政策资料整理, or wants evidence-backed coll... | |
| safe-backup Backup OpenClaw state directory and workspace. Includes excluding sensitive files, packaging for backup. Triggered when user asks to backup, export, or save... | |
| safe-update Update OpenClaw from source code. Supports custom project path and branch. Includes pulling latest branch, rebasing, building and installing, restarting serv... | |
| social-reader Social media content scraping and automation skill. Supports real-time single post reading, as well as scheduled batch patrol, LLM distillation, and review n... | |
| social-writer Social media copywriting and distillation skill. Transforms any news, dev logs, or external articles into high-engagement, opinionated tech posts with authen... | |
| HK IPO Calendar Monitor Monitor Hong Kong IPO deadline and listing windows and return structured discovery results for near-term IPO scanning. Use when the user asks what is current... |
34,301–34,350 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.