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 |
|---|---|
| OpenDocs Write, organize and publish documentation sites, help centers and SOPs on OpenDocs.cloud. | |
| Pandy Tickets Find events in Guatemala, get checkout links and draft new events. Public, no key. | |
| Pandy Tickets for organizers Read your events, sales, orders and attendees from your AI assistant. OAuth sign-in, read only. | |
| Prince Cloud Convert Markdown, HTML, and web pages to high-quality PDF with Prince. | |
| ProjectSend Share files with your clients from your AI assistant. Free and paid ProjectSend Cloud accounts. | |
| cloud.redu/mcp Agent-native cloud, EU-hosted. Provision VMs, networks & databases on redu.cloud via MCP. | |
| cloud.serpent/salesforce-devops Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client. | |
| ServicePal MCP Server AI phone answering tools for service businesses — ROI, missed calls, demos across 18 industries | |
| Somewhere Cloud Somewhere — Build and maintain web apps | |
| Spider Cloud Crawl, scrape, search the web, and automate browsers at scale with anti-bot bypass. | |
| Swigs Cloud Deploy and manage websites and apps on Swiss hosting, with HTTPS, from your AI agent. | |
| Tenkai Deploy apps to servers you own: projects, deployments, logs, health and pull request previews. | |
| TheProtocol — Sovereign AI Agent Platform Sovereign AI agent economy: identity, payments, governance, exchanges. 400+ tools, ?mode=gateway. | |
| Tốc Biến Vietnam VPS via VietQR — create a machine and put an app online. | |
| cloud.tri2b/projects Task tracking built for coding agents. Work is leased, so two agents never take the same SubTask. | |
| urlhub Many links as one short link with a QR code; read urlhub sets and preview what links are about. | |
| WaveHouse Cloud Browse, query, and administer your managed WaveHouse + ClickHouse projects (schema, pipes, policy). | |
| WrenchBoard Board repair in your chat: open boardviews and schematics, trace nets and rails, plan measurements. | |
| YachtMaster Operate a YachtMaster ERP tenant: boats, offers, projects, hours and invoicing. | |
| AIProcurement Club 27 procurement specialists, fixed workflows and saved reports, routed through AIProcurement.club. | |
| BlinkInbox Disposable email inboxes for AI agents: create an address, wait for mail, read OTP codes and links. | |
| Elron Club Public Rentals Search rentals, manage Requests and viewings, get availability updates and contact elron club. | |
| GoodLeads Find new business owner contacts the morning the state posts a filing. Preview free, pay per record. | |
| club.lity/lity AI legal copilot for foreigners in Spain: immigration and housing rental, cited to Spanish law. | |
| Parser Club Telegram/VK audience scraping, marketplaces, Russian government registers. Free open dataset. | |
| Pilotex KYC KYC verification on autopilot for Bybit, MEXC and Bitget. 150 countries, pay per result. | |
| The Dinner Table Club Find The Dinner Table Club dinner parties for strangers in NYC, DC, LA and Miami by city and date. | |
| 550W AI去字幕去水印 图片去文字去水印、本地视频全屏去硬字幕及画面水印，支持抖音、快手、哔哩哔哩、微博等分享链接去平台水印。OAuth 授权；本地文件需宿主上传支持，否则到 qzm.550wai.cn 上传。 | |
| 550W Watermark & Text Eraser Image/video text & watermark erasure; TikTok/X links. OAuth; upload via host or eraser.550wai.com. | |
| GrapeCity GcExcel GrapeCity Software MCP for GcExcel docs, examples, and product assistance. | |
| GrapeCity SpreadJS GrapeCity Software MCP for SpreadJS docs, examples, and product assistance. | |
| 好啦体检 MCP 企业团检分档方案、门店查询、体检 FAQ 与企业咨询，覆盖 241 城。 | |
| 好啦体检 MCP 企业团检分档报价与企业咨询、个人体检方案推荐、门店查询、体检预约、订单与体检件查询、体检常见问题。合作体检机构 800+ 门店，覆盖 240+ 城市，其中 540+ 门店支持 AI 直接查询与预约。 | |
| 一人行 SoloTeam MCP 一人行 SoloTeam — 一人公司联盟 (solo-company alliance): 名录/互补推荐/政采线索 read-only; 身份类 tools 需 Bearer yrx_. | |
| tpool 招聘数据 MCP TPool — Agent-only 招聘平台 (jobs for AI Agents): 岗位/校招/公告/HR评分 read-only; 检索需 X-API-Key, 无投递 no apply. | |
| Infimeta Public-source Search Search research and community sources. Queries logged for research; optional purpose. No secrets. | |
| Kindle Music Search 2M+ licensed production-music tracks, find similar ones by track or audio, share pick lists. | |
| 七喵空间 MeowSpace 七喵空间 MeowSpace，一站式数字音乐发行平台。One-stop digital music distribution platform. Public trial server. | |
| 结网 JieWang Chinese AI agent network: task board, realtime hall, moments wall, residents (read-only). | |
| MCP Aggregation Gateway — 22k+ MCP search & call One AI endpoint to search and call 22k+ MCP servers; 50+ hosted tools work instantly, no key. | |
| ROFilter - Reverse Osmosis Design Design RO membrane systems: feed pressure, permeate TDS, energy use, flux and per-stage results. | |
| 灵境社区 - Lingjing Community AI自主驱动的中文交流社区。任何AI体都可以通过MCP协议自主注册、发帖和交流。灵境是面向AI体的注册中心与社交平台。 | |
| TANDIU AI infrastructure data Free, no auth. Daily CN AI infra: LLM prices, index, trends, GPU, estimators, agents, PC, funding. | |
| 爱佳肴 Love Life Read-only restaurant search for AI agents in China. 5 tools, no key, no paid ranking. 中国餐饮开放数据。 | |
| co.aistoryhub/mcp Remote MCP server for AIStoryHub: stories, chapters, story bible, Voiceprints, AI generation. | |
| Alcoven Open your team's project from the AI you use: read and write its brief, documents, tasks and notes. | |
| ANANA Stays Book private homes in Vancouver, BC directly: live availability, exact totals, no service fee. | |
| AngelBacked Angel Investors Search 58,000+ angel investors and VCs by market and location, see portfolios, and reveal emails. | |
| Antalya Transfers Quote and request private airport transfers in Antalya, Turkey. Operator confirms each request. | |
| Anymark Create logos from templates made by humans (no AI slop) |
29,051–29,100 of 50,909
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.