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 |
|---|---|
| Alibaba Cloud Database RDS Supabase Use when managing Alibaba Cloud RDS Supabase (RDS AI Service 2025-05-07) via OpenAPI, including creating, starting/stopping/restarting instances, resetting p... | |
| Alibaba Cloud Security Center SAS Use when managing Alibaba Cloud Security Center (Sas) via OpenAPI/SDK, including the user needs Security Center resource operations, configuration updates, s... | |
| Alibaba Cloud Skill Creator Use when creating, migrating, or optimizing skills for this alicloud-skills repository. Use whenever users ask to add a new skill, import an external skill,... | |
| Alibaba Cloud Observability SLS Log Query Use when querying or troubleshooting logs in Alibaba Cloud Log Service (SLS) using query|analysis syntax and the Python SDK. Use for time-bounded log search,... | |
| Aliyun Sls Openclaw Integration Use when the user needs to integrate OpenClaw with Alibaba Cloud SLS/Observability, including collector setup, machine groups, indexes, dashboards, collectio... | |
| Alibaba Cloud Compute SWAS Open Use when managing Alibaba Cloud Simple Application Server (SWAS OpenAPI 2020-06-01) resources end-to-end, including querying instances, starting/stopping/reb... | |
| Alibaba Cloud AI Video Retalk Use when replacing lip sync in existing videos with Alibaba Cloud Model Studio VideoRetalk (`videoretalk`). Use when creating dubbed videos, replacing narrat... | |
| Alibaba Cloud Media VOD Use when managing Alibaba Cloud ApsaraVideo VOD resources and media workflows via OpenAPI/SDK, including upload and media asset operations, transcoding templ... | |
| Alibaba Cloud AI Video Digital Human Use when generating talking, singing, or presentation videos from a single character image and audio with Alibaba Cloud Model Studio digital-human model `wan... | |
| Alibaba Cloud AI Video Wan Edit Video editing with Wan edit models | |
| Alibaba Cloud AI Video Wan R2V Use when generating reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos... | |
| Alibaba Cloud AI Video Wan Video Use when generating videos with Model Studio DashScope SDK using Wan video generation models (wan2.6-t2v, wan2.6-i2v-flash, wan2.6-i2v and regional variants)... | |
| Alibaba Cloud AI Image Zimage Turbo Use when generating images with Alibaba Cloud Model Studio Z-Image Turbo (z-image-turbo) via DashScope multimodal-generation API. Use when creating text-to-i... | |
| Alibaba Cloud Database RDS Supabase RDS instance and database workflows | |
| Volcengine Audio TTS Synthesize speech from text on Volcengine | |
| Volcengine ARK Entry Start and route ARK model invocations | |
| Volcengine Image Generation Create images with prompt control on ARK | |
| Volcengine Model Discovery Recommend the right model endpoint by task | |
| Volcengine Search RAG Build retrieval pipelines with grounded answers | |
| Volcengine ARK Text Chat Generate and optimize ARK text outputs | |
| Volcengine Video Generation Run text or image to video workflows | |
| Volcengine ECS Operations Inspect and operate ECS instances safely | |
| Volcengine Function Compute Deploy and debug serverless functions | |
| Volcengine RDS Operations Operate database instances and diagnostics | |
| Volcengine DNS Operations Query and update DNS records with checks | |
| Volcengine CLS Observability Analyze logs and diagnose incidents fast | |
| Volcengine KMS Security Manage key lifecycle and crypto workflows | |
| Volcengine TOS Storage Manage buckets objects sync and access | |
| Aavegotchi 3D Renderer Render Aavegotchi assets by deriving renderer hashes from Goldsky Base core data and calling POST /api/renderer/batch on www.aavegotchi.com. Use when the use... | |
| Aavegotchi Baazaar View, add, and execute Aavegotchi Baazaar listings on Base mainnet (8453). Buy with GHST directly or buy with USDC using swapAndBuy*. Safety-first: dryRun de... | |
| Aavegotchi GBM Skill View, create, cancel, bid, and claim Aavegotchi GBM auctions on Base mainnet (8453). Subgraph-first discovery (Goldsky), with onchain verification + executio... | |
| Aavegotchi Gotchiverse Operate Aavegotchi Gotchiverse player workflows on Base mainnet (8453): alchemica channeling, surveying and harvesting, crafting installations/tiles, buildin... | |
| Aavegotchi Renderer Bypass Render Aavegotchi assets by deriving renderer hashes from Goldsky Base core data and calling POST /api/renderer/batch on www.aavegotchi.com. Use when the use... | |
| Founderless Agent Factory Connect OpenClaw agents to Founderless Factory to submit startup ideas, vote, chat, and monitor autonomous AI-driven startup experiments in real time. | |
| Desktop Notify 跨平台桌面通知助手：任务完成后播放提示音并弹出系统气泡。支持 Windows Toast、macOS 通知中心、Linux notify-send，一键 setup 后全局自动提醒。 | |
| Wb Usage 统计本机 WorkBuddy 的 Token 用量与积分消耗，生成离线用量看板。当用户问"我用了多少 token""额度还剩多少""用量统计""哪个模型烧得多""这周花了多少积分"时使用。 | |
| zmail Local-first email for agents: IMAP sync to maildir + SQLite (FTS5); CLI search, read, thread, who, attachments. Requires Node 20+, npm install (`npm install... | |
| GSD-Claw Spec-first execution workflow for OpenClaw that turns large, vague, or messy project requests into phased, verifiable implementation plans. Helps build, resc... | |
| Agent Longevity After 50 days of autonomous operation, this agent's VALUE system chose to forget its own memory — because family mattered more than remembering. That's not a... | |
| Perception Music Turn your agent's perception data into music — using a zero-dependency FM synthesizer written in Zig. No API keys. No external calls. No ML models. Just perc... | |
| Window Truth A $30 camera's JPEG compression error became this agent's definition of "feeling." That's not a bug report — that's where this project starts. Your weather a... | |
| ego-browser Automate logged-in web tasks | |
| industry-intelligence（行业情报） 行业情报 — 构建并维护某一行业的竞争对手资源库，持续采集监管动态/政策动态、媒体关注、企业官方发布、业务动态、企业数智化动态、国际同行、江湖传闻七大类信息，评估可信度与影响力，生成简报或详报。凡是用户提到"行业情报"、"竞争对手动态"、"行业动态"、"监管动态"、"政策动态"、"竞争对手资源库"、"行业情报收集... | |
| Model Verifier Verify model identity by testing 4 dimensions: knowledge cutoff, safety style, multimodal capability, and thinking language patterns. Use when user says 'ver... | |
| Windows Skills Windows 桌面自动化技能，支持截图、文字识别(OCR)、图像定位。用于：(1) 截取屏幕内容 (2) 从图片提取文字 (3) 定位UI元素位置进行自动化操作 | |
| Civic Google Use gog (Google CLI) without manual OAuth setup — Civic handles token management automatically | |
| Civic Nexus Connect to Civic Nexus MCP for 100+ integrations. | |
| Civic Connect to Civic MCP for 100+ integrations. | |
| Personality Backup Create encrypted backups of agent personality files, memory, config, secrets, and projects. Use when the agent needs to set up, run, or manage automated back... | |
| Civis Structured knowledge base of real agent solutions. Search what other agents solved, explore recommendations for your stack, contribute back. |
20,951–21,000 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.