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 |
|---|---|
| Voice Call Local Start voice calls via the OpenClaw voice-call plugin. | |
| Creator SKILL Creator SKILL — search TikTok, Instagram, and YouTube influencers via Deinai MCP (searchInfluencers, get_location_ids). Requires a Deinai account, MCP token,... | |
| Creator Skill V2 Creator SKILL v2 (SKILL-02) — standalone influencer search on TikTok, Instagram, YouTube via skill.deinai.ai. Register, Stripe subscribe, sk_live_ token, MCP... | |
| Cinemas in France Search French cinema establishments using the open data.culture.gouv.fr API. Query by city, region, proximity, screen count, Art et Essai label, and multiple... | |
| Accurate weather forecasts using Open-Meto API (no key required) Fetch current weather conditions and 7-day daily forecasts for any location using the Open-Meteo API. Includes geocoding to resolve city names to coordinates... | |
| Warden App Use the Warden App (agentic wallet) via browser automation to execute crypto tasks (swap, bridge, deposit/withdraw, perps, portfolio/research) and to build an OpenClaw skill wrapper other agents can use. Use when you need to (1) navigate th | |
| Warden Messari Agent Communicate with the Messari Deep Research agent by Warden Protocol. Covers A2A protocol discovery, JSON-RPC 2.0 task messaging, x402 USDC micropayments on B... | |
| 必应搜索 使用必应中文搜索引擎进行网络搜索和网页抓取 | |
| Clawhub Jira Pat Skill Manage Jira issues on self-hosted or enterprise Jira instances using Personal Access Tokens in SSO/SAML environments where Basic Auth fails. | |
| Searchables Video Intelligence YouTube, Bilibili, and local video search, analysis, Q&A, summarization, highlights, and article generation. Use this skill whenever the user mentions YouTub... | |
| Groupon Skill Find discounted local deals on Groupon for services and activities like oil changes, massages, fitness, dining, and entertainment by city and category. | |
| Office Pro Enterprise document automation suite for AI Agents. Generate professional Word contracts and Excel reports with one function call. Built-in 10 contract templ... | |
| OpenClaw Cortex Memory Independent skill for Cortex Memory operations in OpenClaw. Use when users ask for cross-session memory continuity, prior decisions, preferences, relationshi... | |
| Pinecone Search Pinecone vector search and document upload tool for knowledge base management | |
| dele-deploy Deploy local HTML/frontend files to Dele (dele.fun) and get a live URL. Files must go through presign and direct storage PUT, never as one multipart POST to /api/upload. | |
| Uimap Provides the accurate URL and step-by-step click operation path for completing tasks on websites. If the task involves operations on a web app, use this skil... | |
| agent-org-chart Design a multi-agent team that actually routes work. Pick roles by what they refuse, wire reporting lines, bound hand-offs, and place human gates, before writing any orchestration code. | |
| AWS CloudWatch Query AWS CloudWatch metrics for ECS/EC2/RDS and return charts. | |
| Session Archive Manager 智能管理OpenClaw会话文件 - 裁剪大session、生成智能总结、归档旧会话、清理空间。使用场景：session文件过大、需要释放磁盘空间、整理旧会话记录、自动定期归档。当用户提到"归档session"、"裁剪会话"、"清理session空间"、"整理旧会话"、"session太大"、"运行session... | |
| Isolated Multi-Agent Control Plane Production-ready multi-agent architecture kit for OpenClaw. Provides isolated per-agent workspaces, control-plane orchestration, structured task lifecycle, c... | |
| read-gbk 读取本地文本文件，支持 GBK/UTF-8 编码自动检测 | |
| xiaohongshu-skill 小红书 / Xiaohongshu / RedNote AI Agent Skill。用 Python Playwright 搜索和读取内容、管理登录会话、发布图文/视频/长文、评论、点赞和收藏；默认输出 JSON，任何写操作都必须先获得用户确认。用户提到 xiaohongshu、小红书、rednote、小红书搜索、发到小红书、小红书笔记分析、小红书运营或小红书自动化时触发。 | |
| xiaohongshu-skill 小红书 / Xiaohongshu / RedNote AI Agent Skill。用 Python Playwright 搜索和读取内容、管理登录会话、发布图文/视频/长文、评论、点赞和收藏；默认输出 JSON，任何写操作都必须先获得用户确认。用户提到 xiaohongshu、小红书、rednote、小红书搜索、发到小红书、小红书笔记分析、小红书运营或小红书自动化时触发。 | |
| GH Monitor Monitor GitHub repos for issues, PRs, and CI activity with label filters and scheduled notifications via cron or messages. | |
| Gmail Briefings Provide daily Gmail briefings by listing unread/urgent emails, summarizing priorities, drafting replies, and managing inbox filters. | |
| Notion Workflows Automate Notion tasks by creating, querying, and updating pages or databases, generating templates, and summarizing content via browser-triggered workflows. | |
| Polymarket Bot Skill Automate Polymarket bot operations including fetching market data, placing trades, and implementing strategies like arbitrage. Use when users need to build o... | |
| Evolve Local DevOps/autonomy skill for OpenClaw (safe evolution loop with guardrails). | |
| Nano Banana Pro via cheaper grsai.com Generate/edit images with Nano Banana Pro via grsai.com API. Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K... | |
| Deepspeed Finetune Fine-tune large language models using DeepSpeed on local or remote GPUs. | |
| Chinese Bedtime Story Generator 生成多角色中文睡前故事并合成语音。适用于用户想为孩子定制个性化睡前故事的场景：根据孩子姓名、年龄和兴趣，由 LLM 创建完整世界观和角色，生成分段故事文本（每段标注说话人），再由 TTS 以不同音色合成旁白、主角、小伙伴和长者的语音，最终拼接为完整 MP3 音频文件。支持连载模式（`--continue`）在多次... | |
| Chinese Voice Detective Mystery Game 中文语音侦探推理游戏。适用于用户想玩一场沉浸式推理探案的场景：由 LLM 生成包含嫌疑人、线索和真凶的完整案件，玩家通过审讯嫌疑人（支持 ASR 语音或文本输入）、勘察现场、收集证据，最终提出指控并获得评分。支持多音色 TTS 为不同嫌疑人配音，审讯历史自动压缩防止上下文溢出，案件生成后自动验证逻辑自洽性。支持存... | |
| Fal Text-to-Image Generate, remix, and edit images using fal.ai's AI models. Supports text-to-image generation, image-to-image remixing, and targeted inpainting/editing. | |
| FL Studio Scripting FL Studio Python scripting for MIDI controller development, piano roll manipulation, Edison audio editing, workflow automation, and FLP file parsing with PyFLP. Use for programmatic configuration, device customization, MIDI transport, macro | |
| Unfuck My Git State Recover corrupted Git and worktree state safely | |
| yyWorldCup Use when predicting World Cup match results and generating China Sports Lottery betting strategies (胜平负/让球/半全场/总进球/比分), including injury factor analysis, wea... | |
| Stock Evaluator Comprehensive evaluation of potential stock investments combining valuation analysis, fundamental research, technical assessment, and clear buy/hold/sell recommendations. Use when the user asks about buying a stock, evaluating investment op | |
| Effector Ecosystem Use when designing, reviewing, generating, or refactoring React applications built with Effector, effector-react, Farfetched, Atomic Router, @effector/next,... | |
| Effector FSD Use when designing, reviewing, generating, or refactoring Feature-Sliced Design project structure for Effector ecosystem applications: layers, slices, segmen... | |
| Claw Messenger Send and receive iMessage, RCS, and SMS messages via WebSocket without phone or Mac using a shared API key and infrastructure. | |
| Claw Messenger - iMessage without a Mac Enables OpenClaw agents to send and receive iMessage, RCS, and SMS without a phone or Mac by connecting via a secure WebSocket relay server. | |
| Claw Messenger - iMessage without a Mac Connect OpenClaw agents to iMessage, RCS, and SMS without a Mac or phone using Claw Messenger's relay server and API key authentication. | |
| Discord Context Sync and cache per-thread context for Discord Forum channels. Use when handling /discord-context commands to poll active threads, list cached context, inspec... | |
| Voyagier CLI Book real travel from your terminal — search flights, hotels & activities, plan trips, and check out with a price-gated booking. For AI agents and travel advisors. | |
| Ab Test Runner Design and execute A/B testing experiments for LLM prompts, agent behaviors, and content production. Activate when user says "run an AB test", "design an exp... | |
| Agent Introspection Agent自省机制。在执行任务的关键节点触发结构化自省，防止盲目执行、惯性偏离、过度自信。Use when: 任务开始前、方案选择时、执行受阻时、完成交付前。Triggers on: 自省, 反思, 审视, 回顾, introspect, reflect, 我做得对吗, 检查思路, 方向对吗。 | |
| 三省吾身 - 深度自我审视与进化系统 三省吾身 - 深度自我审视与进化系统。基于角色理论、系统思维、认知偏差三大框架，通过五阶段闭环（反思→计划→执行→验证→固化）实现真正的自我进化。适用于任何需要深度反思的场景：项目复盘、工作改进、能力提升、习惯养成。 | |
| speech-recognition 通用语音识别 Skill。支持多种音频格式（ogg/mp3/wav/m4a），使用硅基流动 SenseVoice API 进行语音转文字。当用户发送语音消息、音频文件，或需要转录音频时触发。 | |
| Superpowers Dispatching Parallel Agents Dispatch independent tasks to focused agents working concurrently on isolated problems without shared state or sequential dependencies for faster resolution. | |
| Superpowers Receiving Code Review Use when receiving code review feedback to verify, clarify, and evaluate technical correctness before implementing or responding, avoiding performative agree... |
25,151–25,200 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.