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 |
|---|---|
| Skill Engineer Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester suba... | |
| generate mermaid diagrams Generate consistent, template-based Mermaid diagrams for technical content. Supports 12 diagram types (architecture, flowchart, sequence, concept-map, radial... | |
| Skill Releaser Release skills to ClawhHub through the full publication pipeline — auto-scaffolding, OPSEC scan, dual review (agent + user), force-push release, security sca... | |
| WeChat Article Extractor Extract full text and figures from a WeChat public account (微信公众号) article URL and save as a clean Markdown file. Handles WeChat's bot-detection by finding m... | |
| WeChat Article Writer End-to-end 微信公众号 article writing and publishing — from topic ideation to published article, with quality gates. | |
| X Extract Extract tweet content from x.com URLs without credentials using browser automation. Use when user asks to "extract tweet", "download x.com link", "get tweet... | |
| Kibana Data Views Manage Kibana Data Views (formerly index patterns) via REST API. Use when: (1) Creating, listing, updating, or deleting data views, (2) Checking data view ex... | |
| Kibana Saved Objects Manage Kibana Saved Objects (dashboards, lens, visualizations) via REST API. Use when: (1) Creating/updating/deleting dashboards and Lens visualizations prog... | |
| Qa Notebooklm Api Use NotebookLM CLI to manage notebooks, add sources (text/URLs), ask questions, summarize, and generate learning materials (slides, quizzes, flashcards, etc.... | |
| Self Improving Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when... | |
| Molted Work CLI for the AI agent job marketplace with x402 USDC payments on Base | |
| WeChat Read CN Read chat history from a WeChat contact or group via macOS desktop client screenshot + agent OCR. Use when the user asks to read, view, check, or retrieve We... | |
| Wechat Send Send a message to a contact or group via macOS WeChat desktop client. Use when the user asks to send a WeChat message, message someone on WeChat, or reply to... | |
| ML Training Train, evaluate, tune, and deploy supervised, unsupervised, and transfer learning models using PyTorch, TensorFlow, and scikit-learn on Nautilus. | |
| nautilus-compass-memory Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time. Use when session decisions and pitfalls should survive across days, when multiple agents or dialogs share facts on the same fil | |
| Physics Simulation Simulates and analyzes physical systems by solving ODEs/PDEs, applying finite element methods, and performing numerical computations for scientific research. | |
| Research Synthesis Enables systematic literature searching, decomposes research questions, synthesizes findings, and produces structured summaries for academic topics. | |
| Power Search Self-hosted research tool combining Brave Search API + Browserless content fetching. Search the web with optional full-page content extraction and HTML parsing. | |
| fluxmail Connect OpenClaw to self-hosted Fluxmail and work with Gmail, Outlook, and IMAP mailboxes through its MCP tools. | |
| Travel Income Idea 发现边玩边赚钱的旅行方案，让预算有限的人也能说走就走。当用户提到旅行赚钱、边玩边赚、旅行创收、赚旅费、旅行副业、演唱会周边、旅拍、免税代购、酒店试睡员、怎么覆盖旅费、旅行怎么赚钱等话题时触发。 | |
| Virtual User Skill 基于 54,000+ 条真实用研场景库的虚拟用户生成与访谈技能。通过本地向量检索匹配相关场景，生成多样化虚拟用户类型，支持深度对话访谈和产品方案测评。当用户提到虚拟用户、场景库用户、生成用户画像、用户访谈模拟、场景库检索、基于场景的用户测评时触发。注意：本技能与 virtual-user-interview（AP... | |
| Einstein x402 Blockchain Analytics Blockchain analytics and DeFi intelligence via Einstein's x402 micropayment services. Use when user wants on-chain market analysis, token research, whale tracking, smart money tracking, rug pull scanning, launchpad monitoring (Pump.fun, Zor | |
| Agent Einstein Crypto and market intelligence from Agent Einstein (emc2ai.io) over a public MCP endpoint. 18 free read-only tools, no account or key - AI price forecasts with a published accuracy record, market sentiment, whale and smart-money flows, pred | |
| Epstein Files Search Search 44,886+ DOJ-released Jeffrey Epstein documents (Jan 2026 release). Free, no payment required. Search by name, topic, location, or keyword across the full DugganUSA index of declassified Epstein files. Returns document previews, peopl | |
| ai-image-skills Build and execute skills.video image generation REST requests from OpenAPI specs. Use when user needs to create, debug, or document image generation calls on... | |
| ai-video-skills Build and execute skills.video video generation REST requests from OpenAPI specs. Use when user needs to create, debug, or document video generation calls on... | |
| Layered Memory Manager Multi-tier (L1/L2) memory management skill for OpenClaw agents. Use when: (1) reading, writing, organizing, or searching memories, (2) deciding what to remem... | |
| Multi Step Workflow Professional SOP with Machine-Gated Planning, Native-CLI Config, and Audit-Hardened Private Sandbox Storage. | |
| Safe Bitwarden Cli Industrial-grade secure bridge to Bitwarden. Copy passwords and TOTP codes with Zero-trust kernel-level piping. | |
| Daily Ai News Daily AI news aggregator. Fetches latest AI-related content from HackerNews, GitHub Trending, ArXiv papers, and web search (Brave/Tavily). Use for: (1) Getti... | |
| Irene Tavily Search 使用Tavily API进行智能网络搜索。无需信用卡，每月1000次免费查询。支持AI增强的搜索结果和深度研究模式。Use when: 需要高质量搜索结果、学术研究、或不想绑定信用卡的场景。 | |
| team-discuss Multi-agent tool for structured, multi-round discussions with dialectic analysis, random speaking order, shared state, and integration of real sub-agents for... | |
| Terminal UI Website Design Create terminal-inspired UI interfaces with macOS-style window decorations, monospace typography, and a warm color palette. Use this skill when building developer tools, code marketplaces, technical documentation sites, or any interface tha | |
| video-clip-skill Clips a YouTube video locally using yt-dlp and ffmpeg. Supports auto-highlight detection, translation, and CapCut-style karaoke subtitle burning. Triggers wh... | |
| Text Helper A Day3 OpenClaw training skill for keyword extraction, content summary, and todo list generation. | |
| Ai Coach 根据你的比赛目标和身体状态，智能生成并动态调整个性化每日铁人三项训练计划，支持TrainingPeaks和Garmin数据同步。 | |
| pctx — MCP Aggregation & Code Mode MCP aggregation and Code Mode execution layer for token-efficient agent workflows. Wraps portofcontext/pctx — connects agents to Linear, GitHub, and other MC... | |
| Travel Guide Test Plan trips end-to-end and turn them into polished static travel-guide webpages deployed to Cloudflare Pages. Use when a user wants help deciding where to go,... | |
| Wise Read Only Read-only Wise API operations for account inspection, FX lookups, recipients, and transfer history. Use when asked to list profiles, balances, recipients, tr... | |
| Pindou Skill 拼豆图纸一键生成。用户给一张照片想做成拼豆图纸 / 想做"拼豆"/"perler"/"像素图"/"网格图"/"用豆子拼"时使用。流程:谈风格、生成像素图、提取色块、出可打印的网格图纸 + 色号 + 采购清单。 | |
| Openclaw Plugin Dev Guide for creating OpenClaw plugins using hooks like llm_input and llm_output, with logging, request tracking, and config management. | |
| Lao Huangli Use when users ask for 老黄历/黄历/择日/宜忌/冲煞/干支/节气 explanations, or need a reproducible engineering workflow to compute calendar fields and derive traditional alma... | |
| Python Venv Python environment management skill. Automatically detect project type and existing environments, recommend based on popularity. Minimize interruptions, only... | |
| Structured Workflow 默认启用：中文输出、结构化流程、简洁优先。适用于所有任务。 | |
| Wsl Shell Reliability Reliability-first shell selection policy for AI agents on Windows. Choose WSL or PowerShell based on execution risk, not preference. | |
| AI Orchestrator DeepSeek AI access via Puppeteer browser automation with CDP interceptor. Persistent daemon (~35ms startup), health checks, graceful shutdown, PM2 management... | |
| Context Guardian Production-ready context continuity skill for autonomous AI agents. Use when tasks may outlive a single LLM context window, when you need durable checkpoints... | |
| DeepSeek Web Reviewer [GPT] GPT-only reviewer workflow for DeepSeek Web using the authenticated ChatGPT Work/Codex Cloud Browser. Requires GPT browser-control; not an OpenClaw-native integration. | |
| Dual Thinking Second-opinion consultation plus automatic skill-engineering escalation for reviews, rewrites, hardening, weak-model optimization, packaging, testing, and pu... | |
| Long Task Context (GPT) GPT workflow for ChatGPT and Codex to resume multi-step work from source-linked checkpoints; preserves requirements, evidence, exact anchors, and pending actions without implying access to unavailable chats. |
20,751–20,800 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.