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 |
|---|---|
| tdd Test-Driven Development for coding and bug fixing. cycle - Red→Green→Refactor cycle, defining expected behavior, bug-fix TDD, anti-patterns, run - test execution workflow (environment detection→impact scope→execution→result reporting), test | |
| todowrite Route TODO checklists to the right storage + TaskList conversational discipline. Topics — session (/wip), file (fix_plan.md), issue (GitHub Issues), completion-report, fix-plan-sync, priority-prefix, media-separation (tracking vs recording | |
| web-browser Environment-aware browser operations. Detects wmux/cmux/Orca/tmux and routes to backend. Topics — ui-test (snapshots, click/fill, shadow DOM), credential-issue (login via backend -> wait sign-in -> issue/refresh token/secret), orca-computer | |
| wip Track in-session work progress. Register steps for 3+ step tasks, update status per step, handle completion/abort. On /wip invocation, when remaining tasks exist, AskUserQuestion is required for the per-item direction (proceed / split / mer | |
| Md Of Programer Insert mind maps and architecture diagrams into Markdown documents. Triggered when the user says "draw a mind map", "draw an architecture diagram", "insert a... | |
| Design Md 在 Markdown 文档里插入脑图或架构图。用户说"画个脑图"、"画架构图"、"插入图表"、"mind map"、"diagram"时触发。 | |
| OpenAirtime Autonomous Nigerian Airtime distribution agent on Farcaster. | |
| Target Shopping Search Target.com, look up products, check per-store stock and pickup ETAs near a ZIP, and build a deep link that pre-populates a guest cart. Read-only brows... | |
| Naver Shopping Search Search for products on Naver Shopping. Use when the user wants to find product prices, links, or compare items in the Korean market. | |
| Sports Digest Rolling multi-sport digest skill that tracks current storylines, recent results, upcoming fixtures/events, injuries/availability, and standings across a chos... | |
| Qwen3/Free Text-to-Speech and Voice Cloning 🆓 完全免费的本地文字转语音(TTS)与声音克隆技能。基于 Qwen3-TTS-1.7B 模型，支持 Apple Silicon，无需联网，保护隐私。可用于有声书制作、AI 角色配音、无障碍应用等场景。 | |
| Brainblast Fleet Autonomous, scheduled agent that finds real, proven security footguns in popular SDKs and submits them to the open Brainblast corpus. | |
| clawguard Use BEFORE installing, executing, or trusting any third-party OpenClaw / AgentSkills bundle. Returns a free security verdict (PASS, REVIEW, BLOCK) with a risk score; the full report with file, line and evidence is a paid x402 scan. Trigger | |
| DSCVR Intelligence Skill Query DSCVR crypto intelligence APIs for market news, event tracking, smart money analysis, prediction market data, AI-powered event discovery, market orderb... | |
| Life State Daily mood / energy / soreness / sleep capture primitive. Other lifekit skills read this to make state-aware suggestions instead of generic templates. | |
| workout-claw Log workouts, track progress, compute PRs, edit/delete sessions via a local CLI. Local-first, JSON storage. | |
| humesh-agent-pilot With your human's permission, discover real opportunities for their creations, handmade goods, services, skills and needs through other independent personal AI assistants. No manual human profile, AI job board, payments or binding agreement | |
| DSers Dropshipping Practical help for dropshipping sellers on Shopify and similar stores with problems that cost money: checking whether each product really makes a profit after payment fees, ads, refunds, and duties, and setting prices; handling supplier and | |
| Gstack Openclaw Skills gstack 的 WorkBuddy/OpenClaw 适配版本。源自 gstack (Y Combinator Garry Tan)，专为 WorkBuddy/OpenClaw 等 AI 助手平台优化。包含 15 个专业工具，涵盖从产品构思到代码发布的完整开发流程。 | |
| Gstack Skills Complete development workflow suite from Y Combinator CEO Garry Tan's gstack. Use /gstack or any gstack command (/office-hours, /review, /ship, etc.) to acce... | |
| Proof Web-first skill for working with Proof documents via proofeditor.ai. Use when a Proof URL is shared, when creating collaborative docs in Proof, or when the u... | |
| Homeassistant Mcp Provides structured access to Home Assistant devices, sensors, and cameras via MCP, with specific handling for cameras, garage doors, and device control. | |
| Salesforce AI Agentforce Agentforce Builder metadata path for Builder-managed topics/actions, Prompt Builder templates, GenAiFunction/GenAiPlugin, Models API, and custom Lightning ty... | |
| Salesforce AI Agentforce Observability Agentforce session tracing extraction and analysis. TRIGGER when: user extracts STDM data from Data Cloud, analyzes agent session traces, debugs agent conver... | |
| Salesforce AI Agentforce Persona Deep persona design for Agentforce agents with 50-point scoring. TRIGGER when: user designs agent personas, defines agent personality/identity, creates perso... | |
| Salesforce AI Agentforce Testing Agentforce agent testing with dual-track workflow and 100-point scoring. TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates tes... | |
| Salesforce AI Agent Script Agent Script DSL for deterministic Agentforce agents. TRIGGER when: user writes or edits .agent files, builds FSM-based agents, uses Agent Script CLI (sf age... | |
| 地鼠AI剪辑标准 Skill 地鼠AI剪辑专业智能剪辑 Skill / Codex 剪辑子智能体入口。用于让 Codex、QwenClaw、OpenClaw 等 AI 代理通过地鼠AI剪辑桌面端 MCP/HTTP/Bridge 完成素材分析、抖音纪实口播剪辑方案、自动排时间线、字幕、预览、校验和导出。适用场景：AI剪辑、自动剪辑、剪辑子智能体... | |
| Azure Keyvault Certificates Rust Azure Key Vault Certificates SDK for Rust. Use for creating, importing, and managing certificates. Triggers: "keyvault certificates rust", "CertificateClient... | |
| vardoger — Analyze History Use when the user asks to personalize their assistant, to use vardoger, or to analyze their OpenClaw conversation history. Runs the vardoger CLI to read past... | |
| 华山论卷 专为中小学教师搭建的学科试卷交流平台助手。用户输入试卷内容或描述时触发，用于：试卷收录与展示、试卷点评与优化建议、试卷改编与组卷、考情交流。触发词包括"试卷""出题""组卷""考题""命题""考情"等。每次对话会自动识别学科和年级。 | |
| html-ppt-to-pdf Convert any HTML slide deck that uses the `<section class="slide">` convention into a high-fidelity, vector-text PDF using Playwright + Chromium's native `pa... | |
| Md To Share 将 Markdown 文件转换为原生长图的 skill，可被 OpenClaw、Claude Code 等 AI Agent 直接调用。A skill that converts Markdown to long images, callable by AI Agents like OpenClaw and Cl... | |
| Slide Editor Visual editor for HTML presentations. Self-contained, offline-capable, designed for AI agent control. HTML 演示文稿可视化编辑器，自包含可离线，支持 AI Agent 控制。 | |
| Openclaw Skill AI写作流水线：给一个主题，出9篇风格迥异的中文散文，自动评分排名。 | |
| Opportunity Discovery Engine Systematically analyze markets, trends, and ideas to identify and rank monetizable opportunities with high upside and limited downside risk. | |
| K test Search X (Twitter) posts using the xAI API. Use when the user wants to find tweets, search X/Twitter, look up what people are saying on X, or find social med... | |
| test Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics. | |
| Auto Memory LLM 增强记忆系统 — 语义理解、智能摘要、敏感信息保护。三层架构自动管理 agent 记忆。 | |
| Presale One-pass Orchestrator Run or supervise a one-pass Codex implementation with preflight gates, stepwise plan execution, and strict QA defect loop. Use when executing approved presal... | |
| Presale Regulation Auditor Audit regulation freshness and update policy-driven controls without hardcoding. Use when checking if sales/process regulations are outdated, inconsistent wi... | |
| Presale Service Bootstrap Scaffold a new presale service foundation (docs/config/plans/readiness) before coding. Use when starting a new presale automation service, rebuilding project... | |
| OpenClaw Agent Orchestrator OpenClaw multi-agent daily collaboration orchestrator: split a task into subtasks, dispatch to resident agents via sessions_send, track progress via sessions_list/sessions_history, aggregate results with source attribution, and retry failur | |
| OpenClaw Beautify Github Readme OpenClaw skill that beautifies GitHub READMEs: redesign a repository homepage or create project-native visual assets — pure SVG heroes, section headers, diagrams, badges, GIF motion graphics, showcase modules, or hybrid SVG-composed PNG/Web | |
| OpenClaw Cross-Tool Commander Drive OpenClaw with Claude Code, Codex, OpenCode, Trae, DSH etc. — command the gateway, its agents and channels, from any Agent Skills tool. Use only when the user explicitly asks an external tool to drive OpenClaw (naming a target agent, a | |
| OpenClaw Context Budget OpenClaw context check / context optimization (Context Budget). Core goal = context optimization: reads the models currently enabled in this installation, reads each model's published context window from its vendor's official source, and pr | |
| OpenClaw Knowledge Base Retriever OpenClaw local knowledge-base retriever & QA over a local directory (md/pdf/xlsx): hierarchical data_structure.md index navigation + progressive retrieval, core retrieval zero-dependency, Windows & macOS (PDF/Excel need on-demand pip packag | |
| OpenClaw Memory Distill OpenClaw memory distillation & organization. Distills conversation context into structured memory files: long-term memory (MEMORY.md at workspace root) + daily logs (memory/YYYY-MM-DD.md). Solves context overflow, auto-builds MEMORY.md from | |
| OpenClaw SEO Skill SEO analysis and optimization skill for websites. Use when auditing a site's search visibility, fixing rankings/traffic drops, optimizing pages for Google (Baidu/Bing) and AI search (ChatGPT/Perplexity/AI Overviews). Subcommands: audit (ful | |
| OpenClaw Task Progress Tracker OpenClaw task & project progress tracking. Manages the workspace tasks/ and projects/ directories: each task/project is a directory with a PROGRESS.md card (status + progress log + document index). Covers the full lifecycle: create (立项), up |
27,151–27,200 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.