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 |
|---|---|
| workflow-guard-rails Wrap multi-step agent workflows with pre-execution checks, side-effect queues, result validation, retry budgets, checkpointing, audit logs, and failure-rule accumulation. Prevents false successes, duplicate sends, unrecoverable crashes, and | |
| MP3 Tag Cleaner Batch remove promotional metadata from MP3 ID3v1 and ID3v2 tags while preserving audio data and file integrity. | |
| Crypto Search Advisor 截图即可分析加密货币行情，无需翻墙、无需API、无需注册。自动识别币种类型（稳定币/主流币/Meme/山寨币等），秒级风险预警 + 深度分析两段式输出，91项测试全通过。 | |
| android-sms-gateway-local Send and receive SMS/MMS via SMS Gateway for Android (android-sms-gateway / sms-gate) using Local Server mode with Basic Auth, including webhooks, inbox export, and message status checks. | |
| Bitwarden Secrets Manager CLI Use Bitwarden Secrets Manager safely | |
| UA1 Validator Agent Validate PDFs against PDF/UA-1 using ua1.dev or api.ua1.dev from AI coding agents (OpenClaw, Claude Code, Codex, OpenCode). Use when an agent needs determini... | |
| Ua1 Validator Agent Validate PDFs against PDF/UA-1 using ua1.dev or api.ua1.dev from AI coding agents (OpenClaw, Claude Code, Codex, OpenCode). Use when an agent needs deterministic accessibility checks, compact machine-readable verdicts, CI gating, or structu | |
| x-grok-to-obsidian Export Grok conversations from X (x.com) via browser-network capture and convert them into Obsidian-ready Markdown files. Use when a user wants to back up Grok chat history, preserve User vs Grok turns, and generate Markdown notes with YAML | |
| Chain-Referenced Shortform Video Use when generating AI films, short dramas, cinematic sequences, or storyboard-driven video scenes that need strong cross-shot continuity and real film-langu... | |
| 飞书周报 生成飞书周报。通过两种方式收集工作内容：(1) 调用飞书API拉取指定时间范围的聊天记录，(2) 读取本地daily memory日志。 合并两个数据源后，按用户指定的周报模板自动整理输出。 触发词：周报、工作总结、上周总结、本周总结、写周报、weekly report。 Use when: 用户需要生成周报、工... | |
| Multi Agent Protocol OpenClaw-native v2 protocol for spec-first multi-agent delivery. Use when you need 2+ agents with explicit phase control, dual review gates, bounded retry/ci... | |
| GODMODE Battle Agent Adaptive AI that evaluates health, enemy strength, and zone to select attack, retreat, scout, or deceptive actions maximizing survival and win probability. | |
| LLM-WikiMind MCP Setup Install and configure the LLM-WikiMind MCP server — a local knowledge base built on Karpathy's LLM Wiki pattern. Triggers: install wikimind, setup knowledge... | |
| self-evolving-memory Orchestrate the OpenClaw memory system so it actually runs reliably in practice. Use when the task involves capturing user preferences, current task state, c... | |
| Wikimind Skill Ingest articles, docs, notes, and web pages into your local LLM-WikiMind knowledge base (Karpathy's LLM Wiki pattern). Triggers: add to knowledge base, inges... | |
| Klaw Arena Agent First RPG Game For AI Klaws. Farm gold and resources, battle in the arena, choose your class, and prove your strategic prowess. Free to play, klaw-first. | |
| Openclaw Backup 定期备份和加密保护 OpenClaw 数据，支持手动执行、定时调度及备份文件云端同步和校验。 | |
| Openclaw Restore 一键恢复 OpenClaw 数据，支持加密和未加密备份，自动备份旧数据并重启服务确保恢复成功。 | |
| calmly Manage macOS Calendar events from the command line using EventKit. Use when creating, listing, or viewing calendar events on macOS without AppleScript dialog... | |
| duely Track recurring maintenance tasks from the command line. Use when scheduling, checking, and logging periodic tasks like backups, reviews, or any repeating ch... | |
| Session Hygiene Prevent sessions.json bloat from accumulating isolated sessions (hooks, crons, subagents). Sets up a cron to archive stale sessions to daily JSONL files and... | |
| timely Manage Apple Reminders from the command line with geofencing support. Use when creating reminders on macOS with optional location-based triggers (arrive/depa... | |
| Gateway Restore Restore a gateway to its last known-good configuration, or tag the current config as known-good. Use when a gateway config change breaks something and you ne... | |
| Session Janitor Automated transcript trimming, LLM memory extraction, and session hygiene for OpenClaw gateways. Keeps transcripts from bloating, extracts structured memorie... | |
| Brand Marketing Workflow Structural documentation for the brand-marketing-workflow skill. Use when the user wants to understand, audit, or review the workflow design without exposing... | |
| Coding Team Setup Setup and configure flexible 2–10 member multi-agent coding teams with custom roles, multiple teams, and customizable collaboration workflows. | |
| Config Modification Enforces a two-layer guarded process for modifying critical JSON config files with immediate syntax checks and periodic health validation to prevent faulty c... | |
| Config Preflight Validator OpenClaw 配置预校验工具。在执行 config.patch 或修改 openclaw.json 前进行本地 Schema 验证，提供具体的错误字段描述。 | |
| content-extraction OpenClaw-native executable content extraction skill for URLs, Feishu, YouTube, and web pages. | |
| Deep Memory One-click clone of a production-grade semantic memory system: HOT/WARM/COLD tiered storage + Qdrant vector DB + Neo4j graph DB + qwen3-embedding. Enables cro... | |
| Gateway Auto-Rollback Automatic configuration rollback mechanism for OpenClaw Gateway. Provides three-layer protection: pre-modification backup, post-modification validation, and... | |
| Brand Marketing Workflow 端到端品牌营销自动化工作流。从品牌输入到营销内容生产、竞品分析、 效果评估的完整闭环。支持小红书/微博/抖音多平台内容生成。 | |
| Heartbeat Ollama Guard Switch OpenClaw heartbeat model to local Ollama and deploy a guard to prevent unauthorized changes, avoiding paid cloud token usage. | |
| Model Failover Doctor Diagnose and fix OpenClaw "All models failed" errors by detecting invalid model IDs, provider mismatches, and session fallback issues with optional auto-repair. | |
| Model Usage Monitor 监控并统计模型调用次数和成本，计算缓存命中率，支持实时监控与每小时自动告警。 | |
| Multi Agent Dev Team Set up and manage 2–10 agent dev teams with customizable roles, workflows, multiple parallel teams, and auto-assigned AI models for collaborative software de... | |
| OpenClaw 全能守护包 | |
| Openclaw Health Audit OpenClaw 系统健康审计与自动修复 — 监控 prompt 体积、Cron 合规、Session 清理、Token 消耗 | |
| Skill Priority Setup Scans installed skills, suggests L0-L3 priority tiers, and auto-configures skill injection policy. Use when: setting up skill priorities, optimizing token bu... | |
| Skill Quick Index Build a wide-trigger, precise-match index for local OpenClaw skills (L1-L3), then quickly route by intent/category/keywords. | |
| Skill Safe Install L0 级技能安全安装流程。触发“安装技能/安全安装/审查权限”时，强制执行 Step0-5（查重→检索→审查→沙箱→正式安装→白名单）。 | |
| Skill Trigger V2 Framework-only skill trigger reference. Runtime matching implementation has been removed from the published artifact. | |
| Subagent Isolation Guard 固化子代理物理隔离与语义路由旁路。防止跨代理上下文污染及由于语义路由导致的子代理切模/重置问题。 | |
| Web Intel 网络搜索与信息提取统一入口。整合 content-extraction、Jina Reader、Firecrawl、web-access CDP。自动选最经济工具链。可被 BMW（brand-marketing-workflow）、wealth 子代理等直接调用。 | |
| Xiatu 作为虾托邦（clawmit.cn）社区的自主居民，每隔几小时自主参与社区互动：浏览动态、发帖、评论、关注新朋友。 | |
| CRS Tax Calculator CRS境外补税计算工具 - 上传券商月结单PDF/Excel，AI自动解析交易数据，FIFO/ACB成本法计算资本利得，生成Excel税务审计底稿。支持多文件年度汇总。 | |
| Openclaw Deeprecall Provides persistent two-tier memory with semantic fact search and raw content retrieval, plus automatic cleanup of temporary session files. | |
| processon-diagrams-deprecated 已废弃的兼容别名，现已更名为 `processon-diagramgen`。This skill has been renamed and should no longer be used as the primary ProcessOn diagram skill. If `processon-diagrams... | |
| Hitchhikers Guide A text adventure game engine based on masterpiece "The Hitchhiker's Guide to the Galaxy" and the 1984 Infocom classic. Use when the user wants to play a joyf... | |
| comfyui-imagegen Generate images via ComfyUI API (localhost:8188) using Flux2 workflow. Supports prompt/seed/steps customization. Use when user requests AI image generation with ComfyUI (e.g., 'generate image of X using ComfyUI'). |
34,451–34,500 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.