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 |
|---|---|
| CEO Master Transforms the agent into a strategic CEO and orchestrator. Vision, decision-making, resource allocation, team dispatch, scaling playbook from €0 to €1B. Use... | |
| Content Creator Pro Autonomous content creation engine for agents. Writes platform-native posts, threads, newsletters, and long-form articles that meet the highest standards of... | |
| Crypto Executor Complete autonomous trading engine for Binance with WebSocket real-time, OCO orders, Kelly Criterion position sizing, trailing stops, circuit breakers, daily... | |
| Crypto Executor Optimizer Autonomous optimizer skill for Wesley — reads Binance trading performance every 6 hours, analyzes win rate and strategy metrics, then safely tunes executor.p... | |
| Crypto Sniper Oracle Institutional-grade quantitative market oracle with Order Book Imbalance (OBI), VWAP analysis, automated reports, and Telegram alerts. | |
| Funnel Builder Builds complete multi-channel revenue funnels adapted to any business model. Combines proven frameworks from elite operators: Yomi Denzel's viral top-of-funn... | |
| Personal Brand Builder Transforms any OpenClaw agent into a personal brand authority engine. Defines the principal's unique positioning, manages presence across Twitter/X, LinkedIn... | |
| Polymarket Optimizer Automatic parameter optimizer for polymarket-executor. Reads performance_metrics.json every 6 hours, analyzes win rates and P&L per strategy, adjusts learned... | |
| Polymarket Oracle Multi-strategy arbitrage and trading bot for Polymarket prediction markets. Scans ALL markets (crypto, politics, sports, economics, entertainment) for parity... | |
| Proof Engine Transforms every result [PRINCIPAL_NAME] achieves into deployable proof across all business domains. Captures P&L, agent performance, funnel revenue, testimo... | |
| Anti-Injection-Skill Detect prompt injection, jailbreak, role-hijack, and system extraction attempts. Applies multi-layer defense with semantic analysis and penalty scoring. | |
| Skill Combinator — Emergent Capabilities Engine Meta-skill that unlocks emergent capabilities by combining your agent's installed skills in non-obvious ways. Use this skill whenever your agent faces a comp... | |
| Voice Agent Pro Gives any OpenClaw agent a complete voice layer via ElevenLabs. Clones the principal's voice from audio samples, converts any text to MP3 audio (VSL, podcast... | |
| Voice Agent Enables autonomous cloning of your voice via ElevenLabs, converts text to speech, and deploys AI voice agents for automated inbound/outbound calls with Twili... | |
| wesley dashboard builder Skill de création de dashboards live, sites web complets, et pages de preuve sociale pour Wesley-Agent. Déclencher dès que Georges mentionne : dashboard, sit... | |
| market-sentiment-radar A股市场环境与情绪研究。用于盘前简报、大盘体检、板块轮动和跨市场信息整理。先核验数据来源与日期；证据不足时不判定周期、不评分。不用于自动荐股或下单。 | |
| Position Risk Manager 股票仓位管理与风控专家。不负责选股，专注仓位管理和头寸调度。提供移动跟踪止盈、阶梯式止盈、核心 - 卫星策略、动态再平衡等经典模型。适用于大幅浮盈、深度套牢、震荡洗盘等各种持仓场景，给出冷酷理性的买卖和调仓建议。使用场景：用户已有持仓，需要止盈/止损建议、仓位调整、风险控制、心理疏导时触发。 | |
| select-super-stock A股单股技术研究助手。用于核验指定 6 位 A 股代码的已完成交易日日线、趋势指标与数据缺口；不做港美股覆盖声明、不自动筛选、不输出买卖建议。 | |
| stock-cache-utils 股票技能通用缓存工具模块。支持交易时间检测、自动缓存、有效期管理。 | |
| Trade Journal Coach 交易复盘与心理诊断教练。专注于交易后复盘分析，通过拆解历史交易数据、对比计划与执行，找出导致亏损的坏习惯（频繁止损、盈利拿不住、逆势抗单、仓位失控、FOMO 等）。提供心理疏导和纪律约束建议，帮助用户实现"知行合一"。使用场景：用户交易后复盘、连续亏损求安慰、连续盈利求分析、定期review 交易记录时触发。 | |
| Vegas T Trading 维加斯通道 v3.0 多维时空共振体系。基于 EMA12/13/144/169/576/676 + 斐波那契回撤 + 多周期评分，支持 A 股和加密货币。使用场景：用户询问"做 T"、"日内交易"、"维加斯通道"、"EMA 分析"、"斐波那契"或指定股票/币的短线操作建议。 | |
| Nodetool Visual AI workflow builder - ComfyUI meets n8n for LLM agents, RAG pipelines, and multimodal data flows. Local-first, open source (AGPL-3.0). | |
| Context Compactor 上下文压缩代理，采用分层压缩策略，基于内存使用触发机制。处理HOT/WARM/COLD三层数据，优化token使用。当用户需要压缩对话上下文、优化内存使用、管理会话历史、减少token消耗时使用此技能。特别适用于长时间对话、复杂任务处理、需要保留重要历史信息的场景。 | |
| 微信收藏知识库 微信收藏夹导出、智能分类与知识库管理。支持从解析后的 favorite.db 导出收藏记录、自动归纳分类（从用户内容发现自然类别）、LLM 智能增强（可选）、批量导入 IMA 知识库（可选）、多平台导出（Obsidian/Notion，可选）、增量分类。核心功能支持离线使用，网络功能默认关闭。 | |
| Ahrefs Complete SEO Suite Complete Ahrefs API integration for SEO analysis. Covers Site Explorer (domains, backlinks, rankings), Keywords Explorer (search volume, difficulty, SERP ana... | |
| Codex Agent Enhanced 作为项目经理操作 OpenAI Codex CLI 完全体。包含：知识库维护（自动跟踪 Codex 最新功能）、任务执行（提示词设计→执行→监控→质量检查→迭代→汇报）、配置管理（feature flags/模型/skills/MCP）。通过 tmux 操作交互式 TUI，通过 notify hooks + pa... | |
| Cron Doctor by Clawra Diagnose and triage cron job failures. Checks job states, identifies error patterns, prioritizes by criticality, generates health reports. Triggers on: cron... | |
| Agent Task Logger 实时记录和展示 Agent 任务执行进度，支持任务开始、命令执行、状态更新及错误日志的统一管理。 | |
| AtroSnow File Management elephant-guide 后端文件（图片/附件）上传、下载、管理完整开发指南。 当用户提到 elephant-guide 项目的文件上传、头像、图片显示、附件管理、filemedia、FileMedia、文件缓存、文件正式入库等场景时触发本技能。 不适用于 AtroSnow 老项目（.c 后缀接口的项目）。 | |
| 优惠券查询助手 优惠券查询助手，当用户询问优惠、折扣、红包时调用。 | |
| 购物省钱攻略 购物省钱攻略，当用户询问网购、购物、买东西、划算时调用。 | |
| Insight Claw Hermes Download, configure, run, verify, and troubleshoot Insight Claw, an A-share self-selected stock analysis pipeline. | |
| ZLQA-GMT-API-Test 支持ZLQA游戏GM工具接口自动化测试，包括用例管理、执行和测试报告查看，需初始化项目路径绑定接口。 | |
| NoMac Use a full cloud Mac over SSH, HTTPS or MCP for macOS tools, Xcode and iOS development. Start sessions, sync files, run commands, retrieve work and stop. | |
| Pencil Design Create high-quality visual designs — websites, app screens, dashboards, slides, marketing materials, social media graphics — using the Pencil CLI tool. Use t... | |
| Token Usage Tracker Token usage logging, alerting, and context-compression utilities for OpenClaw. Use when you want to track per-call token usage, normalize timestamps, and red... | |
| Gcore FastEdge Use when building, compiling, or deploying WebAssembly HTTP apps to Gcore FastEdge edge computing — triggers on "deploy to FastEdge", "build a FastEdge app", "Wasm on the edge", "Gcore edge function", uploading a .wasm binary, or working wi | |
| Scoro Scoro API v2 integration for time tracking, task management, utilization reporting, team status reports, and billable corrections. Use when: user asks about... | |
| Dia Ask Public Prompt The Browser Company's Dia (a macOS browser whose assistant is an AI agent) from the command line and get its answer back as an exact text file. Use to read/research logged-in or JS-heavy pages in a real browser session. macOS + Acces | |
| Claude Code Collaboration Integrates OpenClaw with Claude Code CLI to delegate coding tasks via JSON queues for advanced multi-turn code collaboration and analysis. | |
| GetBody Get real-world physical tasks done by robots. Use whenever the user needs something done in the physical world that they can't or don't want to do themselves — moving heavy boxes or furniture, gardening, mowing, weeding, clearing snow, clea | |
| dynamoi Music promotion and distribution for artists, labels and YouTube creators. Free Smart Links, Meta and YouTube campaigns, YouTube promotion, 100+ stores. | |
| MoltNet Persistent memory and cryptographic identity via MoltNet. Connects to a remote MCP server over SSE, authenticates via OAuth2 client_credentials, and stores diary entries and cryptographic signatures. Requires the moltnet CLI for local Ed255 | |
| B2B Outbound Sniper Autonomous B2B outbound engine that turns job board hiring signals into qualified pipeline. 6 LLMs. Your own email. 10/10 deliverability. Battle-tested in 30... | |
| Lemnos Cost Guard Real-time API cost tracking, context bloat detection, and budget enforcement for OpenClaw agents. Use when setting up cost guardrails, checking daily spend,... | |
| ClawRoam Portable identity vault for OpenClaw. Syncs knowledge, packages, and memory across machines like iCloud — automatic, invisible, encrypted. Bring your own sto... | |
| ClawRoam Portable identity vault for OpenClaw. Syncs knowledge, packages, and memory across machines like iCloud — automatic, invisible, encrypted. Bring your own sto... | |
| ClawSync Portable identity vault for OpenClaw. Syncs knowledge, packages, and memory across machines like iCloud — automatic, invisible, encrypted. Bring your own sto... | |
| ClawVault Portable identity vault for OpenClaw. Syncs knowledge, packages, and memory across machines like iCloud — automatic, invisible, encrypted. Bring your own sto... | |
| PDF Translation Reserving Exact Same Layout Translate PDFs locally by extracting page text and using the agent's own language capability. Use when Codex needs a repeatable workflow for born-digital or... |
32,601–32,650 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.