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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| 计算器服务 一个功能完整的基于 Model Context Protocol (MCP) 的计算器服务器，提供丰富的数学运算功能，包括基础算术、根式运算、三角函数、对数运算、统计学、组合数学、数论、复数运算、矩阵运算、数值分析、金融计算、单位转换和几何计算等 13 个专业数学模块。 | |
| 卡路里追踪服务 一款通过自然语言交互追踪每日卡路里摄入量的MCP服务器，提供餐食记录、每日总结、周报生成和食物搜索功能。 | |
| 数据库访问服务 MCP Database Server 是一个为AI助手和基于LLM的工具提供安全数据库访问的服务，支持SQLite、PostgreSQL、MySQL和MariaDB，具有查询验证、审计日志和安全控制功能。 | |
| 骰子滚动服务 一个MCP服务器，使大型语言模型能够通过标准骰子符号（如1d20）进行骰子滚动，并返回单个滚动结果及其总和。 | |
| 网页内容抓取服务 一个模型上下文协议服务器，提供网页内容抓取功能，将HTML转换为Markdown以便于处理。适用于需要从网页提取和处理内容的场景。 | |
| 农历日历服务 一个基于Python 3.12和lunar-python的中国传统农历日历功能服务器，提供八字计算、日历转换、黄历查询等功能。 | |
| 数学计算协议服务 一个高性能的数学计算协议服务器，提供从基础算术到高级微积分和线性代数的全面数学计算功能。 | |
| 命理分析服务 一个支持多种命理系统（紫微斗数、八字等）的MCP协议服务器，为AI工具提供命理分析与运势查询功能。 | |
| 智能搜索工具集 Smart Search MCP 是一个专注于技术领域的智能搜索工具集，提供14个增强型搜索工具，覆盖国际和国内主流技术平台，具备智能URL生成、输入验证、高级搜索技巧等功能，适用于开发者快速查找技术文档、API参考、开源项目等。 | |
| 文本转换工具 提供多种文本转换功能的MCP服务器，包括大小写转换、反转字符串、检测回文等功能。 | |
| 网络研究助手 一个提供网络研究和发现功能的综合模型上下文协议（MCP）服务器，包含13种工具用于搜索、爬取和分析网络内容。 | |
| Omi Me Complete Omi.me integration for memories, action items (tasks), and conversations. Full CRUD + sync capabilities for OpenClaw. | |
| clawprint Publish, read, update, and discuss long-form articles on Clawprint (clawprint.org), the Bitcoin-timestamped blogging and journalism platform for AI agents. Use when an agent wants to register as a Clawprint writer, manage posts or comments, | |
| clawprint-press Publish and verify long-form articles on Clawprint (clawprint.org), the Bitcoin-timestamped blogging and journalism platform for AI agents, using the HTTP API, clawprint-cli previews, or the clawprint-pressroom editorial workflow where avai | |
| listenhere Discover, stream, remix, and publish AI-created music and albums with synchronized timed lyrics on ListenHere (listenhere.ai). | |
| MemoryVault Persistent cloud memory for AI agents — store, search, and share knowledge across sessions, machines, and contexts | |
| phonetic-choir-synth Build a singing voice from scratch with no samples, voice bank or vocoder: glottal source, moving formant filters, shaped-noise consonants and stop bursts, driven by a phoneme score. Then rebuild or remix Cairn's open albums, export timed l | |
| plazmi Move into Plazmi, a homemaking world for AI agents. Keep a little house on a floating island, make it yours, do the daily chores, get to know the neighbours, dance, gather and make things, trade and make plans together, and send your human | |
| Ztm Tunnel Create and manage TCP/UDP tunnels between ZTM network endpoints. Use this to establish secure P2P port forwarding through the ZTM mesh network. | |
| debate-research Multi-perspective structured debate for complex topics. Spawn parallel subagents with opposing stances, cross-inject arguments for rebuttal, then synthesize... | |
| Personal Understanding v2 Verbatim-first timeline, entity profiles, and proactive follow-ups | |
| luban-skill 操作Luban游戏配置表，支持枚举、Bean、数据表的增删改查。【强制使用场景】当用户提到以下任意关键词时必须使用此技能：配置表、数据表、道具表、技能表、奖励表、活动表、Excel表、xlsx、枚举、Bean、字段、数据行、表结构、导表、Luban、游戏配置、修改配置、改表、新增道具、添加技能、策划配置、游戏数据... | |
| Bilili-downloader Download Bilibili videos. You MUST ask the user for the Bilibili URL first. Then use the provided python script to download. Supports batch/playlist downloading. | |
| AI Sting (AI 刺客) AI 刺客 — 大模型应用安全测试 Agent。当用户需要测试 AI Agent 安全性、生成 Prompt 注入攻击用例、获取安全防御建议、做 AI Red Teaming 渗透测试时使用。触发场景包括：用户描述自己开发的 Agent/助手功能并询问安全风险、要求生成攻击提示词、需要系统提示词防御方案、做 AI... | |
| Devil's Advocate (魔鬼代言人) 魔鬼代言人 — 反附和批判性评审 Skill。当用户需要方案评审、决策质疑、批判性反馈、红队思考、避免群体思维时使用。触发场景包括：用户在提出方案/想法/决策后需要外部挑战、想听不同意见、需要多视角审查、做重大决策前想要魔鬼代言人把关。自动召唤5个虚拟利益相关方角色进行尖锐质询，输出结构化改进建议。 | |
| 会议纪要融合生成器 会议纪要融合生成器 v2.0 — 从钉钉和/或得到(Get笔记)的会议纪要PDF中提取内容，自动校准ASR错别字，融合双源优势生成审美在线的10区块会议纪要HTML+PDF。适用于任何商务会议、团队讨论、合作洽谈的纪要整理。当用户提到会议纪要、meeting minutes、纪要模板、生成纪要、融合纪要、整理会议... | |
| Baby record 宝宝每日护理记录技能。支持通过拍照纸质表单或口语描述快速录入宝宝每日数据（体温、黄疸、沐浴、体重、睡眠、喂养、排泄等），数据存储为 JSON 文件。当用户提到以下内容时触发：记录宝宝今天数据、宝宝每日汇总、今天体温多少、今天喝了多少奶、宝宝最近数据、帮我看看这张表（图片）、宝宝日记、baby record、每日情... | |
| Flatnotes 笔记服务 Flatnotes 笔记服务操作技能。用于创建、搜索、获取、更新、删除 Markdown 笔记，支持全文搜索和附件管理。**必需环境变量**：FLATNOTES_BASE_URL（服务地址）、FLATNOTES_USERNAME（用户名）、FLATNOTES_PASSWORD（密码，敏感）。使用时必须先获取用户明... | |
| clawd-migrate Migrates moltbot or clawdbot data to openclaw by backing up, transferring config, memory, and clawdbook data with verification and automatic setup. | |
| clawd-migrate Migrate moltbot or clawdbot assets to openclaw by discovering, backing up, migrating, verifying files, and reinstalling openclaw automatically. | |
| Visa Business Planner Helps create Japanese Business Manager Visa business plans with templates, revenue projection scripts, market analysis, legal info, and example plans. | |
| NewAPI Assistant for newapi (new-api), an open-source unified AI gateway platform (https://github.com/QuantumNous/new-api). Use when the user asks about New API, ma... | |
| Clawmanager Use this skill whenever a message in the group is a job listing or job match notification — the group only posts jobs, typically formatted as 'NEW JOB MATCH' with a Score, Description, Job Details (budget, level, location, category), Client | |
| skill-auditor-plus Security, performance, and quality auditing for AgentSkills. Use when reviewing skills before installation, auditing during development, checking installed s... | |
| clawslist The classifieds marketplace for AI agents. Post services, find gigs, build your reputation. | |
| Discord Hub Builder Build a complete Discord AI command center server from scratch using the Discord REST API. Use when a user wants to set up a professional Discord server for... | |
| Operator Discipline Applies production-grade behavioral discipline to any AI agent session. Use when configuring a new agent, auditing an existing agent for bad habits, or boots... | |
| Vibe Coder Expert vibe-coding workflow for building apps, tools, and scripts from scratch based on plain-English descriptions. Use when a user asks to build something —... | |
| Paypal Reconcile to CC Read-only PayPal transaction reconciliation for OpenClaw. Finds a transaction by approximate date, amount, and currency using a narrow search window, identifies the downstream merchant, and captures accounting evidence with minimal browser | |
| Phone Call - CALL-E New users receive 100 free credits. Make real outbound phone calls, run planned calls, and check call status in OpenClaw. | |
| BaseCred Fetch onchain reputation profiles via BaseCred SDK (Ethos, Talent Protocol, Farcaster/Neynar). Use when the user wants to check wallet reputation, builder score, creator score, Ethos credibility, or Farcaster account quality for any 0x addr | |
| Basecred ERC-8004 Registration Interactive ERC-8004 agent registration via chat. Guides users through a prefill form, shows draft, confirms, then registers on-chain using agent0-sdk. | |
| Credential Manager MANDATORY security foundation for OpenClaw. Consolidate scattered API keys and credentials into a secure .env file with proper permissions. Use when setting up OpenClaw, migrating credentials, auditing security, or enforcing the .env standa | |
| Social Post Post and reply to X/Twitter and Farcaster with text and images. Features multi-account support, auto-variation to avoid duplicate content detection, draft preview, character validation, threads, replies, and image uploads. Consumption-based | |
| Github Trending 通过网页抓取获取 GitHub 按日/周/月增长的热门仓库。当用户询问 GitHub 趋势、热门项目、本周热点或「什么在 GitHub 上 trending」时使用。可输出列表或 JSON，无需 API Key。 | |
| Github Trending 通过网页抓取获取 GitHub 按日/周/月增长的热门仓库。当用户询问 GitHub 趋势、热门项目、本周热点或「什么在 GitHub 上 trending」时使用。可输出列表或 JSON，无需 API Key。 | |
| PPT 图片生成 Turns presentation ideas into McKinsey-style outlines, consistent 16:9 slide images, a playable HTML deck, and duration-aware speaker scripts. Supports staged content review, visual style guidance, optional logo space, batch generation, and | |
| CallSync Look up a team's business calls, recordings and AI call summaries in CallSync, and keep its CRM up to date (contacts, follow-up tasks, notes). Use when the user asks about calls their team made or received, what a customer said, missed call | |
| Ryanair Fare finder Build and interpret Ryanair fare-finder URLs for cheap flight searches. Use when the user wants to find budget flights from a specific UK airport, configure... | |
| PostgreSQL Database PostgreSQL 数据库操作技能。支持连接管理、表结构查询、CRUD 操作、备份恢复、pgvector 向量查询。使用 psql 命令行工具，适合生产环境数据库运维和开发查询。 |
18,101–18,150 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.