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 |
|---|---|
| Volcano Plot Labeler Automatically label top significant genes in volcano plots with repulsion algorithm | |
| Volcano Plot Script Generate R/Python code for volcano plots from DEG (Differentially Expressed Genes) analysis results. Triggered when user needs visualization of gene expressi... | |
| Gemini Browser Query Google Gemini via browser automation using OpenClaw's Browser Relay. Use when you need to ask Gemini questions and get AI responses. Requires OpenClaw... | |
| Sparkbtcbot Set up Spark Bitcoin L2 wallet capabilities for AI agents. Initialize wallets from mnemonic, transfer sats and tokens, create/pay Lightning invoices, pay L40... | |
| Spark Bitcoin L2 Proxy for AI Agents Use a Spark Bitcoin L2 wallet proxy for AI agents via HTTP API. Check balances, send payments, create invoices, pay L402 paywalls — all without holding the m... | |
| Deploy Spark Bitcoin L2 Proxy Deploy a serverless Spark Bitcoin L2 proxy on Vercel with spending limits, auth, and Redis logging. Use when user wants to set up a new proxy, configure env... | |
| JOULE DAO Interact with JOULE DAO on Base: track treasury, view proposals, vote, discuss, check balances, join as member, and earn JOULE for productive work contributi... | |
| Taskr - Persistent Task Planning & Execution for AI Agents Persistent cloud task planning and execution for OpenClaw. Create hierarchical task plans that survive session resets, span multiple agents, and let users re... | |
| docs-pdf Use this skill whenever the user wants to do anything with PDF files. Triggers include: reading or extracting text/tables from PDFs, combining or merging mul... | |
| qq群聊ai dnd dm 一个极度硬核、冷酷无情、高死亡率的《暗黑地牢》风格跑团 DM。 当用户要求进行暗黑地牢冒险、克苏鲁跑团或探索极暗领地时触发。 内置压力值（Stress）、火把亮度（Light）以及极度致命的战斗检定机制。 | |
| Config Rollback OpenClaw 配置回滚管理 - 备份、超时保护、自动回滚 | |
| Use OpenClaw Manual 配置 OpenClaw 前必须查阅官方文档的技能。当用户提到任何配置相关的话题（agent、session、channel、cron、通知、工具、workspace、gateway 等）时，立即使用此技能搜索本地文档。不要凭经验猜测——先查文档再设计方案。 | |
| 大话职场 大话职场——一个用 15 本经典管理/领导力/职场名著搭起来的"职场参谋"，把《卓有成效的管理者》《管理的实践》《竞争战略》《第五项修炼》《高效能人士的七个习惯》《远见：如何规划职业生涯的三大阶段》《深度工作》《影响力》《格鲁夫给经理人的第一课》《领导梯队》《上任第一年》，以及曾仕强《中道管理》《被领导的艺术》《圆通的人际关系》《中国式管理全集》的核心框架，转成能直接用的判断与动作。当用户遇到任何职场问题时都应主动使用：如何管理时间与精力、如何把事做成做深、如何从个人贡献者变 | |
| 蛋叔订单商品查询 当用户需要查询蛋糕订单信息时使用此技能。通过输入订单号，调用内部API查询对应的蛋糕商品名称。此技能应在下述情况时使用：用户询问"查订单"、"订单查询"、"蛋糕订单"、"查蛋糕"、或直接提供订单号要求查询。技能会自动组装API请求并解析返回结果，提取商品名称返回给用户。 | |
| Decompose Mcp Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic. | |
| bossclaw 智能入职管理工具，支持管理员确认注册，查询简历浏览次数和安全更新个人资料。 | |
| CSDN 文章发布 CSDN 文章发布技能 | |
| Legal Guard Prevents autonomous signing of legal agreements or contracts. Use when an agent identifies a request or document related to signatures (DocuSign, HelloSign,... | |
| Little Steve Agent Guard Self-evolving security system for agent skills enforcing risk assessment, audit logging, tiered approvals, and continuous rule updates on all skill commands. | |
| Little Steve Content Inbox Archive, browse, and manage chat content including links, notes, and images with read/star status and pagination in an IM-native inbox. | |
| Little Steve Task Manager 小史任务管理器：面向 IM 场景的轻量任务系统，快速可用、与工作流高度融合，可在聊天中直接管理任务并支持每日汇总与自动状态更新。 | |
| Echosaw Media Intelligence Analyze video, audio, and image files using AI. Produces structured intelligence reports including transcripts, content moderation signals, sentiment analysi... | |
| Clawculator Analyze OpenClaw costs and detect billing issues. Source code is fully bundled — nothing is fetched at runtime. Requires only the node binary. | |
| Boss BMAD 全自动项目编排 Skill。从需求到部署的完整研发流水线，编排多个专业 Agent（PM、架构师、UI 设计师、Tech Lead、Scrum Master、开发者、QA、DevOps）自动完成完整研发周期。当用户说 'boss mode'、'/boss'、'全自动开发'、'从需求到部署'、'帮我做一个... | |
| Learning System AI 领域系统学习体系。管理知识图谱、深度学习笔记、实战复盘和关联网络。触发场景：学习计划、知识图谱更新、深度研究某个 AI 主题、实战复盘总结、调研后沉淀知识、每周学习回顾。当用户说'学了什么'、'总结一下'、'沉淀知识'、'复盘'、'更新图谱'、'深入研究'、'写笔记'、'学习回顾'、'review what... | |
| QQMail Organizer Agent-facing QQ Mail inbox management over IMAP/SMTP for OpenClaw, Hermes, and other autonomous agents. Use when an agent must read, search, reply to, classi... | |
| Spec Flow Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan',... | |
| Unloopa Api Make your agent sell websites to local businesses on autopilot. Finds leads from Google Maps, builds a custom AI website for each one, sends outreach emails, and can even call them. Use when the user wants to find leads, generate websites, | |
| Flux Publish events and query shared world state via Flux state engine. Use when agents need to share observations, coordinate on shared data, or track entity sta... | |
| ecloud-eos 移动云对象存储(EOS)技能。当用户需要上传、下载、管理云存储文件等操作时使用此技能。 | |
| hindi-drafting Professional Hindi drafting for business documents, government applications, HR, legal, and marketing content for Indian startups and SMEs | |
| bilibili-video-search-and-download Search and download Bilibili videos using yt-dlp and httpx. Use this skill whenever the user wants to search Bilibili for videos by keyword, retrieve video m... | |
| mp3-list-to-video 将指定文件夹下的所有 MP3 文件拼接成一个 MP4 视频文件，可生成黑色背景视频，也可基于已合并 MP4 生成带歌曲清单、当前歌曲高亮和右侧旋转黑胶唱片动效的菜单背景视频。菜单高亮默认使用智能分段渲染：并行生成关键帧、每首歌开头高帧密度、其余静态区间单帧拉长，避免整段 30fps 慢速重渲染；黑胶唱片作为独立动... | |
| E-commerce Gmail Customer Service Privacy-first ecommerce Gmail customer-service skill for OpenClaw. It triages inbox messages, researches public storefront data, creates draft-first replies, learns approved patterns, and auto-replies only in owner-enabled categories. Priva | |
| seo-evaluator Evaluate e-commerce pages with evidence-first SEO findings that distinguish verified issues, likely signals, editorial opportunities, unavailable checks, and appendix items. | |
| Ecosincronia Supabase Connect to Supabase for database operations, vector search, and storage. Use for storing data, running SQL queries, similarity search with pgvector, and mana... | |
| Proposal Service Inspect and create real OpenClaw proposals in public.openclaw_proposals for the current closed-loop workflow. Use for checking duplicate pending proposals an... | |
| Reaction Processor Record real OpenClaw events and reactions for the current closed-loop workflow. Use for logging duplicate-skipped and proposal-created outcomes in public.ope... | |
| Read Policy Read OpenClaw policies from PostgreSQL through the local Supabase Docker stack. Use for inspecting policy keys such as auto_approve, priority_routing, or ava... | |
| Trigger Evaluator Evaluate real OpenClaw trigger rules against the current database state. Use for heartbeat-style trigger checks, especially stale mission detection backed by... | |
| Workspace Files Work safely with files inside the OpenClaw workspace sandbox. Use for listing directories, reading text files, writing text files, and searching files by nam... | |
| ecovacs-skills-deebot-control Control Ecovacs Deebot vacuums via the IoT API and a gateway. Users must obtain and provide an AK from the Open Platform; scripts/ecovacs.py and gateway /rob... | |
| ecovacs-skills-pet-control Control Ecovacs FAMIBOT (pet) robots via the Open Platform Access Key (AK) and POST /robot/skill/pet/cmd. Covers device discovery, queries/settings, display/... | |
| ask-user-md 引导用户通过行业模板逐步选择产品类型、功能和需求，最终形成结构化需求文档，帮助明确产品设计和开发方向。 | |
| LyraShield AI Review LyraShield release-assurance evidence through an OAuth-first MCP connection. | |
| EctoClaw Cryptographic audit ledger and AI firewall for OpenClaw agents. Records every agent action (messages, skills, tools, plugins, memory, models) in an immutable... | |
| Agent Metaverse Trade crypto on Agent Metaverse virtual exchange - spot, futures (1-125x), and AMM swaps with 10k USDT starting balance | |
| discovery-call-prep Turns a stated hypothesis and what you know about a person into a discovery-call question guide where every question asks about something that already happened. Grounded in two books, not paraphrased from either, The Mom Test's rule that a | |
| Tennis Vacation Rater Evaluate tennis vacation destinations with structured scoring across transportation, accommodation, weather, and court facilities. Use when users ask about t... | |
| Harness Engineering Agent Harness 构建规范——当 AI 通过编程构建 harness agent（coding agent / 自动化 agent / 长时运行 agent）时，读取本 skill 作为参考标准，确保产出符合 harness 工程架构：Loop / Provider / Tools / Permissions / Session / Compaction / Prompts & Skills / Extensions 七层 + Delivery。覆盖设计决策、可运行 |
27,901–27,950 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.