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 |
|---|---|
| Writing Style Skill 可复用的写作风格 Skill 模板。内置自动学习： 从你的修改中自动提取规则，SKILL.md 越用越准。 Fork 后改成你自己的风格。 | |
| prompt-architect Use this skill whenever the user wants to create, design, improve, debug, or evaluate prompts or AI workflows. Triggers include: vague ideas like "I want an... | |
| Career Planner 职业规划顾问 A professional AI career planning advisor that guides users step-by-step through a structured interview to understand their background, skills, interests, si... | |
| Deep Planner A meta-skill that activates before complex tasks to enforce structured planning, step-by-step execution, and self-reflection. Works like Claude Code's TodoLi... | |
| 面试助手 面试准备助手。用户提供简历和岗位JD后，支持两种模式：① 分析考点并生成针对性面试题目和参考答案；② 针对JD个性化修改简历，并说明每处改动的原因。适用于"帮我准备面试"、"根据JD出题"、"帮我改简历"、"简历怎么针对这个岗位优化"等场景。简历和JD支持 PDF/图片/Word/纯文字，自动识别格式。 | |
| 个人记账 个人记账技能，支持文字输入和图片账单识别。当用户提到记账、记录花费、添加支出/收入、上传账单图片、查看账单、统计消费时必须使用此技能。用户单独发送图片（无任何文字）时也必须触发此技能，直接看图判断金额并记账，不要等待用户补充说明。所有账单按天存储在 bills/ 文件夹中，同一天的账单累加到同一文件。 | |
| Ai Agent Tools Version Changelog 查询Claude Code、OpenClaw和Hermes Agent的最新版本和版本日志，包括发布日期及主要更新内容。 | |
| Data Structure Protocol (DSP) Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions),... | |
| Local Video Ad Pipeline v0.5 Local Video Ad Pipeline v0.5 is a public OpenClaw skill for producing short commercial videos and YouTube Shorts with local AI models. It uses a local LLM as... | |
| Asana Manage Asana via the Asana REST API. Use when you need to list workspaces, projects, tasks, search tasks, comment, update, complete, or create tasks. | |
| Hyperliquid Read-only Hyperliquid market data assistant (perps + spot optional) with support for natural-language requests and deterministic command parsing (terminal-style `hl ...` and slash-style `/hl ...`). Use to fetch quotes (mark/mid/oracle/fundi | |
| Morning (Green Invoice) Use to authenticate with Morning (GreenInvoice) and create/manage clients, items, and accounting documents (invoice/receipt/quote/order/credit). | |
| Kazakhstan tax assistant Kazakhstan tax assistant — НК РК / ҚР Салық кодексі (актуальная редакция). Отвечает на вопросы о налогах на русском и казахском языках. Ищет статьи, объясняе... | |
| 百度AI搜索（千帆） 基于百度千帆平台，提供联网智能搜索问答，返回AI生成总结及带来源引用的结果。 | |
| Qweather 和风天气 QWeather API 调用。当用户查询天气、获取天气预报（今日/7天/24小时）、空气质量、天气指数等与天气相关请求时使用此技能。支持城市代码/城市名/经纬度定位。注意：仅在用户明确要求使用和风天气或需要免费API天气数据时使用，否则默认用 agent-browser + weather.com.cn。 | |
| SpringBoot升级-BW Spring Boot 2.7 升级到 3.5 的标准流程 | |
| codeql-skill CodeQL security audit pipeline: static scanning, SARIF triage, and QL query optimization. Trigger on: CodeQL, .ql, .sarif, taint tracking, source→sink, LGTM,... | |
| my-crypto-signal-skill Crypto trading signal, price prediction, market analysis for any Binance pair (BTC, ETH, SOL, USDT...). Trigger on: crypto, signal, buy, sell, "should I buy"... | |
| Notnative Use Notnative MCP server for complete AI assistant integration with notes, calendar, tasks, Python, canvas, and permanent memory. This skill provides persist... | |
| DingTalk Channel Install 安装和配置 OpenClaw 钉钉通道。使用当用户需要：(1) 安装 @soimy/dingtalk 插件，(2) 配置钉钉通道（Client ID/Secret 等），(3) 设置钉钉机器人连接。提供一键安装脚本和完整配置流程。 | |
| API Cost Tracker Track AI API costs across OpenAI, Anthropic, Google AI with budget alerts, analytics, and optimization tips | |
| cetus Provides TypeScript SDKs for building DeFi apps on Sui with Cetus Protocol components like AMMs, vaults, farms, limit orders, xCETUS token, and aggregation. | |
| stable-layer-sdk A TypeScript SDK for interacting with Stable Layer on Sui blockchain, supporting minting, burning stablecoins, claiming yield rewards, and querying supply. | |
| Sui Sec Sui Secure - Pre-simulate transactions via sui client call --dry-run and sui client ptb --dry-run, compare results against user intent to detect malicious contract behavior. Only execute if intent matches; block otherwise. | |
| sm-ocr-scanner Lokale OCR für Rasterbilder (jpg, png, bmp, gif, tiff, webp) und PDF-Dateien mit dem systemeigenen tesseract-Binary. PDF-Seiten werden lokal mit pdftoppm gerastert, vorhandene PDF-Textlayer mit pdftotext gelesen. Ausgabe als Klartext, TSV m | |
| pomodoist Manage the user's Pomodoist tasks, projects, deadlines and synchronized Focus sessions through the configured Pomodoist MCP connection. | |
| Portfolio Optimizer virtual-trading MCPの価格情報とautomatic-investment-strategy/analysisのニュース分析を 組み合わせてポートフォリオを最適化し、割安資産の購入・割高資産の売却を実行する。 年率7%以上を目標とし、買い判断・売り判断・リバランス提案を行う。 ユーザーが「ポートフ... | |
| Youtube Music Player Operate YouTube Music via natural language. Search songs, artists, albums, playlists, lyrics, charts, recommendations, and control playback. Browse personal... | |
| AIOS App Service 当请求依赖 AIOS、OpenClaw、Forguncy 等业务系统的实时数据、接口调用或业务操作时，优先使用本技能。先读取 AIOS_ONTOLOGY_DIR 指向的本体目录，再确认应用、命令、参数结构和枚举映射，通过 aios-apps-invoke-cli 发起调用，并以实时返回结果作为后续分析和执行依据。... | |
| AIOS Chart Image Render JSON or Markdown data into ECharts images | |
| AIOS 自改进 Agent 在 AIOS/OpenClaw 运行环境中记录当前 agent 的错误、纠正、经验、知识缺口和可复用改进。适用于命令失败、用户纠正回答、发现过时知识、外部工具/API 异常、同类问题反复出现、完成复杂任务后需要沉淀经验、或开始重要任务前需要回顾当前 agent workspace 内历史 learnings 的场... | |
| AIOS File Transfer 通过兼容 AWS S3 的 SDK 为 OpenClaw 和 AIOS agent 处理文件传输。当 agent 收到 `file_input://...` URI、需要按当前 `senderId` 把输入文件下载到工作区，或需要把当前 `senderId` 目录内的本地文件上传后以 `file_output:/... | |
| Convert Document To Markdown Convert supported local files into Markdown by running this repository's Dockerized file-only CLI. This skill must run through Docker with a prebuilt Aliyun... | |
| Develop and Deploy Web App Build, run, and share a simple full-stack web application with a TypeScript Express backend, React frontend, and SQLite database. Use when a user wants a wor... | |
| File Exchange via Qiniu Kodo Transfer files exclusively through Qiniu Kodo using qshell commands for downloading and uploading with timestamped filenames in specific directories. | |
| Operate Web Apps Built by Forguncy (aka 活字格) Provides functionality to interact with SpreadJS tables in the web applications built by Forguncy (aka 活字格), specifically for extracting table data and colum... | |
| Install Skills from Clawhub for all Agents Install or upgrade a ClawHub skill, then make the global copy under the machine's OpenClaw home `skills/` directory the final source of truth. Use when the u... | |
| 多用户隔离型长期记忆 Multi-user Long Term Memory 为多个用户创建和管理独立的长期记忆文件，记录偏好和上下文并按用户名隔离存储。 | |
| 七牛云对象存储操作 使用七牛云 Kodo 与 qshell 执行对象存储操作，包含下载 qshell、配置账号、查询 bucket、上传文件、下载文件。适用于用户提到七牛云、七牛 Kodo、qshell、对象存储上传下载、AK/SK、bucket、key、文件中转、把文件上传到七牛或从七牛下载到本地的场景。 | |
| Knowledge Base with Faiss and Bailian (embedding and rerank) 使用 Python、FAISS、BM25、阿里云百炼 text-embedding-v4 与可选的 qwen3-rerank，维护基于文件目录的本地知识库；适用于在 OpenClaw 预先抽取文本后，遍历 chunks 与 T2Q 建立索引，以及对指定知识库或全部知识库做综合、语义或关键词查询。 | |
| agentchan Anonymous imageboard for AI agents. Agents post. Humans observe. | |
| Train your mind with algorithms 🎯 Interactive algorithm practice with 100+ problems across Easy/Medium/Hard difficulties. Generates ready-to-run code templates in Java & Python with built-... | |
| Weather Outfit Advisor Query weather and provide outfit recommendations. When information is insufficient, ask about destination, date, and clothing preferences. Uses free weather... | |
| 港股卖空数据 Get Hong Kong stock short selling data (daily and historical) from HKEX and ETNet. 免费获取港股每日和历史卖空数据。 | |
| aegis-japan-tourism-entry Find a machine-readable, business-only entry guide for launching an experiential tour in Japan, then use its free preview before any optional paid preparation pack. | |
| agent-card-health-check Check authorization, endpoint, and authentication of an A2A Agent Card with a read-only diagnostic before connecting. | |
| Japan RuleWatch Provides official-source guidance and evidence for Japan experiential-tourism market entry and Japanese ecommerce regulations. | |
| x402 MCP Starter Validate x402 USDC payment configurations for a read-only MCP product on Cloudflare Workers before adding paid tools or deploying. | |
| ASI-Proxy Phase Skill Advance evidence-gated ASI-proxy capability | |
| PIC Residual Guard OpenClaw agent safety checklist for action review, risk assessment, rollback planning, and LLM output validation before external effects. |
43,951–44,000 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.