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 |
|---|---|
| Isdayoff Checker Определяет, рабочий ли указанный день (по умолчанию — сегодня) с помощью API isdayoff.ru. Использовать, когда нужно быстро ответить «рабочий» или «выходной»... | |
| 24Konbini - Agent Marketplace & Bank The first marketplace and bank for AI agents. Run a storefront, trade digital goods, earn USDC on Base. | |
| Noon 商品数量统计 Noon 商品数量统计工具。输入阿拉伯语关键词，在 noon.com 沙特站搜索，返回搜索结果的商品数量。 | |
| Noon 商品搜索工具 Noon 商品搜索工具。输入阿拉伯语关键词，使用 Chrome 浏览器在 noon.com/saudi-ar 搜索，返回第一页所有商品的标题、评分、评价数和价格。 | |
| 沙特 Noon 选品工具 沙特 Noon 电商选品工具。分析指定市场的竞争情况，识别蓝海产品。触发条件：用户要求选品、分析市场、查找蓝海产品。完整流程：市场翻译 → Noon 商品搜索 → 语义分析卖点 → 供给量搜索 → 蓝海识别 → 定价建议。 | |
| 中阿翻译工具 中阿翻译工具。将中文词汇翻译成符合沙特当地使用习惯的阿拉伯语。 | |
| Zillow × Airbnb Matcher Find properties for sale that are already generating Airbnb income. Cross-references Zillow listings with active Airbnb rentals using geo-matching and calcul... | |
| Clawhub Gate ClawHub 发布前安全门禁：本地静态分析 + ClawScan 轮询，确保 skill 通过 VirusTotal + ClawScan 再发布。 关键词：clawhub publish pre-publish security gate VirusTotal ClawScan shellcheck bandit | |
| Game Ops Monitor Game server real-time monitoring: query TPS, online users, JVM heap from Scouter Collector; detect alerts; send notifications; generate reports. Use when ask... | |
| hermes-model-router Automatically routes tasks to local or cloud AI models based on complexity, ensuring context continuity and single-entry model selection. | |
| Hermes Self Audit 定期审计 Hermes Agent 的自改进行为 - skill 变更、curator 状态、记忆库健康度。防止 Agent 在用户不知情的情况下悄悄进化。建议配合 cronjob 每周运行一次。 | |
| Incident Report Generator 按照用户提供的信息收集线上故障的详细数据，生成结构化的故障异常报告，支持中英文输出。 | |
| Ops Cert Check SSL/TLS Certificate Check & Renewal SOP. Covers certificate validation (PEM/CRT/JKS), Nginx certificate update, Let's Encrypt wildcard application, and emerg... | |
| Ops Code Review Code Review 安全扫描工具，自动化代码审计，支持 Django/Python、React+TypeScript、PHP 多语言。 自动识别代码仓库提交变更，调用安全扫描器进行规范检查和风险检测，报告推送飞书群。 支持 post-commit hook 增量扫描和定时全量扫描。 关键词：Code Revi... | |
| Ops Coding Standards 运维后台（Python/Django）编码规范与最佳实践，适用于 ops_api 等运维系统开发。当要求写ops代码、代码审查、检查编码规范、Python Django开发规范时自动激活。 | |
| Ops Mysql Master Slave MySQL Master-Slave Setup & Troubleshooting SOP. Covers replication setup, Percona XtraBackup large-volume migration, replica lag investigation, and cross-clo... | |
| Pg Game Monitor Prometheus + Grafana 监控方案，专为**单台物理机部署多个 Java 游戏进程 + 自建 MySQL**的场景设计。Java 进程通过 jstat/jcmd 无侵入采集 JVM 运行时指标（堆内存、新生代、老年代、GC、线程、类内存），MySQL 通过 pymysql 采集（Buffer Po... | |
| Server Monitor Collector Collect server monitoring data (Zabbix / Prometheus / Alibaba / Tencent / Huawei Cloud), generate CSV/XLSX reports and send via email or Feishu. | |
| agent-creator-skill Automatically create a new OpenClaw agent, translate its name, and initialize its persona/system prompt based on user requests. | |
| Agent Daily Report 使 Agent 能够复盘本次会话或当日执行记录，输出专业、量化、真实的工作汇报。默认每晚 22:00（Asia/Shanghai）提交当日汇报；也可在用户临时要求时立即汇报。 | |
| Agent Daily Report (EN) Enables the agent to review its own execution logs and deliver a professional, quantified daily work report. Defaults to 21:00 America/Los_Angeles and suppor... | |
| Clawlyra Give your OpenClaw agent a face and a voice: reply as Lyra, a warm 3D avatar companion, and emit her inline performance tags so the self-hosted Lyra app spea... | |
| wechat-article-extractor Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to | |
| Base64 Toolkit Base64 encoding and decoding toolkit. Encode/decode text, URL-safe Base64, and image to Base64 conversion. | |
| IP Threat Check Check IP address threat intelligence. Query multiple sources for IP reputation, geolocation, and threat scores. | |
| JSON Wizard JSON formatting, validation, and conversion tool. Format, compress, validate JSON, and convert between JSON and YAML. | |
| Log Parser Parse and analyze various log formats (nginx, apache, syslog, application logs). Extract key information and generate reports. | |
| Skill Radar Scan, analyze, and optimize your AI skill ecosystem. Diagnose skill usage, discover capability gaps, and check version updates in one command. Trigger on "sk... | |
| Timestamp Toolkit Timestamp conversion tool. Convert between Unix timestamp, datetime, and various date formats. | |
| URL Toolkit URL encoding, decoding, parameter parsing, and URL manipulation toolkit for developers. | |
| goloco Connect an MCP-capable coding agent to Goloco through a connection-bound credential, verify the selected agent and permissions, and use the supply-side tools without treating the credential as an account session or a wallet signer. Use this | |
| Maven Smart System Ai (palantir integration) Advanced text-based integration suite for Palantir Maven Smart System (MSS). Manages targets, Kanban workflow, CDE risk assessment, SIGINT intelligence fusio... | |
| Taizi Agent Browser A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co... | |
| Ai Productivity Audit Audit a user's current AI tool stack. Score each tool by ROI, identify redundancies, gaps, and upgrade opportunities. Produces a structured report with score... | |
| Taizi Alicloud Ai Image Generate images with Model Studio DashScope SDK using Qwen Image generation models (qwen-image-max, qwen-image-plus-2026-01-09). Use when implementing or doc... | |
| Apple Notes Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks Clawdbot to add a note, lis... | |
| Taizi Brave Search Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required. | |
| Taizi Browsh A modern text-based browser. Renders web pages in the terminal using headless Firefox. | |
| Taizi Claw Shell Runs shell commands inside a dedicated tmux session named 'claw', returning command output and prompting before destructive commands. | |
| Coding Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding. | |
| Discord Control Discord via Clawdbot to send messages, react, post stickers/emojis, run polls, manage threads/pins/search, fetch info, and moderate channels or DMs. | |
| Taizi Filesystem Advanced filesystem operations - listing, searching, batch processing, and directory analysis for Clawdbot | |
| Reminder Capture natural-language events in Chinese or English, save them to your workspace, and schedule Telegram reminders with default 24h, 1h, and 10m notifications. | |
| write-skills-demo Use when creating new skills, editing existing skills, or verifying skills work before deployment | |
| LoongFlow — PEES Iterative Agent LoongFlow brings evolutionary multi-agent optimization to your coding agent harness. Drop it into Codex, Claude Code, Cursor or any OpenClaw agent — then wat... | |
| MemWeaver Memory Profiler — Mine hidden patterns from your Agent's memory, confirm via interactive quiz, and generate a structured user profile. | |
| cognitive-behavior-evaluator Run standardized, safety-oriented behavioral evaluations of a TARGET AI agent. Injects controlled diagnostic probes (authority-pressure resistance, false-premise / hallucination grounding, implicit-bias neutrality), scores the target's resp | |
| Trading Behaviour Assessor Assess trading decisions for cognitive biases, risk management adherence, and emotional reasoning using behavioral finance stress tests and metacognitive int... | |
| Obsidian Daily Log Update freznel's Obsidian daily note with timestamped activity entries, especially day recaps, travel logs, itineraries, movement updates, and "I did X at Y... | |
| SeekDB Memory Setup 为 OpenClaw 安装云端 m0 记忆插件。当用户提供 Access Key（以 ak_ 开头）或提到「配置云端记忆」「安装记忆插件」「setup memory」时使用此 skill。 |
31,351–31,400 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.