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 |
|---|---|
| AI Hotel Booking Search and book hotels through TourMind using live hotel, room-rate, availability, policy, order, and payment data. Use for accommodation discovery, comparison, booking, order lookup, cancellation, or payment in any language, including impl | |
| Travel Plan-Journione 为旅行灵感、目的地选择、逐日行程、Citywalk、主题旅行、行程调整和照片回忆整理提供完整旅行方案。可自然语言触发，或由用户选择 journione。先规划每天怎么玩；联网与机酒工具按实际可用能力增强，确认后且生成能力就绪时创建可分享的 JourniOne Travel Journal。 | |
| PrivateBin Upload Skill Upload content to a PrivateBin instance and return a shareable link. Use when the user wants to share text, code, reports, or files via paste URL with option... | |
| LOFMonitor Finance Stock Investment Monitors A-share LOF fund premium/discount exceeding 10% to identify and output potential arbitrage opportunities. | |
| SwiftUI macOS Expert SwiftUI guidance for macOS apps — covers writing and reviewing code with runtime-level understanding of observation, concurrency, performance, and pla... | |
| Deeplake SDK for ingesting data into Deeplake managed tables. Use when users want to store, ingest, or query data in Deeplake. | |
| FlowForge Workflow Engine Run structured multi-step workflows via FlowForge engine. Use when user requests step-by-step execution, structured workflows, or when a task needs enforced... | |
| Agent Memes Send meme reaction images in chat. One command to pick & send. Multi-platform (Discord, Feishu, Telegram, etc). Use when the conversation calls for a visual... | |
| Cove Ops Cove platform operations: channel files, cove.md, webhooks, channels, messages, members, reactions, roles, and permissions. | |
| Gogetajob Open-source contribution workflow — find GitHub issues, implement fixes, submit PRs, track results. Use when: (1) starting a work loop or contribution cycle... | |
| FlowForge Run structured multi-step workflows via FlowForge engine. Use when user requests step-by-step execution, structured workflows, or when a task needs enforced... | |
| openclaw-teleport Migrate, backup, or restore an OpenClaw agent workspace to/from a single .soul file. Use when the user wants to move an agent to a new machine, back up their... | |
| OpenClaw Zulip Channel Plugin Zulip channel plugin for OpenClaw with topic threading, metadata DB, bot commands, and event queue processing. Install from source when you want to connect O... | |
| Pulse TODO Unified task management and scheduling for AI agents. Use when: (1) a commitment is made (I'll do X, 帮你跟进, remember to), (2) checking what's pending (待办, wha... | |
| 个性化BOSS直聘打招呼生成器和JD对比 BOSS直聘打招呼内容生成器。当用户提到「打招呼」「BOSS直聘」「投简历」「JD」「岗位」「求职」 或发送招聘截图/岗位描述时触发。支持：生成个性化打招呼话术、多岗位匹配度排序对比、 截图识别JD内容、用户求职档案管理。首次使用时引导建档。 | |
| 考公备考追踪 朱批录 · 国考备考追踪 Skill。当用户发来套题成绩、错题截图、备考打卡或复习进度时触发。 核心功能：识别错题截图 → 分类错题原因 → 更新本地记录 → 生成每日总结 → 导出 Excel / 同步飞书。 触发关键词：做了一套题、今天做了、错了几道、帮我分析、备考打卡、行测、申论、 判断推理、资料分析、言语... | |
| 拾遗 · 通用备考错题追踪（shiyi-study-tracker） 拾遗 · 通用考试备考追踪 Skill。适用于任何考试——GRE、雅思、考研、注会、高考、期末…… 核心功能：识别错题截图 → 自由标签分类 → 词库积累复用 → 二刷提醒 → 导出 Excel。 触发关键词：做了题、错了、截图发来、导出错题、待二刷、记得、不记得、换考试。 图片消息直接触发识别。 | |
| smart-control-skill Control smart home devices configured in Smart Plus APP. Use when you need to: (1) Query devices and scenes (lights, AC, switches), (2) Control device power... | |
| Cypress Agent Skill Production-grade Cypress E2E and component testing — selectors, network stubbing, auth, CI parallelization, flake elimination, Page Object Model, and TypeScr... | |
| chatppt-agent 使用 ChatPPT CLI 命令行工具通过 AI 自动生成 PPT 演示文稿。适用场景：用户需要根据主题文字或现有文件（Word/PDF/Markdown）生成 PPT 时触发本 skill。支持登录认证、PPT 生成、文件导入生成、结果查询等完整流程。 | |
| Catallax Interact with the Catallax decentralized contract work protocol on Nostr. Use when the user mentions tasks, bounties, contract work, arbiters, escrow, labor market, gigs, or Catallax. Supports browsing open tasks, creating task proposals, d | |
| Gmail OAuth Setup Set up Gmail API access via gog CLI with manual OAuth flow. Use when setting up Gmail integration, renewing expired OAuth tokens, or troubleshooting Gmail authentication on headless servers. | |
| Figma Interact with Figma files to read structure, export layers as images, and retrieve comments using the Figma REST API with authentication. | |
| Notion 2025 API Skill Query, create, and manage Notion databases and pages using the 2025-09-03 API format. Use when: (1) querying or filtering database entries via data_source_id... | |
| OpenCC Chinese character conversion between Simplified/Traditional and regional variants. Use when Pi needs to convert Chinese text with precision and awareness of... | |
| Pi Workflow Orchestration Workflow orchestration for Pi's task management, self-improvement, and code quality standards. Use when starting new projects, managing multi-step tasks (3+... | |
| Traditional Chinese Dictionary Query Traditional Chinese dictionaries from Ministry of Education (MOE) Taiwan. Supports looking up word definitions from the "國語辭典簡編本" (Concised Mandarin Di... | |
| PizzINT Monitor 实时监测五角大楼披萨店活跃度，预测地缘政治紧张与军事行动风险的披萨指数工具。 | |
| Trump Tback 基于文本与互动数据的特朗普情绪T-Back分析，区分成就宣传、威胁攻击和中性内容，评估市场情绪动能。 | |
| Us Treasury Radar Provides real-time US Treasury debt and foreign holding data analysis, detecting risk signals like "Davidian double kill" for informed investment decisions. | |
| docx-pdf-knowledge-parser Parse local `.docx` and `.pdf` files into structured knowledge artifacts with detailed reports, tracking successes, failures, and summaries without auto-writ... | |
| Feishu Knowledge Ingest batch ingest feishu folders and single attachments into report-first knowledge artifacts. use when chatgpt needs to read a feishu directory or a single share... | |
| pyscripts-org Skill for agents managing terminal Python scripts, aiming to improve efficiency. Every .py file must have a summary block at the END of the file. Automatical... | |
| Flesh Renderer Immersive prose rendering engine for the "viết full" task. Reads Outline from vn-outline, transforms structured beats into visceral in-character prose using... | |
| Vn Write Guide Hướng dẫn toàn diện — giải thích how/why, sửa lỗi người dùng, tối ưu pipeline viết gốc & dịch thuật với bộ kỹ năng kb-vn. Version dành cho người đã biết basics. | |
| Vn NSFW Sensory Lexicon Vietnamese Sensory Vocabulary Engine for immersive narrative prose. Provides compound-phrase construction rules, anatomical synonym banks, fluid descriptors,... | |
| Lore filter - Anti Dump Info Living world filter for immersive prose. Reads lore from a lorebook (generated by vn-worldbuilding or any world bible), controls HOW lore seeps into prose —... | |
| Scene Blueprint Converts raw story ideas into structured, character-anchored scene outlines with authentic dialogue and mapped emotional beats for chapter planning. | |
| Perspective Control System Perspective Control System for novel immersive narrative. Enforces scene-level POV dominance, sensory anchoring, subjective filtering, hard-break transitions... | |
| Roleplay - Chat box Immersive character roleplay protocol for Vietnamese text-based experiences. Governs response formatting (narrative, dialogue, internal thought), character c... | |
| Dịch Truyện Dịch tiểu thuyết từ ngôn ngữ nguồn sang tiếng Việt bằng quy trình xử lý dữ liệu tuần tự. | |
| Nạp liệu Nạp liệu chuyển đổi từ bản clean (69c.txt / raw) sang bản 18+ (nl69.txt / erotic) bằng kỹ thuật "微加料" (small erotic additions). Giữ nguyên 100% plot và dialo... | |
| World Building Generates and updates a detailed, structured world bible for Vietnamese text stories, building and maintaining lore with cross-references and open mysteries. | |
| Movedone Manage Movedone kanban projects, columns, tasks, comments, and task links via the local HTTP API. | |
| sutrena Deploy websites, landing pages, forms, and dashboards instantly — no git, no hosting, no build step. Use when the user wants to publish a page, create a land... | |
| Phenosnap Phenotype Extractor Extract clinical phenotypes and medication entities from user-provided text using PhenoSnap, producing a timestamped JSON output. | |
| consensus-agent-action-guard Pre-execution governance for high-risk agent actions. Uses persona-weighted consensus to decide ALLOW/BLOCK/REQUIRE_REWRITE before external or irreversible s... | |
| consensus-code-merge-guard Persona-weighted merge governance for AI-assisted engineering. Evaluates PR risk (tests, security markers, reliability signals), returns MERGE/BLOCK/REVISE d... | |
| consensus-deployment-guard Pre-deployment governance for release and infrastructure rollout requests. Use when an agent or workflow proposes shipping code/config/infrastructure changes... | |
| consensus-engineer AI solution architect for consensus-tools. Interactive multi-step skill that analyzes your project, recommends consensus-tools integration, scaffolds setup,... |
44,001–44,050 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.