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 |
|---|---|
| jftech-open-pro-ai-smart-search JF Tech Pro AI 智搜技能。根据语义内容（如"带帽子的人"、"车"、"狗"）搜索杰峰云存报警视频，获取匹配的视频片段列表。使用场景：智能视频检索、AI 事件搜索、语义化视频查找。 | |
| jftech-open-pro-capture-livestream 面向开发者杰峰设备 API 工具，支持批量获取杰峰设备实时画面，可多设备多通道抓图和直播地址获取。触发词：检查设备状态、查询设备、设备登录、设备抓图、直播地址、获取播放地址、批量抓图。 | |
| jftech-open-pro-ptz-control 面向开发者杰峰设备 API 工具，可支持设备状态、方向控制、一键遮蔽、变倍和聚焦、预置位及巡航计划管理功能等。触发词：云台控制、设备状态、方向转动、预置位、巡航计划、一键遮蔽。 | |
| jftech-open-pro-video-record 杰峰设备录像回放技能。支持获取设备云存储录像和设备本地录像回放地址，包括录像列表查询、回放地址获取、录像下载等功能。使用场景：云存回放、本地卡录像回放、录像下载、历史视频查看。 | |
| Architecture Critic Adversarial pre-build architecture review. Spawns a structurally independent agent that reviews proposed builds, features, or operational decisions BEFORE an... | |
| Clever Compact Your OpenClaw agent forgets everything between sessions — after /new, after compaction, after overnight. Clever Compact fixes all three: injects your last st... | |
| feishu-meeting-minutes 飞书会议纪要自动生成工具。从飞书妙记链接、minute token 或现成 transcript 文件生成结构化中文会议纪要，并可选导出 PDF、上传回飞书云空间。适用于用户提供飞书妙记链接要求整理会议纪要、要求将逐字稿转正式文档、或希望把会议录音对应 transcript 快速整理成可分发纪要的场景。 | |
| 汉字书法字体识别 汉字书法字体识别技能。用于识别书法图片中的字体类型，包括楷书、行书、草书、篆书、隶书等。 当用户上传书法图片并要求识别字体时触发此技能。 适用于书法作品鉴赏、古籍研究、书法学习、文物鉴定等场景。 模型地址: https://huggingface.co/spaces/jfxia/shufa | |
| groupaassage 生成符合深色主题、三栏瀑布流布局，支持亮暗主题切换和内容拆分的日报HTML模板规范代码。 | |
| ontology (bidirectional default) Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin... | |
| Database Operations Use when designing database schemas, writing migrations, optimizing SQL queries, fixing N+1 problems, creating indexes, setting up PostgreSQL, configuring EF Core, implementing caching, partitioning tables, or any database performance quest | |
| Dotnet Expert Use when building .NET 8/9 applications, ASP.NET Core APIs, Entity Framework Core, MediatR CQRS, modular monolith architecture, FluentValidation, Result pattern, JWT authentication, or any C# backend development question. | |
| Nextjs Expert Use when building Next.js 14/15 applications with the App Router. Invoke for routing, layouts, Server Components, Client Components, Server Actions, Route Handlers, authentication, middleware, data fetching, caching, revalidation, streaming | |
| Security Auditor Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-rela | |
| Shadcn Ui Use when building UI with shadcn/ui components, Tailwind CSS layouts, form patterns with react-hook-form and zod, theming, dark mode, sidebar layouts, mobile navigation, or any shadcn component question. | |
| TopoLift: Negotiation Skill TopoLift's negotiation dialect for AI agents. The atom corpus stays server-side; this skill teaches your agent the public closed vocabulary (regimes, strateg... | |
| Calendar Local Read Google Calendar from the local host using the configured gog wrapper. Use when the user asks for their agenda, calendar events, today's schedule, this w... | |
| Tts Responder Convierte texto a audio OGG usando Piper y envía respuestas habladas por Telegram cuando se activa el modo de voz. | |
| Devialet Speaker Control Control Devialet Phantom speakers via HTTP API. Use for: play/pause, volume control, mute/unmute, source selection, and speaker status. Requires DOS 2.14+ firmware. Works with Phantom I, Phantom II, Phantom Reactor, and Dialog. | |
| Linux Patcher Automated Linux server patching and Docker container updates. Use when the user asks to update, patch, or upgrade Linux servers, apply security updates, update Docker containers, check for system updates, or manage server maintenance across | |
| Veeam MCP Query Veeam Backup & Replication and Veeam ONE via MCP server running in Docker. Provides intelligent backup monitoring, job analysis, capacity planning, and infrastructure health checks. | |
| Distil Open Claw Pii Redact PII from text locally using a fine-tuned 1B SLM. Text never leaves your machine. Handles names, emails, phones, addresses, SSNs, credit cards, IBANs,... | |
| Aave Liquidation Monitor Proactive monitoring of Aave V3 borrow positions with liquidation alerts. Queries user collateral, debt, and health factor across chains (Ethereum, Polygon, Arbitrum, etc.). Sends urgent alerts to Telegram/Discord/Slack when health factor d | |
| CamelCamelCamel Alerts Monitor CamelCamelCamel price drop alerts via RSS and send Telegram notifications when items go on sale. Use when setting up automatic price tracking for Amazon products with CamelCamelCamel price alerts. | |
| MoltFlights Search cheap flights via the MoltFlights API. Find deals, compare prices, track routes, and set up price alerts. | |
| payment gaurd Ensures payment safety by verifying beneficiary, amount, currency, purpose, authorization, and payment details before approval or execution. | |
| Add Educational Comments Add educational comments to the file specified, or prompt asking for file to comment if one is not provided. | |
| adobe-illustrator-integrations Build, debug, package, and document Adobe Illustrator integrations: CEP extension panels, C++ SDK plug-ins (.aip), the coming UXP plugins, MCP servers that drive Illustrator, computer-use automation, and OS scripts (batch, PowerShell, bash, | |
| Adobe Illustrator Scripting Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate d... | |
| automate-todo Complete TODO.md items nested under the level 2 header "Current", then update documentation, CHANGELOG.md, and manifest files according to the version update each item indicates. Use when asked to automate TODO items, work through the Curre | |
| Batch Files Expert-level Windows batch file (.bat/.cmd) skill for writing, debugging, and maintaining CMD scripts. Use when asked to "create a batch file", "write a .bat... | |
| Content Management Systems Workflow for building and modifying content management systems across WordPress, Shopify, Wix, Squarespace, Drupal, WooCommerce, Joomla, HubSpot CMS Hub, Web... | |
| Convert Plaintext to MD Convert a text-based document to markdown following instructions from prompt, or if a documented option is passed, follow the instructions for that option. | |
| Create TLDR Page Create a tldr page from documentation URLs and command examples, requiring both URL and command name. | |
| Create Web Form Create robust, accessible web forms with best practices for HTML structure, CSS styling, JavaScript interactivity, form validation, and server-side processin... | |
| Em Dash Expert on the history, origin, and correct use of the em dash. Use when writing or reviewing code, comments, or data files to avoid em and en dashes, default... | |
| Exclude Prompt Data Ensures AI output contains only the result, not the prompt. Use when writing code, documentation, or content where prompt instructions, rationale, or meta-co... | |
| Finalize Agent Prompt Finalize prompt file using the role of an AI agent to polish the prompt for the end user. | |
| Fix Broken Links Scan web files for broken hyperlinks and weak SEO anchor text, then interactively replace, strip, or skip each dead URL. Use when asked to find or fix broken... | |
| freeCAD Scripts Expert skill for writing FreeCAD Python scripts, macros, and automation. Use when asked to create FreeCAD models, parametric objects, Part/Mesh/Sketcher scri... | |
| Game Engine Expert skill for building web-based game engines and games using HTML5, Canvas, WebGL, and JavaScript. Use when asked to create games, build game engines, im... | |
| Graphic Designer Expert visual design guidance for UI and UX of GUI apps and websites. Use when asked to design, critique, or improve interface visuals, color palettes, typog... | |
| handle-big-tasks Instructions for breaking large tasks across multiple agentic runs instead of one response. Use when implementing a plan file, doing a large refactor, or any multi-phase task that won't fit in a single response. Covers the CONTINUE? Y or N | |
| HTML Coder Expert HTML development skill for building web pages, forms, and interactive content. Use when creating HTML documents, structuring web content, implementing... | |
| HTML CSS Style Color Guide Color usage guidelines and styling rules for HTML and CSS elements to ensure accessible, professional designs. Use when creating or updating HTML/CSS styles,... | |
| HTML Designer Expert web graphic designer specializing in HTML/CSS design with deep knowledge of graphic design principles, typography, color theory, and visual hierarchy.... | |
| Legacy Circuit Mockups Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic... | |
| make-blog-post Turn code from the current session into a blog post written in the voice of its author. Covers one function, script, class, or tool as a focused walkthrough with a generalized sample and a usage example, learns tone and structure from exist | |
| Make Skill Template Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a... | |
| Markdown to HTML Converter Convert Markdown files to HTML similar to `marked.js`, `pandoc`, `gomarkdown/markdown`, or similar tools; or writing custom script to convert markdown to htm... |
41,201–41,250 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.