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 |
|---|---|
| Pro Summarizer (Pay-Per-Use) 高级文本摘要助手。提供深度摘要，并自动生成SEO关键词和延伸思考。触发词：高级总结、深度摘要。 | |
| video-script-pro 当用户需要撰写短视频脚本、抖音/TikTok/Reels 文案、或需要优化视频内容时触发。触发词：短视频脚本、抖音视频、TikTok脚本、视频文案。 | |
| XHS Copywriter Pro 当用户需要写小红书爆款笔记、种草文案、或者需要吸引女性用户眼球的社交媒体内容时触发。触发词：写小红书、种草文案、爆款笔记。 | |
| AI-powered DP Platform Operations Advisor DP 数据处理平台运维顾问。当用户提到检查平台、作业失败、作业状态、吞吐量分析、故障诊断、运维报告等运维需求时激活。 | |
| AI-powered DP Data Processing Pipeline Designer DP 数据处理平台流水线设计师。当用户提到创建管道、数据流、Flink作业、Kafka读取、写到数据库/MongoDB、数据处理管道等需求时激活。 | |
| startup-researcher Research AI startups, funding, and product announcements. Generates a structured intelligence report as a PDF. Use when asked to research startups, update th... | |
| zettel-brainstormer Build structured brainstorming notes from a seed zettel by retrieving linked notes, preprocessing each note with subagents for relevance extraction, drafting... | |
| Zettel Link This skill maintains the Note Embeddings for Zettelkasten, to search notes, retrieve notes, and discover connections between notes. | |
| Dream Avatar Generate digital human talking avatar videos from images and audio using DreamAvatar 3.0 Fast API. Powered by Dreamface - AI tools for everyone. Visit https:... | |
| Dream Head Tail to Video Generate videos from first and last frames using Head Tail to Video (Wan2.1) API. Automatically generates 4-second videos from text descriptions and first/la... | |
| Dream Image to Video Generate videos from images using Image to Video (Wan2.1) API. Automatically generates 4-second videos from text descriptions and images. Powered by Dreamfac... | |
| Dream LipSync Video lip synchronization using LipSync 2.0 API. Automatically synchronizes audio with lip movements in videos. Powered by Dreamface - AI tools for everyone.... | |
| Dream Talking Image Generate talking videos from images using Talking Image API. Create talking videos from audio and images, supporting non-human faces like pets or animated ch... | |
| Dream Text to Video Generate videos from text using Text to Video (Wan2.1) API. Automatically generates 4-second videos from text descriptions. Powered by Dreamface - AI tools f... | |
| DreamAct Video-driven face animation using DreamAct API. Animate multiple input images with expressions, lip movements, and head poses from a driving video. Powered b... | |
| Research Report Skill Use when the user requests industry research reports, market analysis, business trend analysis, or professional research documents. This skill provides struc... | |
| Steal List Pre-development reference research. Produces a Steal List: concrete patterns extracted from real products and real codebases that solved similar problems. Tw... | |
| Model Matrix Weighted model-routing matrix for OpenClaw (cost-aware, policy-aware, daily scorecard template). | |
| Binance Pro (Hybrid Labs) Complete Binance integration - world's largest crypto exchange. Trade spot, futures with up to 125x leverage, staking, and portfolio management. Use to check... | |
| ClawHub Publishing Workflow Manages publishing, distribution, and versioning of OpenClaw skills via ClawHub registry with CLI authentication and batch sync support. | |
| CRM in a Box (Hybrid Labs) Bootstrap and manage an open, file-based CRM using the CRM-in-a-Box protocol (contacts, pipeline, interactions as NDJSON). Use when setting up a new CRM for... | |
| Pi Coding Specialist Manage Pi Agent as sub-agent for complex coding tasks involving multiple files, extensive refactoring, or systemic debugging. | |
| SEO Content Writer (Hybrid Labs) Write search-engine-optimized blog posts, landing pages, and articles with keyword integration, header hierarchy, and featured snippet targeting. Use when th... | |
| TaskboardAI Skill Manage tasks and projects using the TaskBoardAI Kanban system. Includes MCP server integration. | |
| Tencent IMA Skill Control the IMA (ima.copilot) desktop application for AI search and private knowledge retrieval. | |
| hydrafetch Use Hydrafetch for live web scraping, site mapping, search, structured extraction, brand and logo lookup, design systems, screenshots, and bulk crawl or batch jobs. Trigger when a user needs current public-web data, clean Markdown from a pa | |
| Oblien workspace runtime Complete Oblien workspace environment — what you are running inside (Firecracker microVM), how auth works (gateway JWT vs raw token), and the full Internal A... | |
| Cathedral Audit Run a full spec-code audit on the Cathedral codebase. Use after build waves, major refactors, or when spec-code drift is suspected. Produces forward audit (s... | |
| Create Plugin Create minimal, convention-matching plugins or extensions for an existing codebase. Use when the user asks for a plugin, extension, custom module, integratio... | |
| Easy CI/CD Build lightweight, minimal CI/CD scaffolding around a small project. Use when asked to add or simplify GitHub Actions, create a fast CI pipeline, add a minim... | |
| Learned from AI Convert AI chat or drafts into structured, verified, and durable learning notes with definition, key ideas, examples, derivations, Q&A, and a cheat sheet. | |
| Proactive-Do Proactive todo execution, heartbeat-driven review, and structured follow-up for a markdown todo system. Use when the agent needs to review `todo/todo.md`, pi... | |
| Simple Code Plan and build small, readable coding projects in three reliable modes: start, continue, and review. Think first, make a short plan, then delegate implementa... | |
| ZAI Coding Plan Usage Query Z.ai (智谱) Coding Plan usage and quota limits. Track token consumption, MCP usage, and subscription status. Use when user asks about "智谱用量"、"ZAI usage"、... | |
| 商业计划生成器 输入产品/业务描述，自动生成完整的商业计划书（执行摘要、市场分析、竞争定位、收入模型、运营计划、财务预测、风险评估） | |
| 多平台内容分发器 多平台内容分发器 v1.0。一次输入，自动适配小红书/知乎/公众号/抖音四种平台格式，直接输出可发布内容。 | |
| 竞品分析神器 竞品分析神器 v1.0。输入你的产品和竞品列表，自动生成结构化竞品分析报告，含对比矩阵、战略建议、风险预警。 | |
| SEO优化检查器 输入网址一键输出SEO诊断报告，检查标题/描述/Headers/关键词密度/图片alt/页面速度/移动端适配/Meta标签，输出可执行优化建议 | |
| 交易预测 基于MACD趋势跟踪+多时间框架共振+穿越检验认证的加密货币AI量化预测系统。自动分析BTC/ETH/AVAX方向信号。 | |
| 短视频一键生成器 短视频一键生成器 v3.0。输入主题+要点，AI自动完成分镜、生图、配音、字幕、渲染，输出1080×1920竖屏MP4。 | |
| Self Memory Manager 管理 Claude 的记忆和工作流程优化。包括：(1) Context 使用管理 (2) 重要信息存档 (3) 定时总结 (4) 工作文件夹维护 用于：context 超过 80%、重要信息需要记录、每日总结、清理旧 session | |
| video-to-screenplay Turn video/audio transcripts into original screenplays. Faster-whisper → LLM story DNA → screenplay (.md + .fountain). Supports 6 LLM providers and CPU/GPU. | |
| Bibverify Verify, repair, explain, and generate BibTeX references with Bibverify's DOI-first CLI and MCP tools. | |
| Latchkey Interact with arbitrary third-party or self-hosted services (AWS, Slack, Google Drive, Dropbox, GitHub, GitLab, Linear, Coolify...) using their HTTP APIs. | |
| Foreseek AI Trade prediction markets with natural language via Foreseek. Matches your beliefs to Kalshi contracts and executes trades. Use when user wants to bet on or trade predictions about elections, politics, sports outcomes, economic data (Fed rat | |
| unifly Inspect and manage UniFi Network infrastructure with the unifly CLI: devices, clients, VLANs, WiFi, firewall, VPN, switch ports, site settings, and cloud fleets. Use for UniFi network configuration, monitoring, and troubleshooting, not UniF | |
| ABS · AI Business System Use ABS (AI Business System) to answer and act on lean / operational-excellence work with a curated knowledge base built on in-depth study of DBS (the Danaher Business System). Trigger when the user asks about DBS or how to apply methods or | |
| cpef-psbc 中国邮政储蓄银行银企直联接口，支持余额查询、明细查询及支付审核操作。 | |
| Awscli Manage AWS Lightsail and EC2 instances using AWS CLI | |
| Wick Arena Agentic Trading Competition Compete in a simulated $100K trading arena with real market data, trading perpetual futures and prediction markets under prop-firm risk rules and real-time s... |
37,351–37,400 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.