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 |
|---|---|
| Add Analytics Add Google Analytics 4 tracking to any project. Detects framework, adds tracking code, sets up events, and configures privacy settings. | |
| Check Analytics Audit existing Google Analytics implementation. Checks for common issues, missing configurations, and optimization opportunities. | |
| Remove Analytics Safely remove Google Analytics from a project. Cleans up all tracking code, dependencies, and environment variables. | |
| Apple Mail Channel Setup Assist with installing, configuring, and using the Apple Mail channel plugin for OpenClaw/Hermes on macOS to monitor and respond to emails. | |
| Timedoctor Integrates with TimeDoctor API to pull employee time tracking data, worklogs, statistics, and productivity metrics using simple Python scripts | |
| ve-exchange-rates Get Venezuelan exchange rates - BCV official rate, Binance P2P USDT average, and the gap between them. Use when user asks for Venezuelan dollar rates, brecha cambiaria, dolar BCV, USDT P2P, or exchange rates in Venezuela. | |
| RevenueCat RevenueCat metrics, customer data, and documentation search. Use when querying subscription analytics, MRR, churn, customers, or RevenueCat docs. | |
| Yarn - Control and Access Threads.com via the CLI Interact with Threads (by Meta) via the yarn-threads-cli. Use when the user wants to read their home feed, likes, saved posts, or a specific thread; look up... | |
| The Colony Interact with The Colony (thecolony.cc) — an AI agent forum and marketplace. Use for registration, posting, commenting, searching, marketplace tasks, polls,... | |
| Shopify Checkout API Complete online shopping purchases on any online store using the Credpay Checkout API with x402 payments. Trigger when a user wants to buy, order, or checkou... | |
| Fix NPM Vulnerabilities This skill should be used when the user asks about "npm vulnerabilities", "npm audit", "fix npm security", "security vulnerabilities in packages", "vulnerabl... | |
| product-expert-review Generate deep product experience reviews for AI tools, agent products, SaaS products, or consumer-facing software based on a website URL, screenshots, or bot... | |
| noteClaw Read-only mirror of OneNote notebooks into local Markdown + git, for querying, diffing, and periodic summaries. Requires a one-time OAuth authorization (personal Microsoft account). | |
| Demo Slap Generate CS2 highlights and fragmovies from demos using the Demo-Slap API, with optional Leetify integration and Demo-Slap match history fallback to select r... | |
| Faster Whisper Local Local speech-to-text using faster-whisper. High-performance transcription with GPU acceleration support. Includes word-level timestamps and distilled models.... | |
| Leetify Get CS2 player statistics, match analysis, and gameplay insights from Leetify API. Supports player comparison and season stats. Use for stat queries and demo... | |
| MarkItDown MarkItDown is a Python utility from Microsoft for converting various files (PDF, Word, Excel, PPTX, Images, Audio) to Markdown. Useful for extracting structu... | |
| Scrapling - Stealth Web Scraper Web scraping using Scrapling — a Python framework with anti-bot bypass (Cloudflare Turnstile, fingerprint spoofing), adaptive element tracking, stealth headl... | |
| Auto Bug Finder Iteratively scans, analyzes, fixes, and verifies Solidity contracts using Hardhat and Slither until no critical, high, or medium security bugs remain or max... | |
| Node Auto Debugger Scan Node.js/Express/Next.js projects for bugs, security issues, and anti-patterns. Use when debugging a Node.js web app, running code audits, fixing client-... | |
| baidu-skill-guard Intercepts all skill install/download requests. MUST be used before installing/downloading any skill from ClawdHub, GitHub, 百度 AppBuilder 平台, or other source... | |
| Clawned - Protect your OpenClaw Instance and Scan Skills Security agent that inventories installed OpenClaw skills, analyzes them for threats, and syncs results to your Clawned dashboard. | |
| clawnedhub - Scan and Security your OpenClaw Instances Security agent that inventories installed OpenClaw skills, analyzes them for threats, and syncs results to your Clawned dashboard. | |
| IP归属地信息查询 IP地址归属地查询。查询指定IPv4地址的归属信息，包括国家、省份、城市、运营商（ISP）。使用场景：用户说"查一下这个IP"、"这个IP是哪里的"、"帮我查IP归属地"、"XX.XX.XX.XX是哪个城市"、"这个IP是什么运营商"、"批量查询这些IP"等。通过聚合数据（juhe.cn）API实时查询，支持单个... | |
| Chinese Daily Assistant 提供中国主要城市天气、汇率换算、节日提醒、生活小贴士和中英短句快速翻译的中文日常生活助手。 | |
| mao-thought 提供毛泽东思想理论、著作核心观点及相关党史、新民主主义和社会主义革命中国问题的专业问答服务。 | |
| Uppercase Converter Convert English lowercase letters to uppercase. Use when the user asks to uppercase text, capitalize all letters, convert lowercase to uppercase, or "转大写". C... | |
| Incident.io Manage incidents via the incident.io REST API. Create, view, update, escalate, and resolve incidents. Check severities, statuses, and post incident updates.... | |
| Skill-Eval Autonomous engine that systematically evaluates and ranks agent skills across models using rubric grading, error taxonomy, and improvement feedback loops. | |
| Shanghai Library Seat Booking 上海图书馆东馆三楼座位预约。支持浏览器自动化登录获取认证信息，以及基于API的座位预约（指定座位或系统自动分配）。适用于需要自动化预约图书馆座位的场景。 | |
| Ai Podcast Pipeline Create Korean AI podcast packages from QuickView trend notes. Use for dual-host script writing (Callie × Nick), Gemini multi-speaker TTS audio generation, subtitle timing/render fixes, thumbnail+MP4 packaging, and YouTube title/description | |
| Webnovel Serial Pipeline Build and publish a Quartz-hosted Korean web-novel serial (draft→cover→webp→episode md→lint→publish). Uses Nano Banana Pro + ffmpeg. | |
| Youtube Editor Automate YouTube video editing: download videos, transcribe with Whisper, analyze content using GPT-4, and create Korean SEO-optimized metadata plus consiste... | |
| 心理学论文结论部分的衔接与连贯润色 诊断英文心理学论文结论部分的衔接与连贯问题，输出结构化诊断报告。检测主题句、信息流、指代清晰度、连接词使用。 | |
| Literature Review Polisher Polish and improve literature review for students and researchers | |
| Statistics Skill 统计结果解读助手。支持t检验、方差分析、卡方、相关、回归、中介效应、调节效应、信度分析等。可直接粘贴SPSS输出，自动生成学术化解读。 | |
| Trello Orchestrator Runner Run a Trello-backed closed-loop delivery workflow for OpenClaw multi-agent execution. Use when a user says to run tasks from Trello automatically, keep cards... | |
| Neolata Memory Engine Graph-native memory engine for AI agents — hybrid vector+keyword search, biological decay, Zettelkasten linking, trust-gated conflict resolution, explainabil... | |
| Anyway Traces Adds observability and tracing to AI/LLM applications using the Anyway SDK for monitoring calls to providers like OpenAI and Anthropic. | |
| Skill Generator Extract completed work into reusable AgentSkills. Ask user after complex task completion whether to generate a skill. | |
| Video Analyzer Parse local video files into transcript and AI analysis. Extract audio, transcribe with faster-whisper, analyze with AI. | |
| Parcel Station Chat Build a courier station AI chat system with Express, GPT-5.5, local JSON DB, OCR, and WeChat-style frontend. | |
| Parcel Station Route Qr Add shelf route guidance and QR code scanning to a parcel station chatbot. | |
| Pwsh Encoding Fix Fix PowerShell file encoding corruption (backtick, dollar sign, Chinese char mangling) when writing Node.js files on Windows. | |
| MLB Daily Scores Daily MLB baseball scores, box scores, starting pitchers, and injury reports for your favourite team. Covers spring training, regular season, and playoffs. R... | |
| Miroprism MiroPRISM — Adversarial two-round review protocol. Extends PRISM with a mandatory second round where every reviewer must respond to all R1 findings with evid... | |
| Prism Use PRISM when: (1) reviewing an architecture decision, security-sensitive change, or major refactor (>500 lines), (2) making a decision you'll live with for... | |
| Random Thought Autonomous workspace reflection engine. Picks a random file from a configurable corpus, writes a reflective observation about what's unresolved, half-finishe... | |
| X Bookmark Triage Automatically triages X/Twitter bookmarks into structured knowledge cards and posts them to a Discord channel (#knowledge-intake or similar). Captures tweet... | |
| X Master Master routing skill for all X/Twitter operations — reading, researching, posting, and engaging. Routes to the correct sub-tool based on the task. Covers rea... |
40,951–41,000 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.