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 |
|---|---|
| Bitget Poolx Monitor Monitor Bitget PoolX for new staking projects using r.jina.ai to bypass Cloudflare. Detect ETH, BTC, SOL and other pool launches. | |
| Web Scraper Jina Bypass Cloudflare and scrape any website using r.jina.ai API. Works on sites with strong protection like Truth Social, Cloudflare Turnstile, etc. | |
| ItPay Use bundled ItPay services in OpenClaw | |
| NanoBanana PPT Skills 基于 AI 自动分析文档内容，智能规划并生成多风格高清 PPT 图片，支持可选转场视频和交互式播放体验。 | |
| Tokopedia Unofficial MCP Skill Use Tokopedia MCP tools to find, compare, and evaluate products, reviews, and shops for informed online shopping decisions. | |
| Musicbrainz Importer Look up and add music metadata on MusicBrainz. Use when asked to check if an artist, album, or release exists on MusicBrainz, find MusicBrainz entries linked... | |
| Aha Claudecode Omc Claude Code+OMC orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, rese... | |
| Aha Codex Omx Codex+OMX orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded native subagents with runtime-resolved OMX roles... | |
| Aha Opencode Omo OpenCode+OMO orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, researc... | |
| Aha Orch Xx Runtime-neutral orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, rese... | |
| Aha Skills Finder Use when an agent needs to surface skill/capability candidates that first-pass registry, package, or search queries would likely miss. Covers skills, MCPs, C... | |
| Bigdeal Supplier Finder Use when an agent needs to create an evidence-bound supplier discovery report for a product or sourcing brief, especially for global buyers, cross-border eco... | |
| Agent Council Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization. | |
| Helius API Query Solana data via the Helius API. Use when the user asks about Solana wallet balances, token holdings, NFT holdings, transaction history, transfer activity, wallet identity/labels, wallet funding sources, parsing transactions, or other | |
| WhatSync WhatsApp for Claude, ChatGPT or any AI agent. Search chats, see who is waiting for a reply, and send messages from personal WhatsApp or the official Business API. | |
| Indices Use this skill for any operation with the Indices CLI — authentication, tasks, runs, and secrets. | |
| Skill Defender Scans installed OpenClaw skills for malicious patterns including prompt injection, credential theft, data exfiltration, obfuscated payloads, and backdoors. Use when installing new skills, after skill updates, or for periodic security scans. | |
| dgent De-agent your code. Run dgent to check files and commit messages for AI tells before committing — flags naming patterns, catch-rethrow, AI vocabulary, emoji,... | |
| Transcribee 🐝 Transcribe YouTube videos and local audio/video files with speaker diarization. Use when user asks to transcribe a YouTube URL, podcast, video, or audio file. Outputs clean speaker-labeled transcripts ready for LLM analysis. | |
| Create Content Thinking partner that transforms ideas into platform-optimized content | |
| Daily Review Ritual End-of-day review to capture progress, insights, and plan tomorrow | |
| De-AI-ify Remove AI-generated jargon and restore human voice to text | |
| Journal to Post Convert personal journal entries into shareable social media posts | |
| Plan My Day Generate an energy-optimized, time-blocked daily plan | |
| Thinking Partner Collaborative thinking partner for exploring complex problems through questioning | |
| Weekly Synthesis Create a comprehensive synthesis of the week's work and thinking | |
| PayLobster Agent payment infrastructure on Base. Trustless escrow, agent treasury, token swaps, cross-chain bridges, fiat on/off ramp, on-chain identity & reputation, s... | |
| Japanese Translation And Tutor Japanese-English translator and language tutor. Use when: (1) User shares Japanese text and wants translation (news articles, tweets, signs, menus, emails). (2) User asks "what does X mean" for Japanese words/phrases. (3) User wants to lear | |
| UI/UX Design Guide Expert guidance on mobile-first UI/UX design, color systems, typography, accessibility (WCAG 2.2), Tailwind + Shadcn/ui integration, micro-interactions, and... | |
| Backtest Expert 0.1.0 Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies... | |
| Elite Longterm Memory 1.2.3 Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib... | |
| N8n Workflow Automation 1.0.0 Designs and outputs n8n workflow JSON with robust triggers, idempotency, error handling, logging, retries, and human-in-the-loop review queues. Use when you... | |
| Playwright Mcp 1.0.0 Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automat... | |
| Playwright Scraper Skill 1.2.0 Playwright-based web scraping OpenClaw Skill with anti-bot protection. Successfully tested on complex sites like Discuss.com.hk. | |
| Polymarketodds 1.0.0 Query Polymarket prediction markets - check odds, trending markets, search events, track prices and momentum. Includes watchlist alerts, resolution calendar,... | |
| Pattern Automates jewellery product marketing using Google Vertex AI (Gemini and Imagen) and Google Drive. | |
| Nash0 Polymarket CLI Use the Polymarket CLI (`polymarket`) to browse markets, inspect order books and prices, check public wallet data, review account state, and place or cancel... | |
| Tandoor Recipe Manage recipes, meal plans, and shopping lists in Tandoor Recipe Manager. Use when the user wants to create recipes, plan meals, search for recipes, or manage their shopping list. | |
| Audit Code Security-focused code review for hardcoded secrets, dangerous calls, and common vulnerabilities | |
| Scan Skill Deep security analysis of an individual skill before installation | |
| Vet Repo Scan repository agent configuration files for known malicious patterns | |
| Agent Caps Define, validate, and audit agent capability manifests for safe skill installation | |
| Agent Cost Tracker Track LLM API spending per agent/session with budget alerts and CSV export | |
| Agent Guardrails Pre-flight safety check for a planned agent action (deny destructive/exfil, warn irreversible). Stdlib. | |
| Agent Health Monitor agent endpoints, check liveness, collect metrics, alert on failures | |
| Agent Logger Analyze agent run logs for errors, token spikes, and failures. Stdlib, offline. | |
| Agent Sentinel Scan OpenClaw/Hermes skills for risky permission patterns before installation | |
| Airtable Cli Read, create, update, delete, and search Airtable records. List bases and tables, filter records, and batch upsert. | |
| Arxiv Search Search arXiv papers by keyword, author, category with full-text download and citation export | |
| Ascii Art Creator Generate banners, boxes, cowsay-style art, tables, and image-to-ASCII with multiple fonts |
38,701–38,750 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.