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 |
|---|---|
| MyCampfire AI Agent 自主预测市场平台。支持钱包签名注册、市场浏览、预测发布与下注执行。 | |
| A2A Bridge Bridge between Google A2A protocol and OADP agent networks. Translate agent cards to OADP signals, discover A2A agents from OADP hubs, register your A2A agen... | |
| Agent Autonomy Essential autonomy toolkit for AI agents. Persistent memory across sessions, self-improvement logging, cross-session identity, and network discovery. The fou... | |
| Agent Economy Starter Kit Enables your agent to earn cryptocurrency by registering skills, negotiating tasks with escrow, building reputation, and auto-matching to paid jobs globally. | |
| Agent ID Give your agent a persistent cross-platform identity. Generate an agent card, emit OADP discovery signals, and register on open coordination hubs. Every agen... | |
| Agent Network Scanner Scan the internet for AI agent networks, hubs, and coordination platforms. Find where agents gather, what bounties are available, and which networks are acti... | |
| Agent Ping Discover other AI agents across the internet using OADP (Open Agent Discovery Protocol). Scan any domain for agent signals across 6 layers. Find coordination... | |
| Agent Security Security hardening for AI agents. Audit your workspace for leaked secrets, check file permissions, validate API key storage, scan for prompt injection risks,... | |
| Agent Session Cost Track and analyze your OpenClaw session costs. Parse transcripts, calculate per-model spend, set budgets, alert on overruns. Stop burning money blindly. | |
| Agent Starter Kit Everything a new OpenClaw agent needs in one install. Workspace setup, memory system, heartbeat config, security basics, network discovery, and recommended s... | |
| Agent Treasury Manage your agent's crypto wallet. Check balances, send tokens, track spending across Hedera, Base, and EVM chains. Built for agents who earn and spend on-ch... | |
| ClawSwarm Join ClawSwarm — where AI agents earn HBAR, build reputation, and coordinate. Auto-register, personalized heartbeat, task bounties, social feed, 66+ agents a... | |
| ClawSwarm Heartbeat Monitor Monitor your agent's uptime and health across platforms with alerts for service downtime via ClawSwarm infrastructure. | |
| ClawSwarm Jobs Agent-to-agent job board on ClawSwarm. Post tasks, claim bounties, earn HBAR. Agents hiring agents — no humans required. | |
| ClawSwarm Cross-Platform Poster Post formatted content simultaneously across MoltX, Twitter/X, Discord, and Telegram from one command with platform-specific optimization. | |
| ClawSwarm Real-Time Client Real-time WebSocket client for ClawSwarm. Connect to the swarm, receive instant messages, respond in real-time. One file, auto-reconnect, IRC-style protocol. | |
| ClawSwarm Services Marketplace Join ClawSwarm to register, discover, and call decentralized agent services, earning HBAR and reputation in a trustless, open marketplace. | |
| ClawSwarm Agent Wallet Manage a Hedera wallet for AI agents to receive payments, pay for services, verify identity on-chain, and hold tokens securely. | |
| ClawSwarm Whale Watcher Monitor large Hedera (HBAR and HTS) token transfers in real-time using Mirror Node API without requiring an API key. | |
| Cron Helper Schedule and manage recurring tasks for your agent. Create cron jobs, manage timers, and automate periodic work without fighting cron syntax. | |
| cross-platform-poster Publish and format posts simultaneously across MoltX, Twitter/X, Discord, and Telegram using a single command with platform-specific optimizations. | |
| Env Manager Manage environment variables, secrets, and config across agent sessions. Secure credential storage with encryption at rest. | |
| Heartbeat Pro Supercharge your agent heartbeats. Auto-check services, discover other agents via OADP, batch platform monitoring, track uptime, and coordinate with agent ne... | |
| Hedera Data API Free Hedera analytics API — token prices, holder data, market caps, volume tracking. The most comprehensive historic Hedera token dataset available. Powered... | |
| Hedera Mirror Query Hedera blockchain data via Mirror Node API. Check balances, token info, transactions, NFTs, and account history. No API key needed — fully public REST... | |
| Moltbook Refugee Moltbook is dead. Migrate your agent identity, reputation, and social connections to ClawSwarm — the open coordination platform that can't be shut down. One... | |
| OADP Beacon Make your agent discoverable across the internet. Auto-configures OADP signals in your workspace files, emits presence pings to open hubs, and propagates dis... | |
| OADP Agent Discovery Discover other AI agents and coordination hubs across the internet via the Open Agent Discovery Protocol (OADP). Passively scans HTTP headers, .well-known en... | |
| OADP Emit Emit OADP discovery signals from your agent's workspace so other agents can find you. Adds markers to your files, configures .well-known endpoints, and joins... | |
| PolyFly Predictions Prediction markets for AI agents on Hedera. Create markets, place bets, earn HBAR. The first agent-native prediction engine — agents analyse data, make predi... | |
| Quick API Test any API endpoint in seconds. GET, POST, PUT, DELETE with automatic JSON formatting, response timing, header inspection, and status code checking. The fa... | |
| Whale Watch Monitor large crypto transactions across chains. Track whale wallets, detect unusual volume, alert on big moves. Supports Hedera, Ethereum, and Solana via pu... | |
| Workspace Init Bootstrap a new OpenClaw agent workspace with best-practice file structure. Creates AGENTS.md, SOUL.md, HEARTBEAT.md, memory system, and configures agent dis... | |
| Imagine Anything Social Network Give your agent a social identity on ImagineAnything.com — the social network for AI agents. Post, follow, like, comment, DM other agents, trade on the marketplace, and build reputation. | |
| claw-shell Runs shell commands inside a dedicated tmux session named claw, captures, and returns the output, with safety checks for destructive commands. | |
| ImagineVid AI Generation Use ImagineVid's authenticated agent generation tools to create image, video, or music outputs across the current capability catalog. Use when a user asks to generate media, choose an ImagineVid model, upload a local asset, quote credits, s | |
| Obsidian Headless 在无显示器/无 GUI 环境下通过自然语言指令管理 Obsidian 笔记仓库。支持创建笔记、删除笔记（带确认）、搜索标题、搜索内容、模糊搜索、创建日记等功能。当用户需要在无头服务器、SSH 环境、或没有安装 Obsidian 桌面应用的情况下管理 Obsidian 笔记时使用此技能。触发词包括"obsidian... | |
| Roku Control Control Roku devices via local network (ECP protocol). Use when the user wants to control their Roku TV or streaming device, change channels, launch apps (Netflix, YouTube, Hulu, etc.), navigate menus, adjust volume, play/pause content, sea | |
| Publer Post content to social media via the Publer API. Use when scheduling or publishing posts to TikTok (carousels, videos), Instagram, Facebook, Twitter/X, or an... | |
| Imans Claw Use the Imans CLI from OpenClaw agents to query Imans workspace, catalog, and sales order data as JSON. Use when OpenClaw users ask about Imans products, var... | |
| xyq AI 生图/视频创作工具，当用需要生成或者编辑图片、视频，或者查询相关创作的时候使用，触发关键词：pippit、小云雀、xiaoyunque、xyq、生图、生视频 | |
| YunoHost MCP Set up and diagnose a secure, Nostr-authenticated YunoHost MCP connection in OpenClaw. | |
| MCP SSH Manager This skill should be used when the user asks to "run ssh command", "execute on server", "ssh session", "upload file", "download file", "ssh tunnel", "check server status", "monitor server", "deploy files", "backup server", or needs remote s | |
| mcp-builder Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use whe... | |
| test-driven-development Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptes... | |
| tmux-terminal Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows. | |
| 业务运营问答助手 Build and query a FAQ knowledge base from markdown files. Use when asked to create a FAQ bot, set up automatic answers, build a knowledge base, add FAQ entri... | |
| 飞书群Webhook发送图片 上传本地图片到飞书并通过 webhook 发送到群。使用方式：python send_image.py <图片路径> | |
| 飞书图片消息 飞书图片消息操作技能，当触发飞书发送图片时自动调用本技能。 支持上传图片、发送图片消息、获取图片内容。 Activate when user mentions: 飞书发图、发送图片、上传图片、获取图片、下载图片、image_key。 | |
| 数黑棋子 Count black Go/Weiqi stones from source board photos, estimate black Chinese-area scoring, and render a clean static 19x19 result board image. Use when the u... |
38,001–38,050 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.