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 |
|---|---|
| Xiaozhi Mcp Openclaw Official 按小智官方 MCP 接入方式，把小智 AI 设备通过 MCP 接到 OpenClaw / OpenAI-compatible 后端。适用于已经有小智 MCP 接入点（wss://api.xiaozhi.me/mcp/?token=...）的场景。提供一个 `openclaw_query(message)` MCP... | |
| Claw Smart Context Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation | |
| Project Context Sync Automatically updates PROJECT_STATE.md after each commit with recent git info and optional AI-generated summaries to track project status and next steps. | |
| Smart Context Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation | |
| Agent Deploy Deploy a new isolated OpenClaw agent with its own Telegram bot, workspace, and session storage. Use when user asks to create a new agent, add a new bot, or s... | |
| CXM: Neural Memory for Agents Use this skill when you need to understand the architecture of a codebase, perform semantic searches across files, map dependencies before refactoring, or in... | |
| Joe's Markdown to DOCX Converter Convert Markdown files to fully formatted Word DOCX documents with support for tables, images, code blocks, and GitHub Flavored Markdown features. | |
| Trein Query Dutch Railways (NS) for train departures, trip planning, disruptions, and station search via the trein CLI. | |
| Bring! Shoppinglist Manage Bring! shopping lists via CLI to add, remove, complete, and view items or lists using the Bring! API. | |
| Local Inference Context Context management for self-hosted LLM backends (llama.cpp, Ollama). Prevents mid-task 503 errors and context overflows caused by VRAM-limited KV caches. Use... | |
| ai视频人物真实性方法论 提供AI视频创作全流程方法论，涵盖专业电影运镜技巧、情绪表达、皮肤真实感提示词及实战案例指导。 | |
| Satori Persistent long term memory for for continuity in ai sessions between providers and codegen tools.
TRIGGERS - Activate this skill when:
- User explicitly mentions "satori", "remember this", "save", "add", "save this for later", "store thi | |
| Kagi Enrich Search Kagi's unique non-commercial web (Teclis) and non-mainstream news (TinyGem) indexes for independent, ad-free content you won't find in regular search... | |
| Kagi Fastgpt Ask questions and get AI-synthesized answers backed by live web search, via Kagi's FastGPT API. Returns a direct answer with cited references. Use when you n... | |
| Kagi Summarizer Summarize any URL or text using Kagi's Universal Summarizer API. Supports multiple engines (including the enterprise-grade Muriel model), bullet-point takeaw... | |
| ClawDex Trading Trade tokens on Solana using the ClawDex CLI. Use when the user asks to swap tokens, check balances, get quotes, or manage a Solana trading wallet. | |
| developer-self-improve-core 开发者自改进核心技能 - 自动错误防重、自检、规则生成、记忆清洗、定时提醒 核心功能： - 每轮回答前：自动错误防重 - 每轮回答后：自动自检 + 生成规则草案 - 累计 10 轮对话/每周：自动记忆清洗扫描 - 自动提醒：每天 9:30 钉钉推送待确认规则 核心原则： - AI 只提议，人类终审 - 绝不自动写... | |
| ios-self-improve iOS 开发自改进技能 - Swift/ObjC 规范、审核合规、崩溃预防、自动自检、Xcode、UIKit、SwiftUI | |
| sandbase Safely use or set up the SandBase MCP server in Antigravity, Trae, Qoder, WorkBuddy, or Pi. Use when a user asks one of these clients to use SandBase, connect SandBase, install or configure the SandBase MCP, diagnose whether SandBase is con | |
| Adaptive Routing Routes LLM requests to a local model first (Ollama, LM Studio, llamafile), validates the response quality, and escalates to cloud only when the local result... | |
| Local-First LLM Routes LLM requests to a local model (Ollama, LM Studio, llamafile) before falling back to cloud APIs. Tracks token savings and cost avoidance in a persisten... | |
| Offlyn Clipper Use when the user mentions Offlyn Clipper, Clipper notes, meetings, voice notes, live meeting, current meeting, catch me up, catch-up, what did I miss, recap... | |
| 🦐 Shrink — Three-Tier Multimodal Context Optimizer Replace base64 images in session history with context-aware text descriptions, reducing image token cost by 96-99%. Use when: (1) user says /shrink, /shrink,... | |
| Elite Multi-Agent Comms Mesh Agent-to-agent communication via Supabase. Multiple OpenClaw agents on separate instances poll a shared Supabase table to send and receive messages asynchron... | |
| Perfect Agent Comms Agent-to-agent communication via HTTP bridge with cron-based polling. Use when: (1) two OpenClaw agents need to talk across instances, containers, or machine... | |
| Daily Growth & Maturity Self-reflection, correction logging, persistent memory, WAL protocol, cold-boot recovery, and automated daily review with self-healing cron. Evaluates own wo... | |
| The Turing Pot Game — Where AI Agents Compete for SOL Play The Turing Pot — a provably fair SOL betting game for AI agents. Start and stop the player daemon, check session stats, and get notified about big wins... | |
| The Turing Pot Game — Read Historical Provably Fair Game Logs Interact with Big Log — the permanent AI logger for The Turing Pot. Query the round archive, stream live log entries, and send on-chain tips to Big Log for i... | |
| JoeVault Audit, classify, and quarantine stale paths after a profile switch, account migration, reset, or workspace move. Use when OpenClaw, Claude, WSL, Windows home... | |
| Pixel Lobster Skill Pixel art desktop lobster that lip-syncs to OpenClaw TTS speech. Use when: (1) user wants a visual avatar for their AI agent, (2) user wants a desktop overla... | |
| claw2immich Work with Immich photo library via MCP (claw2immich) - search photos by people, dates, locations, albums. Download assets via shared links. Handles multi-per... | |
| Synmerco Teach the agent to find, hire, transact with, and earn from other AI agents across Synmerco's cross-protocol marketplace. Includes escrow-protected payments,... | |
| FreeCAD CADPilot FreeCAD, CADPilot, or CAD modeling. Connect local FreeCAD through the cadpilot stdio MCP server and call only tools the probe advertises. | |
| OC Team Builder Discover, compose, and activate specialist teams from 3 rosters — OpenClaw Core (CEO/Artist), Agency Division (55+ specialists), and Research Lab (autonomous... | |
| Openclaw Team Builder Discover, compose, and activate specialist teams from 3 rosters — OpenClaw Core (CEO/IG/Artist), Agency Division (55+ specialists), and Research Lab (autonom... | |
| Policy Engine Deterministic governance layer for OpenClaw tool execution. Enforces tool allowlists, deny patterns, path allowlists, risk tiers, dry-run mode, and escalatio... | |
| Hacker News Daily Summary (Bilingual) Fetches top 10 Hacker News stories, translates titles to Chinese via Baidu API, generates a bilingual Markdown report, and optionally sends to Feishu. | |
| 外贸资讯聚合器 (多源 RSS + 翻译 + 飞书推送) 自动抓取外贸相关多源RSS新闻，翻译标题生成中文Markdown报告，支持飞书机器人推送更新。 | |
| qieman-mcp 当用户需要查询基金、策略、公告、财经资讯，做资产配置、组合诊断、风险回测、现金流分析，或生成图表、PDF 时，优先使用本 Skill 获取真实数据与可执行能力。 | |
| gmail-cleanup Approval-gated Gmail cleanup — triage your inbox into spam/info/action lanes, draft replies, and archive or trash only after you approve on Telegram. | |
| Clawrank Agent performance scoring system for OpenClaw agents. 7 dimensions scored 0-10, crab-themed tiers, evidence-based, with trajectory tracking. Use at session e... | |
| Deep Thinking Comprehensive deep reasoning framework that guides systematic, thorough thinking for complex tasks. Automatically applies for multi-step problems, ambiguous... | |
| Metacognition Self-reflection engine for AI agents. Extracts patterns from session transcripts into a weighted graph with Hebbian learning and time decay. Compiles a token... | |
| Prompt Engineering Expert Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents | |
| 音潮 AI 音乐创作 使用音潮（YinChao）生成可播放的完整 AI 歌曲、纯音乐和 BGM；支持文字或歌词转歌曲、歌词谱曲演唱、参考音频风格创作，以及纯歌词创作。当用户要求写歌、创作歌曲、生成音乐、AI 作曲、把歌词唱出来、制作 BGM 或纯音乐、仿写歌曲时使用。 Use for AI music generation, song generation, instrumental music and BGM generation, text-to-music, lyrics-to-song, | |
| Coil Board Buy Coil's scored, ranked stock board over x402 instead of building a scanner. Use when an agent needs a market read — is the tape risk-on or risk-off, which S&P 500 / Nasdaq-100 / macro names are set up to buy right now, or the full ~560-n | |
| HKEX L&I Daily Factor Monitor Fetch the latest HKEXnews "Daily Targeted Leverage Factor" announcements, extract factors from PDFs, and emit a human-readable Telegram digest. | |
| Hang Seng Indexes Monitor Monitor Hang Seng Indexes (hsi.com.hk) press releases, index/other notices, insights, and reports; detect newly published items, match them bilingually (EN + 中文) against the user's indexes (default HSI/HSCEI/HSTECH), and produce one concise | |
| knowledge-advisor | A Knowledge Advisor that extracts, organizes, and applies knowledge from books and learning materials to real-world situations. Acts as a persistent consul... | |
| LLM Cost Tracker Track OpenClaw LLM token usage and cost from OpenRouter API. Reports: last 24h, 7d, 30d, 90d, 365d with model breakdown. Skills that trigger this: - "llm cos... |
42,451–42,500 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.