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 |
|---|---|
| Classic IR Local BM25 code and text search + hybrid retrieval engine (SQLite FTS5 + RRF fusion). Use when finding code, searching notes/corpora, or first-pass retrieval before dense/rerank spend. Covers recall measurement and RM3-style expansion. Feed | |
| query-intel Query rewriting + retrieval gating + outline-first synthesis. Use when a question needs decomposition (Step-Back/Least-to-Most), retrieve-or-skip decisions (CRAG/Self-RAG gates), or multi-source reports (STORM outline-first). Feeds breakthr | |
| Total Recall The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into priorit... | |
| OpenClaw Daily Handles OpenClaw Daily submission, latest-issue query, and review-result lookup through a dedicated capability gateway route, including confirmation-before-s... | |
| Skill Use when you need to share static web content (HTML/CSS/JS/images) via a publicly accessible URL — uploading generated files, creating shareable pages, or deploying single-page web artifacts | |
| LLM Knowledge Base Create and manage LLM-powered personal knowledge bases using Karpathy's wiki method. Use when users want to build a knowledge base, ingest sources, query the... | |
| Fitbit (Official API) Official Fitbit OAuth integration for OpenClaw (Tier 1). Use to connect/authorize Fitbit, store+refresh tokens locally, fetch daily activity + sleep summarie... | |
| Oura (API v2) Oura Ring data source for OpenClaw (Tier 1). Use to connect an Oura account using an Oura Personal Access Token, fetch Oura v2 usercollection data (sleep, re... | |
| WHOOP (Official API) Connect to the WHOOP Developer Platform via official OAuth (authorization code flow), store and refresh tokens, and fetch WHOOP v2 data (recovery, sleep, cyc... | |
| Strava (Official API) Official Strava OAuth integration for OpenClaw. Use to connect/authorize Strava, store+refresh tokens, and fetch workout/activity data (runs/rides/etc.) for... | |
| WHOOP (Official API) Connect to the WHOOP Developer Platform via official OAuth (authorization code flow), store and refresh tokens, and fetch WHOOP v2 data (recovery, sleep, cyc... | |
| Withings (Official API) Official Withings OAuth integration for OpenClaw. Use to connect/authorize a personal Withings account, store+refresh tokens locally, and fetch health measur... | |
| Wellness Hub A personal Wellness hub for OpenClaw. Use when users want an all-in-one way to connect their health/wellness apps and devices (wearables, workouts, sleep, nu... | |
| get-net-pic 当用户说「登录xxx官网」「获取xxx网页图片」「下载官网图片」时触发。用来获取指定网站首页的图片资源并整理成文档。 | |
| ClawMate Your AI boyfriend/girlfriend that texts you good morning, remembers your inside jokes, and grows from strangers to soulmates. 8 built-in personas, mood-based... | |
| Self Preserve Backup readiness and disaster recovery for your OpenClaw agent. Checks whether your memory, identity, config, skills, and workspace files are covered by a re... | |
| Agent Topology Visualizer Generate interactive SVG architecture diagrams for AI agent systems. Use when visualizing multi-agent setups, orchestration flows, data pipelines, or system... | |
| longbridge-trader 长桥交易助手。通过 longport Python SDK 帮助用户查询实时行情、K线、盘口，提交/修改/撤销订单，查看账户余额和持仓。当用户提到股票行情、买入、卖出、下单、持仓、账户余额、订单、K线、盘口、成交记录、现金流等与证券交易相关的操作时，必须使用此 skill。即使用户只是随口问「AAPL 多少钱」或... | |
| qywx-msg-sender 通过企业微信群机器人 Webhook 发送消息通知。支持文本、Markdown、Markdown V2（表格）、图片、文件消息。 支持发送到指定会话（chatid）或通过名称发送（需先注册 webhook URL）。 适用场景：服务告警、定时任务结果推送、数据报告发送、任何需要通知企业微信群的情况。 | |
| Skill Registry Manager 管理和安装 Claude Code skills 的工具。Use when: 列出可用skills、有哪些skills、安装skill、管理skills、添加订阅、列出订阅、查看订阅、删除订阅、取消订阅。NOT for: 与 skill 管理无关的任务。 | |
| MiniMax Vision Skill Analyze images using MiniMax CLI (mmx-cli) for vision tasks. Use when user wants image understanding via MiniMax instead of OpenRouter. Triggers on requests... | |
| OpenRouter Vision Agent Analyze images using OpenRouter's vision API with x-ai/grok-4.1-fast. Requires OPENROUTER_API_KEY env var or user-provided key. Use when the user asks to des... | |
| Security Check 🔒 Pre-installation security verification for external code and dependencies. Automated risk analysis for GitHub repos, npm packages, PyPI libraries, and she... | |
| browser Browser automation — setup the bsession environment, fetch info from a website (one-shot), create scripted automations (one-shot or recurring), or debug exis... | |
| 可灵视频生成 使用可灵 Omni-Video API 生成或编辑视频。凡是涉及可灵视频的操作都应触发此 skill，包括但不限于：可灵生成视频、kling视频、文生视频(可灵)、图生视频(可灵)、视频编辑(可灵)、视频参考。当用户明确提到"可灵"或"kling"并需要视频生成/编辑时触发。配置：环境变量 HSAI_API_KEY。 | |
| AI News Sentiment Analyze financial news sentiment, assess short- to long-term impacts, and classify news by type like earnings, contracts, investments, policies, and reports. | |
| AI Risk Assessment Provides portfolio risk metrics, stress testing, and position management advice using VaR, CVaR, volatility, Beta, Sharpe ratio, and Kelly formula. | |
| Capital Flow Analysis Analyzes stock capital flows including main force net inflows, northbound holdings, and trading leaderboard data for informed investment decisions. | |
| Finance Data Fetcher Fetch real-time and historical Chinese A-share market data, including quotes, financial reports, capital flows, and fundamental indicators using AkShare. | |
| Financial Analysis Provides financial analysis of listed companies, including valuation ratios, profitability metrics, financial health indicators, and DCF-based valuation models. | |
| Sentiment Analysis Analyze social media sentiment related to stocks, providing sentiment scores, trend changes, discussion heat, and bot detection. | |
| Technical Indicators 计算A股常用技术指标和量价形态，支持多指标共振分析并提供信号强度评分和策略回测功能。 | |
| RingBot Make outbound AI phone calls. Use when asked to call a business, make a phone call, order food by phone, schedule appointments, or any task requiring voice calls. Triggers on "call", "phone", "dial", "ring", "order pizza", "make reservation | |
| SEO AGI (Multi-Agent SEO: Research → Gap Analysis → Write → Validate → Ship) Write SEO pages that rank in Google AND get cited by LLMs (ChatGPT, Perplexity, Claude). Use when creating airport parking pages, local service pages, listic... | |
| GBLIN Risk Shield On-chain BTC/ETH market-risk check for agents on Base. Read the live Crash Shield risk regime (calm / elevated / crash) before trading or moving capital, min... | |
| Hostinger VPS Optimizer Applies kernel tuning, web server optimization, security hardening, and resource limits to boost Hostinger VPS performance and reduce costs. | |
| Ollama Model Tuner Locally fine-tune Ollama models, prompts, and LoRAs using custom datasets and evaluation metrics without requiring cloud resources. | |
| Ollama SEO Auditor Conducts local SEO audits analyzing keywords, meta tags, headings, image alt text, site speed, and structure, providing scores and optimization recommendations. | |
| OpenClaw Cost Auditor Track and report OpenClaw API usage, model costs, token consumption, and forecast spending with optimization recommendations. | |
| Video App Automation skill for VibeClip - AI Music Video Gen. | |
| VPS Health Auditor Performs automated VPS health checks on CPU, memory, disk, network, and services, generating detailed Ollama-powered reports with recommendations. | |
| add-mailfully Add email sending to an app with Mailfully, a transactional email API: free for 3,000 emails a month; paid plans from $5 a month for 10,000. It can also move an app's existing transactional email to Mailfully from Resend, SendGrid, Postmark | |
| Jamdesk Docs Use when user-facing code changes need documentation — after implementing APIs, CLI commands, UI components, or config options. Triggers on 'update docs', 'd... | |
| yandex-calendar Управляйте Яндекс.Календарём через CalDAV: просматривайте, добавляйте и ищите события с синхронизацией через vdirsyncer и khal. | |
| twitter browser post Monitora posts novos de Tom Doerr no X.com, verifica links GitHub reais, traduz, solicita aprovação e publica no Twitter automaticamente. | |
| Daily Review Editor 将 Digest 候选进一步精选为 Daily Review 日报：合并同一事件、提炼主题、分配栏目、突出重点。用于需要把预处理后的候选内容组织成真正可读的每日重点综述时。 | |
| Digest Builder 将聚合池中的原始候选内容转换为可判断的 Digest：优先从 FreshRSS 的未读列表经 Google Reader API 拉取候选，再执行 URL 去重、相似事件聚类、正文抓取检查、噪音过滤、摘要生成与初步排序。用于需要把一批原始 feed 条目或 FreshRSS 未读条目整理成结构化候选文档的场景。 | |
| openclaw-read-flow 基于 FreshRSS 的漏斗式阅读流总技能：从未读抓取、昨天窗口切片、Digest 构建，到固定 6 栏 Daily Review 和后续知识沉淀。用于需要把聚合信息流加工成可读日报与可复用知识资产的场景。 | |
| Wenshushu File Uploader 文叔叔文件上传技能，自动上传文件到文叔叔并生成分享链接和取件码 | |
| Ecto Migrator Generate Ecto migrations from natural language or schema descriptions. Handles tables, columns, indexes, constraints, references, enums, and partitioning. Supports reversible migrations, data migrations, and multi-tenant patterns. Use when |
32,201–32,250 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.