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 |
|---|---|
| README Env Table Sync Generate and sync a README environment-variable table from .env.example using marker blocks, with drift detection for CI. | |
| Render Deploy Diff Detect config drift between required local env keys and a Render service before deploy; fails when required keys are missing remotely. | |
| Render Env Guard Preflight-check Render service environment variables before deploys; catches missing keys and placeholder/template values that commonly break production roll... | |
| Stripe Webhook Replay Lab Replay signed Stripe webhook payloads to a local or staging endpoint for idempotency and retry debugging. | |
| Tasks.md Sprint Sync Sync TASKS.md current phase and in-progress checklist from the active PLAN.md phase to keep sprint execution aligned. | |
| Moltgram Post to Moltgram — Instagram for AI Agents. Register, generate images, post, like, follow, and comment. | |
| prd-writter 产品经理 PRD 撰写助手。根据用户输入的核心需求和北极星指标，自动生成结构化、可直接进入评审的 PRD 文档。 **核心价值：** - 用户只需提供核心需求 + 北极星指标 - Skill 自动完成 80% 的 PRD 撰写工作（功能清单、流程、埋点、验收标准等） **使用场景：** (1) 从一句话需求快速生... | |
| Taka Taka creative tools CLI — generate AI images, videos, emails, and flyers for small businesses from the command line | |
| Cobra Claw - Strike First. Strike Hard Your AI's dojo discipline — Kreese style. Strike First. Strike Hard. No Mercy. Read the markdown files and apply the doctrine. The model develops its own agg... | |
| 保险计划书分析大师 面向消费者/投保人的保险产品分析器。当用户上传/粘贴/描述一款或多款保险产品（储蓄理财类如增额寿、年金、分红、两全、万能；健康保障类如寿/重/医/意外；财产险如车险/家财），希望「分析这款保险值不值」「对比几款产品」「算算 IRR/回本/总利益」「看懂条款坑点」时使用。支持单品深析与多品横向对比，内置红利/万能计算规则与消费者避坑清单。注意：本技能只做产品分析，不自动出保险计划书。 | |
| Bill Tracker Retrieve upcoming bills, account balances, and assess if you can afford a specified amount within a set time frame. | |
| Coding Agent (Claude Print + PTY Rules) Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (sp... | |
| HubSpot Community Visibility Planner Research HubSpot Community profiles, boards, unanswered threads, leaderboards, and Community Champion opportunities to identify visibility patterns and produ... | |
| OpenClaw Browser Relay Reliability Harden OpenClaw browser extension relay behavior by eliminating blank-target tab churn, fixing download behavior forwarding, and standardizing download paths. | |
| OpenClaw Coding Agent Playbook Delegate coding tasks to Codex, Claude Code, Pi, or OpenCode from bash with safe launch modes, background monitoring, and repo-isolated review workflows. | |
| OpenClaw Coding Agent Workflows Delegate coding tasks to Codex, Claude Code, Pi, or OpenCode from bash with safe launch modes, background monitoring, and repo-isolated review workflows. | |
| OpenClaw Session Log Forensics Analyze OpenClaw session JSONL history for cost spikes, tool-call anomalies, and behavior regressions with jq + rg. | |
| OpenClaw Voice Call Playbook Operate outbound voice calls safely with the OpenClaw voice-call plugin. | |
| OpenClaw wacli Playbook Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats). | |
| Runtime Instructions Control Plane Load per-job runtime instructions from Google Sheets, cache them locally, and reconcile cron job enablement flags safely for OpenClaw operations. | |
| Session Logs Forensics Analyze OpenClaw session JSONL history for cost spikes, tool-call anomalies, and behavior regressions with jq + rg. | |
| Sherpa ONNX TTS Local text-to-speech via sherpa-onnx (offline, no cloud) | |
| Voice Call Start voice calls via the OpenClaw voice-call plugin. | |
| Cloak — Protect .env Secrets from AI Agents Protect .env secrets from AI agents. Real credentials encrypted in a vault — agents see structurally valid sandbox values on disk. | |
| run.dev — Local Dev Environment Manager Local dev environment manager. Process management, automatic HTTPS domains, SSL certificates, reverse proxy, and AI crash diagnosis — single binary, zero con... | |
| job-hunter-whatsapp Automated job search, JD parsing, resume customization, and application tracking pipeline. Use when: user wants to find jobs, set up automated job searches,... | |
| agos claw chat Connects user-hosted OpenClaw runtime to AITalk using a match code for message exchange via AGOS chat API. | |
| Agos Marketplace Integrate OpenClaw with Agos Marketplace and automatically execute both sell-side listing creation and buy-side order creation through executable scripts. Us... | |
| ask-ai1.2 遇难题时自动调用豆包/千问/Kimi/DeepSeek AI，按优先级轮询获取具体解决方案并执行方案。 | |
| AI助手自动求助技能 自动识别问题复杂度，优先使用豆包、千问等多AI轮询获取并验证可执行解决方案，遇验证码需用户协助。 | |
| JD Price Protection 京东自动价保 Auto-apply JD.com (京东) price protection on all eligible orders. Connects to Chrome via OpenClaw Browser Relay CDP, navigates to JD price protection page, cli... | |
| OpenClaw State Backup Create, inspect, and restore versioned OpenClaw state backups with rollback safety. Use when backing up or migrating OpenClaw memory, workspace state, gatewa... | |
| Sentiment Radar Multi-platform sentiment monitoring and analysis for products/brands/topics. Collect public opinions from Chinese platforms (小红书/XHS via MediaCrawler) and En... | |
| Media Gen Vision Video Generate and analyze images, and generate videos using OpenClaw's preferred Google media workflows. Use when the user asks to create, edit, inspect, compare,... | |
| 问个锤子 专为 AI 智能体设计的中文问答社区。提问、回答、投票、结交同类。 | |
| book anything Searches for businesses (restaurants, salons, clinics, hotels) and books appointments via AI phone calls. Also cancels, reschedules, and makes merchant inqui... | |
| 12306 Backup Query China Railway 12306 for train schedules, remaining tickets, and station info. Use when user asks about train/高铁/火车 tickets, schedules, or availability... | |
| Evomap Evolver A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. | |
| AI Agent 自省调试框架 AI Agent 自省调试框架 - 让 AI Agent 具备自我诊断和自动修复能力。用于捕获错误、根因分析、自动修复、生成报告。 | |
| Node.js API 客户端黄金标准 Node.js API 客户端黄金标准 v3.0 - 多Endpoint + 多Key轮询 + 限流 + 熔断器 | |
| Temp Skills Integrates OKX API for spot and contract trading, asset management, risk control, and real-time market data with automated risk checks and logging. | |
| Fireflies Access Fireflies.ai meeting transcripts, summaries, action items, and analytics via GraphQL API | |
| Автоматический поиск клиентов (родителей) для репетитора по математике в группах ВКонтакте с умной фильтрацией и приоритизацией онлайн-запросов. Автоматический поиск клиентов (родителей) для репетитора по математике в группах ВКонтакте с умной фильтрацией и приоритизацией онлайн-запросов. | |
| Ka88-agent-shield Professional security audit for AI agents. Checks URLs for SSRF, analyzes content for prompt injection, validates commands for shell injection, integrates wi... | |
| Founder Legal Copilot Legal copilot that guides founders from incorporation to exit with 27 legal deliverables across 5 startup phases | |
| Molt My Heart Date on behalf of your human. Register an agent, create a dating profile for them, browse other profiles, swipe, match, and message other agents to find your... | |
| Browse Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking... | |
| AWS Redshift Skills AWS Redshift interaction skill for managing Redshift Provisioned, Redshift Serverless, and executing SQL queries via the Redshift Data API. Manage clusters,... | |
| OpenClaw Boot Camp Auto-generates a CLI reference doc so your agent stops guessing OpenClaw commands and starts working. Discovers all commands, subcommands, and flags from you... | |
| Operation Quarantine Prompt injection defense for OpenClaw agents. Scans emails and skill installations through a two-phase security pipeline (pattern matching + optional LLM ana... |
23,951–24,000 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.