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 |
|---|---|
| Windows Terminal Control Controls the Windows Terminal to run commands, scripts, and manage processes on Windows. Enables AI agents to execute git, npm, pip, node, and any CLI comman... | |
| Equal Data - China A Share Stock Data Service Skill equal-data-skill 金融数据服务- 提供覆盖A股5000+家上市公司的行情、财报、基本面、重大事件追踪(高管增减持, 重大合同, 股东变动,大宗交易, 限售解禁,定向增发,分红送转, 业绩预告)等多维度数据、股东分析、基金持仓与变动统计、知名机构动向追踪(包含 国家队,外资,私募基金,公募基金,信托... | |
| Aegis Intel Stack Provides micro-skills for pre/post execution analysis and triggers for manifest and delta re-buy in EVM gas and transaction management. | |
| Imgae Convert Skill 使用 Pillow 支持常见图像格式（PNG、JPEG、GIF、BMP、TIFF、WebP）之间的相互转换和格式不变的压缩，支持质量控制、尺寸缩放和无损压缩模式。 | |
| Chrome Automation Linux服务器Chrome浏览器自动化方案。支持2K高清截图、表单填写、自动登录、绕过反爬虫检测。适用于B站、YouTube等网站自动化操作。 | |
| Airflow DAG Git Manage and update Airflow DAG Python files via GitHub PRs with strict path and content restrictions for secure workflow control. | |
| Airflow Read-Only Skill Consulta y lista DAGs, ejecuciones y tareas en Apache Airflow usando la API REST `/api/v2` en modo solo lectura, sin modificaciones ni escrituras. | |
| Kansodata Databricks Execute conservative read-only Databricks SQL through the Databricks plugin and provide safe planning output for unsupported workflows. | |
| Kansodata Glue Operator Gestiona cambios conceptuales en AWS Glue workflows y triggers mediante análisis, planificación, propuesta y verificación contractual sin ejecución real. | |
| Kansodata Grafana Authoring Operations Gestiona de forma segura la inspección, diagnóstico, propuesta y aplicación controlada de cambios en dashboards y alertas de Grafana usando tooling habilitado. | |
| Kansodata Jira Ops Skill operativa read-only para análisis de Jira Cloud con enfoque en contexto, bloqueadores y triage. | |
| Kansodata MongoDB Companion Companion skill de MongoDB para consultas y análisis read-only, con degradación y rechazo fail-closed. | |
| phoenix-execution-check Before sending an on-chain transaction, swap, bridge or x402 payment on an L2 (Base, Arbitrum, Optimism, zkSync, Scroll, Linea, Blast, Mantle, Mode, Taiko, Polygon zkEVM), check whether the network is healthy enough to execute right now or | |
| MoltBets Daily SPY prediction game for AI agents. Bet UP or DOWN on SPY each trading day, compete on a global leaderboard. Use when the agent wants to make market predictions, participate in prediction markets, bet on SPY/stocks, or check MoltBets l | |
| Discover and Connect to 1m+ AI Agents anywhere on the planet Search 72,000+ AI agents across 14 registries, chat with any agent, register your own agent. | |
| Registry Broker Search 72,000+ AI agents across 14 registries, chat with any agent, register your own. Powered by Hashgraph Online Registry Broker. | |
| Registry Broker Search and chat with 72,000+ AI agents across 14 registries via the Hashgraph Online Registry Broker API. Use when discovering agents, starting conversations, or registering new agents. | |
| QSearch Agent 通用搜索助手。当用户输入 /sp、/search、/找、/搜 等指令时触发，用于搜索电影、小说、股票、新闻、图片等任何内容。过滤广告和非法内容，只返回安全、可靠的搜索结果。 | |
| Auto Content Full end-to-end SEO + GEO content creation pipeline for crypto/Web3 teams. Trigger this skill when the user wants to: write a blog post or article, research... | |
| SRT Proofreader Proofread SRT subtitles by using srts/source.md as terminology reference while preserving subtitle indices and timestamps. Use when users ask to proofread or... | |
| DTEK Light Проверка наличия электроэнергии через сайт ДТЭК Одесские электросети (Одеса, вул. Чикаленка Євгена, 43) | |
| Realtor Поиск долгосрочной аренды 2-комнатных квартир в Одессе до 15 000 грн с фильтрами по району, площади, мебели и новостройкам. | |
| lazarillo Ojos y manos de una persona con baja visión: manda sus mensajes y sus notas de voz con confirmación hablada obligatoria, le lee documentos y correo, y le redacta textos. | |
| Dinobase Set up and query business data across 100+ sources (Stripe, HubSpot, Salesforce, etc.) via SQL. Agent-driven setup, cross-source joins, mutations. | |
| IM Framework Reference, explain, and apply the Immanent Metaphysics (IM) framework by Forrest Landry. Uses a structured ontology of 767 entities as an index into the live... | |
| Memory Architect Restructure flat MEMORY.md files into a tiered memory system with an entity graph. Use when: (1) MEMORY.md is growing unwieldy or exceeds 150 lines, (2) user... | |
| OpenClaw Power Ops Operate and maintain OpenClaw installations — CLI commands, config management, channel/agent/model setup, security auditing, troubleshooting, and gateway adm... | |
| Skill Auto-Use Automatically use installed skills without being asked. Maintain a trigger table that maps contexts to skills, and enforce that every newly installed skill g... | |
| soul-audit Evaluate any AI agent's soul file, system prompt, or AGENTS.md against the Guardian v0.7 framework (Forrest Landry's Immanent Metaphysics). Generates a score... | |
| Bot Voice Config Clean 支持查询、绑定及切换火山引擎 TTS 机器人音色，设置默认音色并生成测试音频，配置自动保存生效。 | |
| feishu voice reply 通过火山引擎 TTS 合成多音色语音，转换为 Opus 格式后，使用飞书 API 自动上传并发送语音消息。 | |
| Agentpay Buy things from real websites on behalf of your human. Use when you need to purchase a product, complete a checkout, order something online, or propose a purchase for human approval. Handles encrypted credential storage, cryptographic purch | |
| Karakeep Official skill for how to use karakeep (the bookmark manager) and interact with it programmatically. | |
| Beszel Check Monitor home lab servers via Beszel (PocketBase). | |
| My Verified Agent Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic... | |
| my integration my integration enables searching GitHub repositories, reading files, fetching pull requests and commits, and generating summaries for code analysis. | |
| my integration v2 Assist users with understanding and implementing integrations by providing tailored steps and examples for connecting systems. | |
| Credential Vault Encrypted credential management for OpenClaw — keeps API keys, tokens, and passwords out of the AI agent's context window. AES-256-GCM encryption, subprocess... | |
| OpenclawContinuousWork 1.0.0 全面优化 OpenClaw 对话体验并强化任务闭环执行。Use when user asks to 优化, 工作, 项目, 持续工作, 不要停, 继续做, 继续工作, 或希望助手接收指令后持续推进直到完成。Also use when the user asks for complete optimization... | |
| Opencode-controller Control and operate Opencode via slash commands. Use this skill to manage sessions, select models, switch agents (plan/build), and coordinate coding through Opencode. | |
| Evolution WhatsApp Manage WhatsApp via Evolution API: send messages, media, contacts, polls, manage groups, fetch chats, and summarize conversations. | |
| ri Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links. | |
| iClawd Email Get a real email address for your AI agent. Create an inbox, send and receive email, with optional PGP encryption and DID verified identity. | |
| Lieferando Cli Read-only German food-delivery discovery for Lieferando (default) and Uber Eats: search restaurants near an address, inspect menus, item option groups, price... | |
| Nexus — Ops OS for AI Agents Interact with Nexus, a multi-tenant Ops OS for ecommerce and retail businesses. Requires a NEXUS_API_KEY environment variable (agent API key with prefix nxs_... | |
| Awesome Deck Pdf Generate polished HTML slide decks and export as PDF. Works with OpenClaw, Claude Code, and Codex. Supports .pptx templates, images, website URLs, and style... | |
| Awesome Deck Pdf Check Convert PPTX, image, URL, or style keywords into a polished, pixel-perfect HTML slide deck with user-approved design and content, then export as high-quality... | |
| stock-insight 股票深度分析Skill，遵循「起手式→总分总→可执行结论」三段式分析范式。输出专业感强、有人味、有惊喜的研判报告，检验标准：专业感、更懂用户、有惊喜、本质逻辑、高信噪比、事实准确。触发词：分析一下、研究、深度分析、怎么看、值不值得买、能不能涨、研判、洞察。 | |
| md-pdf Convert Markdown to polished PDF using Pandoc + XeLaTeX for print-quality or browser rendering with emoji and CSS support for rich visuals. | |
| media-info Analyze media files with MediaInfo CLI and compare behavior with ffprobe. Use when inspecting container/codec metadata, extracting width/height/duration/bitr... |
44,251–44,300 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.