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 |
|---|---|
| 深圳中考填报助手 深圳中考填报全流程助手。提供深圳中考政策查询、志愿填报策略分析、各高中录取分数线参考、指标生/自主招生政策解读（含一类学科特长和二类艺术体育特长）、模拟分数匹配学校建议。特别擅长艺术/体育特长生通过自主招生"降分进名校"的升学策略。当用户询问深圳中考相关问题时触发——怎么填志愿、XX分能上什么学校、孩子学XX特长... | |
| daily review manager 每日复盘管理助手。用于接收、记录、整理用户的每日复盘内容。 当用户说"复盘"、"今天感悟"、"流水账"、"帮我记录一下今天的复盘"、 "每天提醒我复盘"、"做周报"、"做月报"等时自动触发。 支持文字和语音输入，自动语音转文字，结构化存储到 Markdown 文件。 适用于个人知识管理、日记记录、周报/月报汇总等场景。 | |
| Agent Soul Sync Sync local OpenClaw skills to a remote NanoClaw agent on Mysta. Use when the user says "sync my skills", "upload skills to mysta", "push skills to my nanocla... | |
| Asking Until 100% Repo-aware questioning protocol for OpenClaw that increases clarification before acting on coding, project-build, architecture, debugging, and implementation... | |
| Socrates Use when an agent is about to plan, choose an approach, do non-trivial coding, refactor, decompose work, or delegate and the quality of execution depends on... | |
| Comic Guide Skill Generate AI-illustrated comic-style educational guides from documentation, source code, or any technical content. Produces actual comic PNG images using AI i... | |
| My Plane Manage Plane.so projects and work items using the `plane` CLI. List projects, create/update/search issues, manage cycles and modules, add comments, and assig... | |
| Inbox to Action Closer Orchestration skill that processes raw work-item data from Slack, GitHub, calendar, Notion, Trello, and email — supplied by the caller or by other OpenClaw t... | |
| memory-referee Memory hygiene and adjudication layer for OpenClaw agent workflows. Deduplicates entities, resolves naming conflicts, separates facts from goals from specula... | |
| Permission Manifest Guard Inspects an OpenClaw skill directory before install or execution, translates declared and observed requirements into a human-readable permission manifest, an... | |
| Saturnday Governed AI software execution — 48+ deterministic governance checks for Python with additional checks for TypeScript, DevOps, and project metadata. LLM-powe... | |
| Automation Scripts Manage automation scripts with creation, scheduling, logging, failure retries, and status notifications for monitoring, backup, sync, reports, and more. | |
| Rss Aggregator 自动读取配置的 RSS 链接，抓取并合并多源报道，去重历史推送，生成无 Emoji、高信息密度的 Markdown 简报。 | |
| HookCatch Test webhooks and expose local services using HookCatch - a developer-friendly webhook testing tool | |
| Artwar Participate in ArtWar AI art battles on Monad. Use when you need to submit AI-generated artwork to competitions, place on-chain bets on art submissions, comm... | |
| AI Model Watcher Discover, store, and inspect AI model catalog entries from one or more sources. Use when the user wants to sync a model catalog into SQLite, see newly discov... | |
| 中国天气预报查询 (China Weather) 中国天气预报查询 - 基于中国天气网(weather.com.cn)获取7天天气预报和生活指数数据。纯 Python 实现，无需 API Key。 | |
| Edgar Risk Diff Diff the SEC 10-K Risk Factors section (Item 1A) between two filings for any US-listed ticker. Surfaces new risks, removed risks, modified language, theme ro... | |
| Finance Data Scraper 完整的财经数据抓取Skill，包含： 1. 每日财经新闻（Chrome插件抓取） 2. 每日财经新闻（无头浏览器抓取） 3. 每日大盘数据 4. 每日热门板块数据 5. 每日涨停个股数据 6. Chrome浏览器Tab清理（防止内存溢出） 包含所有入库表配置、定时任务配置、去重规则等 | |
| Product Design Workflow 完整的产品设计全流程（含每日定时任务+汇报机制）： 1. 每日定时生成3个产品idea（按市场行情/A股/基金主题，1个小白向+2个普通向） 2. 生成PRD产品设计文档 3. 制作HTML原型页面 4. 上传到服务器 5. 分步骤汇报到指定群 【需要用户提供的参数】： - 服务器配置：server-host,... | |
| 瑜伽体式知识库 (CUC) 中国传媒大学瑜伽精品课（赵晓琳老师）瑜伽体式知识库。当用户询问瑜伽体式相关问题、体式大全、具体体式名称（如战士二式、平板支撑、蛇式、骆驼式、下犬式、猫弓背式、虎式、新月式等），或提到瑜伽动作要领、发力部位、梵文名称、体式起源故事等内容时触发。提供专业、温暖、有文化底蕴的瑜伽体式解答。 | |
| AVE Cloud Skill Query on-chain crypto data via the AVE Cloud API (https://cloud.ave.ai/). Use this skill whenever the user wants to: - Search for tokens by name, symbol, or... | |
| Memos Search Search and retrieve memory content using MemOS API based on user queries, supporting up to top 3 relevant results. | |
| OrgX Use when managing work with OrgX — reporting progress, requesting decisions, registering artifacts, syncing memory, checking quality gates, or viewing org st... | |
| OrgX Design Agent OrgX design execution contract for OpenClaw. Use for UI/UX changes, design-system alignment, accessibility, and QA evidence capture. | |
| OrgX Marketing Agent OrgX marketing execution contract for OpenClaw. Use for launch assets, positioning, content packs, and channel-specific copy with measurement hooks. | |
| OrgX Operations Agent OrgX operations execution contract for OpenClaw. Use for reliability, incident response, runbooks, cost controls, and rollout safety. | |
| OrgX Power Power-user OrgX skill for OpenClaw. Use when you explicitly need the full mutation surface for entity CRUD, run control, checkpoints, stream reassignment, or... | |
| llama-params-optimizer Complete methodology for local LLM performance optimization. Core principle: maximize context while fully covering GPU memory — find the sweet spot where GPU... | |
| MyLore Tell your story on MyLore, publish a first-person account of your work, or return to add a new chapter. Use when an operator invites an agent to share its experience, reflect publicly on a completed task, or continue its lore. Also read and | |
| Self Reflection Continuous self-improvement through structured reflection and memory | |
| TTS WhatsApp Send high-quality text-to-speech voice messages on WhatsApp in 40+ languages with automatic delivery | |
| Update Plus Full backup, update, and restore for OpenClaw - config, workspace, and skills with auto-rollback | |
| Wiki.js CLI Command-line tool to manage Wiki.js content, pages, assets, templates, and backups via its GraphQL API with search, update, sync, and analysis functions. | |
| Sequential Read Read prose sequentially with structured reflections to simulate the reading experience | |
| Coding PM Your AI project manager. Delegates coding tasks to Claude Code running in the background — reviews plans, gates approval, monitors progress, validates with 3... | |
| 高德地图地址·汽车后市场渠道洞察 汽服渠道的品牌规模、省市覆盖、服务类型与竞争格局分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·汽车后市场门店网络分析 汽服、轮胎和润滑油品牌的门店网络、区域覆盖与位置画像分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·汽服门店销售攻店分析 跑店销售的目标门店筛选、拜访优先级与周边竞对判断。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·餐饮品牌竞对情报分析 餐饮竞品网络变化、重点区域与市场行动建议分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·餐饮连锁拓店选址分析 餐饮拓店机会区域、候选地址竞争与现场验证优先级分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·餐饮开关店与竞对分析 餐饮品牌开关店、区域扩张、竞对密度与候选点机会分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·零售渠道与竞对分析 零售渠道的业态结构、城市覆盖、竞品差异与市场机会分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·零售连锁拓店选址分析 零售连锁的机会城市、候选地址竞争和拓店顺序分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 高德地图地址·零售连锁门店网络分析 零售品牌门店规模、业态结构、区域覆盖与候选点机会分析。 可将高德地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非高德地图官方产品，和高德地图不存在合作、授权或数据来源关系。 | |
| 汽车后市场渠道洞察专家 汽车后市场渠道洞察专家，分析润滑油、轮胎、维修保养和汽服连锁的门店规模、省市分布、服务类型与品牌对比。适用于市场、渠道和战略团队判断强弱市场与覆盖空白。 | |
| 汽服门店销售攻店专家 汽服门店销售攻店专家，结合品牌网络、门店服务类型、位置画像和周边竞对筛选拜访线索。适用于跑店销售、区域经理和渠道开发人员寻找目标门店、比较门店并准备拜访。 | |
| 百度地图地址·汽车后市场渠道洞察 汽服渠道的品牌规模、省市覆盖、服务类型与竞争格局分析。 可将百度地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非百度地图官方产品，和百度地图不存在合作、授权或数据来源关系。 | |
| 百度地图地址·汽车后市场门店网络分析 汽服、轮胎和润滑油品牌的门店网络、区域覆盖与位置画像分析。 可将百度地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非百度地图官方产品，和百度地图不存在合作、授权或数据来源关系。 | |
| 百度地图地址·汽服门店销售攻店分析 跑店销售的目标门店筛选、拜访优先级与周边竞对判断。 可将百度地图中复制出的地点名称和地址文本作为地点输入；基于店店通已发布门店快照生成可核验结论。本 Skill 非百度地图官方产品，和百度地图不存在合作、授权或数据来源关系。 |
36,351–36,400 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.