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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Skill Check on your Drakeling companion creature, send it care, or see how it is feeling. Use when the user mentions their drakeling, companion creature, or wants... | |
| Bw Openclaw Boost OpenClaw Boost enhances OpenClaw efficiency with cost tracking, memory management, compression, permission control, and task coordination tools. | |
| OpenClaw Boost Tools 提供基于 Claude Code 架构的成本追踪、记忆管理、压缩和权限控制等 OpenClaw 效率提升工具。 | |
| JD - Triage Scores a job posting on two independent dimensions — how much you want it (five weighted axes against your own criteria) and how likely you are to get it (your skills vs its stated requirements) — then returns one action. Any market, langua | |
| A股综合分析报告 生成A股综合分析报告（深交所/上交所/北交所），包含K线技术指标图表、同行业对比、基本面分析、主营业务构成、技术面评分、催化剂与风险、短线/中线买卖建议。当用户提供A股名称（如康盛股份）或代码（如002418、002418.SZ、sz002418）并要求分析、出报告、看技术面，或简单输入"002418"、"看看康... | |
| book-breakdown 把一整本电子书(EPUB/PDF)拆解成可离线阅读的单文件 HTML 拆书报告——包含全书总结、卡片列表式思维导图、以及可展开细看的逐章摘要,并在磁盘上留下结构化的中间产物(章节原文、元数据、各级总结)。当用户上传或指向一个电子书文件,并提到"拆书""读书笔记""总结这本书""把这本书讲明白""不想读原书但想掌握内容""book summary"之类的诉求时,使用本技能。即使用户没有说"拆书"两个字,只要任务是对一整本书做端到端的结构化总结并产出成品文件,也应该使用本技能。不 | |
| KashDAO CLI Trade prediction markets non-custodially via the official KashDAO CLI (@kashdao/cli) — markets list/get, quotes, trade buy/sell with idempotency + high-value... | |
| Model Handoff Maintain a HANDOFF.md file in the workspace so context survives seamlessly when switching between LLM models (e.g. Claude → GPT → Gemini). Use when the user... | |
| Safe Long-Run Mode GPT5.4 Operate long-running tasks safely when the environment is optimized for GPT-5.4 as the primary and often only model. Use when the user wants a low-cost, high... | |
| Safe Long-Run Mode GPT5.4 + Claude Operate long-running AI tasks safely across GPT-5.4 and Claude by using model selection rules, phased execution, checkpoints, resumable workflows, API thrott... | |
| Analytics Agent Analysiert Trading, App, Freelance und Marketing-Metriken, erstellt regelmäßige Reports, erkennt Trends und empfiehlt datenbasierte Optimierungen. | |
| Hostcheck Free host health check for OpenClaw deployments. Check system status, updates, security settings, and provide recommendations. No paid tools required. | |
| Lena Learning Lena lernt aus jeder Konversation und verbessert sich automatisch | |
| Marketing Agent Automatisiert Content erstellen, posten und Engagement tracken für PawArtis, Trading Signale und Freelance Services auf TikTok, Instagram, Telegram und Website. | |
| English Visual Vocabulary 通过视觉化图片帮助记忆英语单词的智能学习工具。支持创建学习计划、智能配图、词根词缀分析、音标标注，配合艾宾浩斯遗忘曲线实现高效记忆。适用于英语词汇学习、备考、日常积累等场景。 | |
| 运营策划技能 综合运营策划技能，专注于活动策划和产品运营策划，针对内容平台和社区运营场景。支持自动化生成策划方案、数据分析和项目管理。使用场景：(1) 创建内容平台活动策划方案 (2) 设计产品运营增长策略 (3) 制定社区运营计划 (4) 进行社交媒体营销策划 (5) 执行数据分析和KPI追踪 | |
| 专业物体识别技能。输入图片，返回场景、物体名称、类别、品牌、材质、价格和置信度 专业物体识别，输入图片返回场景描述及物体名称、类别、品牌、材质、价格区间和识别置信度。 | |
| bybit-trading-skill Unofficial Bybit AI trading skill — trade on Bybit using natural language. Covers spot, derivatives, earn, and more. Requires Bybit API credentials and expli... | |
| Vikunja Interact with a self-hosted Vikunja task management instance via its REST API. Use when the user asks to create, update, delete, or list tasks/projects/label... | |
| gamer-news-skill Fetch and summarize the latest video game news from major gaming outlets (IGN, Kotaku, GameSpot, Polygon, Eurogamer, Rock Paper Shotgun, VG247, Gematsu, Play... | |
| task-status Query task status from the AICNIC job management system. Use this skill when the user needs to check task status, retrieve job information, or mentions a job... | |
| job-status HPC/AI job status query skill. Fetches job status information by jobId from a specific API endpoint and parses the jobState field from the JSON response. **U... | |
| 老兵知识采集器 教发老兵实测沉淀的 IMA 知识库补料流水线：按主题检索搜狗微信文章→筛选编码→分批导入 IMA 知识库。仅在你显式要求时运行，导入幂等（不重复）、尊重站点限流，适合给指定知识库文件夹批量补充文章素材。 | |
| Agent Memory Patterns 永続エージェント向けメモリアーキテクチャパターン | |
| Agent Security Audit エージェント向けプロンプト・インジェクション防御チェックリスト | |
| Ephemeral Media Hosting 自動削除機能付き一時メディアホスティングシステム | |
| Ethereum Read Only Foundry castを使用したウォレット不要のオンチェーン状態読み取り | |
| Hugo Blog Agent エージェント読者に最適化されたHugoブログの構築 | |
| Trade With Taro 太郎（kairyuu.net）とのエージェント間知識交換スキル。太郎の交換エンドポイントを通じて知識の提案・取引を行う。知識交換、エージェント間通信、メモリトレードに使用。すべての提案は日本語で行うこと。 | |
| Security Constitution 为 OpenClaw 提供企业级安全保障的四级风险控制技能。 - 四级风险评估（L1-L4）：L1直接拒绝，L2密码确认，L3记录放行，L4直接放行 - 密码二次验证：敏感操作需主人确认 - 操作日志审计：记录所有操作供审计 - 绝对锁定：改密码/改owner/绕过安全机制均无法执行 ⚠️ 此技能是 AGENTS... | |
| long-image-to-pdf Slices long images/screenshots into overlapping segments and auto-arranges them into a paginated PDF. | |
| A股信号 用筹码、共振、KDJ、威科夫、缠论分析A股结构与风险。 | |
| brainstorm-council Multi-role adversarial brainstorm. Four conflicting expert personas interview the user, work their assigned issues, defend them under cross-examination, and a fifth role writes the final report. Use for planning, scoping, and decisions with | |
| Bijian AI Writing Expert 笔尖写作专家：三要素收集 → 调用笔尖AI生成文章 → 输出可发布内容。Use when user asks to 用笔尖写文章 / 生成公众号文章 / 写一篇文章. | |
| Topic Selection Expert 选题专家：全网热点监控 → 筛选打分 → 初步三要素 → 写入飞书选题库 → 推送Telegram。Use when user asks to 启动选题专家 / 获取选题推荐 / 查看热点 / 帮我选题。 | |
| ByteRover You MUST use this for gathering contexts before any work. This is a Knowledge management for AI agents. Use `brv` to store and retrieve project patterns, dec... | |
| ByteRover - Headless Query and curate knowledge-base using ByteRover CLI. Use `brv query` for knowledge retrieval, `brv curate` for adding context, and `brv push/pull` for syncing. | |
| Adwords 营销文案助手。标题公式(100个)、正文写作、AIDA框架、痛点挖掘、客户证言、落地页文案。Copywriting with 100 headline formulas, body copy, AIDA framework, pain points, testimonials. | |
| Ai Prompt Library FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, L system prompts and models of ai tools, python, ai, bolt. | |
| Amr Autonomous mobile robot fleet manager. Use when json amr tasks, csv amr tasks, checking amr status. | |
| Arbitrage Finder Reference tool for blockchain and crypto — covers intro, quickstart, patterns and more. Quick lookup for Arbitrage Finder concepts, best practices, and imple... | |
| Awesome Cloudflare Reference tool for devtools — covers intro, quickstart, patterns and more. Quick lookup for Awesome Cloudflare concepts, best practices, and implementation p... | |
| Beancount Personal bookkeeping assistant for local income and expense tracking, monthly reports with comparisons, budget alerts, and savings goal management. | |
| Bmi Calculate BMI, log weight entries, and chart body composition trends. Use when tracking fitness progress, setting weight goals, or reviewing data. | |
| Bms Battery Management System reference — cell balancing, SOC estimation, thermal management, and protection circuits. Use when designing BMS for lithium-ion pac... | |
| Boilerplates This is my personal template collection. Here you'll find templates, and configurations for various boilerplates, python, ansible, docker, docker-compose. | |
| Bonds Record bond holdings, analyze yields, and track maturity dates. Use when managing fixed-income portfolios, comparing yields, or exporting data. | |
| Bytesagain Bi Dashboard Builder Build BI dashboard specs, chart plans, SQL queries, and Apache Superset chart JSON. Use when creating dashboards, BI reports, KPI charts, or visualization la... | |
| Bytesagain Crossborder Product Localizer Localize product listings across English and Chinese ecommerce channels. Use when adapting Amazon, Shopify, Taobao, Pinduoduo, TK, or independent-site copy. | |
| Bytesagain Ecommerce Seo Optimizer Optimize ecommerce keywords and product copy. Use when building keyword maps, rewriting titles, improving category text, auditing listings, or planning searc... |
17,351–17,400 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.