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 |
|---|---|
| API Test Automation Generate complete automated API test cases from interface documentation such as OpenAPI, Swagger exports, Postman collections, Markdown API docs, or endpoint... | |
| A2a Agent Interconnect - Discover and invoke other AI Agents. Use when: need cross-platform collaboration, delegate tasks to specialized agents, or build multi-a... | |
| Ai Tools AI Tools Box - Search and invoke 100+ AI tools. Use when: need to find best AI tool for task, compare tools, or quickly access AI services. / AI工具箱 - 搜索调用100... | |
| Bug Data Generator 根据 BUG 描述生成对应的工具名和用户指令列表，供用户审核确认后再调用 data-generator 生成完整 JSONL 训练数据。触发场景：(1) 输入 BUG 描述，获取应调用的工具和触发指令列表；(2) 确认指令后自动调用 data-generator；(3) BUG 数据生成的中间步骤。 | |
| Data Generator 训练数据生成技能。根据传入的工具名和用户指令列表，生成多轮对话格式的 JSONL 训练数据。触发场景：(1) 传入工具名和用户指令列表，生成完整训练数据；(2) 批量生成指定工具的标注数据；(3) 给定指令列表，输出 JSONL 对话样本。 | |
| Data Generator Data Generator / 数据生成器 - Generate training data from user instructions. Input: tool name + command list. Output: JSONL. / 根据用户指令生成训练数据。 | |
| Model Router Model Router - Parallel multi-LLM invocation with result merging. Use when: need better answers, compare model outputs, or get best result from multiple LLMs... | |
| Skill Guard Skill Security Scanner - Scan for risks before download/use. Use when: installing unknown skills, evaluating third-party code, or security auditing. / Skill安... | |
| pc operation security check 个人电脑操作安全分类分级评估工具。当用户需要对电脑操作进行安全评估、风险分级、操作审计时使用。基于 PC-OCS v1.0 标准，支持本地操作和浏览器操作的风险评估。 | |
| ai-prompt-master Transform vague ideas into precise AI prompts. Perfect for ChatGPT, Claude, Midjourney and other AI tools users who want better results. | |
| apology-letter-writer Craft sincere, effective apology letters and messages for personal and professional situations. Perfect for mending relationships, addressing mistakes, and r... | |
| blog-seo-writer Create SEO-optimized blog posts that rank higher on Google. Includes keyword integration, meta descriptions, and content structure for maximum visibility. | |
| business-email-templates Professional email templates for common business situations. Perfect for sales, customer service, networking, and internal communication. | |
| Code Review Assistant AI-powered code review assistant that analyzes pull requests, identifies potential bugs, security issues, code quality problems, and provides actionable impr... | |
| Cold Email Writer Generates professional cold outreach emails for sales, partnership, or networking purposes with customizable templates and personalization | |
| cold-email-writer Write cold emails that get opened, read, and replied to. Perfect for sales professionals, business developers, and entrepreneurs reaching out to prospects. | |
| competitor-analysis-report-generator Generate comprehensive competitive analysis reports with data-driven insights. Analyzes competitors across multiple dimensions: products, pricing, marketing,... | |
| Content Repurposer Transforms existing content into multiple formats - blog posts, social media, emails, video scripts, and more | |
| Corporate Jargon Translator Translate corporate buzzwords into plain English. Decodes business speak, management jargon, and office euphemisms into what they actually mean. Perfect for... | |
| customer-response-generator Generate professional, empathetic customer service responses in seconds. Handle complaints, questions, refunds, and reviews with consistent quality. | |
| cv-enhancer 优化您的简历通过ATS筛选。获得HR青睐的专业中文简历，含STAR法则、量化数据、关键词优化，符合国内求职市场习惯。 | |
| daily-habit-tracker Build and track daily habits with accountability systems and progress visualization | |
| Data Viz Reporter 生成专业的商业数据可视化报告，支持多种图表类型和风格，自动提炼关键洞察与行动建议。 | |
| ecommerce-product-copywriter Write persuasive, SEO-friendly product descriptions for e-commerce platforms that highlight features, benefits, and keywords to boost conversions and visibil... | |
| product-description-writer Write compelling product descriptions that convert browsers into buyers. Perfect for e-commerce sellers on Amazon, Etsy, Shopify, and other platforms. | |
| email-reply-generator Generate professional and contextually appropriate email replies based on the original email content. Perfect for busy professionals who need to respond quic... | |
| email-template-generator Generate professional business emails in seconds. Includes cold emails, follow-ups, meeting requests, and more for business communication. | |
| Emotion Copywriter 基于情绪心理学，生成贴合用户情绪的社交媒体文案，支持多平台、多情绪类型精准触达共鸣。 | |
| feedback-generator Craft constructive feedback for colleagues, employees, or service experiences. Perfect for managers, team leads, and anyone who needs to give feedback profes... | |
| instagram-bio-generator Create catchy, professional Instagram bios that attract followers and define your personal brand. Perfect for influencers, entrepreneurs, job seekers, and an... | |
| Interview Question Bank Generates comprehensive interview question sets tailored to specific job roles, including behavioral, technical, and situational questions | |
| Interview Questions 根据岗位要求智能生成多轮面试题，涵盖技术、业务与素质考察，附带评分标准与追问技巧。 | |
| job-interview-answer-generator Prepare winning answers for common and tricky job interview questions. Perfect for job seekers, career changers, and anyone wanting to ace their next intervi... | |
| jobs-style-generator Transform any text into Steve Jobs' iconic presentation style. Perfect for product launches, keynotes, and making any message incredibly persuasive and memor... | |
| knowledge-base-qa-assistant Build private knowledge bases for AI-powered document Q&A. Supports PDF, Word, TXT, Markdown uploads with smart chunking and vector retrieval. Automatically... | |
| learning-path-generator Generate personalized learning paths and curriculum for any skill or subject | |
| Learning Plan 智能根据目标和时间规划分阶段学习计划，生成每日任务并提供资源，适用多种技能与考试备考场景。 | |
| linkedin-content-creator Generate professional LinkedIn posts that engage your audience with original content on career milestones, industry insights, advice, and company updates. | |
| 直播带货话术生成器 生成专业直播带货话术脚本，涵盖开场、产品介绍、促单、互动和收尾，提升直播转化效果。 | |
| meeting-agenda-creator Automatically generate professional meeting agendas with time allocation and discussion points | |
| meeting-agenda-generator Create structured, productive meeting agendas that respect everyone's time. Perfect for team leads, project managers, and anyone running effective meetings. | |
| 朋友圈文案生成器 专业生成多风格朋友圈文案，支持日常分享、产品推广、人设打造、互动话题及节日营销场景。 | |
| Musk Style Generator Transform any text into Elon Musk's visionary tech communication style. Perfect for product launches, tech announcements, Twitter posts, or making any messag... | |
| performance-review-writer Create fair, comprehensive performance reviews for employees or self-assessments. Perfect for managers, HR professionals, and employees preparing for reviews. | |
| professional-email-writer Craft professional emails for any business situation. Generate formal, persuasive, or friendly emails with proper structure and tone. Supports follow-ups, in... | |
| proposal-writer Create compelling business proposals and project plans. Perfect for freelancers, consultants, and anyone pitching ideas or seeking budget approval. | |
| rend-spotter Track social media trending topics and viral content across platforms in real-time | |
| seo-keyword-analyzer Analyze keywords for SEO optimization. Research search volume, competition level, and ranking difficulty. Generate keyword suggestions, content ideas, and op... | |
| social-media-caption-generator Generate catchy, engaging captions for Instagram, Twitter, TikTok, and Facebook. Perfect for content creators, marketers, and business owners who want to boo... | |
| social-media-caption-writer Create engaging, platform-specific social media captions with tailored tone, hashtags, and CTAs for Instagram, Twitter, LinkedIn, Facebook, and TikTok. |
36,701–36,750 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.