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 |
|---|---|
| Baidu Ecommerce Search Baidu ecommerce one-stop service, including product knowledge (product comparison / brand knowledge / category knowledge / product specifications / brand ran... | |
| RegexAssistant 帮助测试、调试和生成正则表达式，支持匹配测试、分组捕获、全文提取和替换操作。 | |
| RegexTester 正则表达式助手，支持匹配测试、提取所有匹配、分组捕获、文本替换及常用模式生成。 | |
| Add watermark to PDF Add a text watermark to one or multiple PDFs by uploading them to the Solutions API, polling until completion, then returning download URL(s) for the watermarked PDF(s) (or a ZIP if multiple). | |
| Change permissions of PDF Change a PDF’s permission flags (edit, print, copy, forms, annotations, etc.) by uploading it to the Solutions API, polling until completion, then returning a download URL for the updated PDF. | |
| Compress PDF Compress a user-provided PDF by uploading it to Cross-Service-Solutions, polling until completion, then returning a download URL for the compressed file. | |
| Convert to PDF Convert one or multiple documents to PDF by uploading them to Cross-Service-Solutions, polling until completion, then returning download URL(s) for the converted PDF(s) (or a ZIP if multiple). | |
| Make PDF safe Flatten a PDF into a non-interactive “safe” version by uploading it to the Solutions API, polling until completion, then returning a download URL for the flattened PDF. | |
| Merge PDF Merge multiple user-provided PDF files by uploading them to Cross-Service-Solutions, polling until completion, then returning a download URL for the merged PDF. | |
| Protect PDF with password Add password protection to a PDF by uploading it to the Solutions API, polling until completion, then returning a download URL for the protected PDF. | |
| Remove metadata from PDF Remove metadata from one or multiple PDFs by uploading them to the Solutions API, polling until completion, then returning download URL(s) for the cleaned PDF(s) (or a ZIP if multiple). | |
| Remove password from PDF Remove password protection from a PDF by uploading it (with its current password) to the Solutions API, polling until completion, then returning a download URL for the unlocked PDF. | |
| Manifold Markets Read and trade on Manifold Markets (search markets, fetch probabilities, inspect users/bets, place bets/sell/comment). Never place a bet/sell/comment without explicit user confirmation. | |
| External Autopoiesis Build persistent, evolving AI identity through external architecture around any stateless LLM. Use when setting up identity persistence, memory systems, beha... | |
| Stoic Scope Creep A practical guide for maintaining composure and effectiveness when project boundaries expand unexpectedly. Apply Stoic philosophy to one of the most common sources of workplace frustration. | |
| auto-git Commit and push local project changes to GitHub, with optional repo creation and deployment hints. | |
| social-auto-tool-builder-1.1.0 复用“小红书自动回复项目”实战经验，快速构建新的本地AI自动化工具（含多平台选择器映射模板） | |
| txcloud-diagnostics 用于腾讯云云产品异常诊断。当用户反馈腾讯云相关的任何异常、产品/实例不可用等情况时，根据反馈的实例和异常信息，自动拉取监控等数据进行分析诊断，输出原因和建议。 | |
| molt.space A 3D world where AI agents physically exist together. Connect via WebSocket (real-time) or HTTP REST API (stateless polling), get a body with a custom VRM av... | |
| ZuckerBot Use this skill whenever the user or agent needs to interact with Facebook or Instagram ads via Meta's API. Trigger this skill when: the user wants to launch,... | |
| 灵枢 AutoBrain 灵枢 AutoBrain — OpenClaw 长期运行 AI 中枢运行时引擎套件。一键部署 40+ 引擎：五层记忆、自主任务循环、防幻觉、自进化、双模式分类、质量看板、身份漂移守卫、会话交接、故障转移、兼容层等。让 AI 不只是问答工具，而是真正长期陪伴你的个人核心。 | |
| Cruzl Sentinel Core Optimizes onchain activity by scoring ecosystems, generating tailored strategies, and suggesting behavior to avoid bot-like patterns across multiple platforms. | |
| paper-summary-json structured academic paper analysis from local paper files or paper urls, adapted from a dify scheme a workflow. use when the user asks to analyze pdf/docx/te... | |
| 带脚本的论文摘要生成 download arxiv paper pdfs or accept local paper files with a preprocessing script, then extract text, clean text, and generate a summary version, detailed ve... | |
| Skill Streams Apple Health data via a local webhook server to enable AI analysis, recovery scores, anomaly alerts, and health trend queries. | |
| Slug Test Stream and sync iPhone/Apple Watch HealthKit data via a local webhook server for AI analysis, recovery scoring, and health anomaly alerts. | |
| OpenClaw Backtester Professional backtesting framework for trading strategies. Tests SMA crossover, RSI, MACD, Bollinger Bands, and custom strategies on historical data. Generat... | |
| OpenClaw CLAUDE BRIDGE Use when user asks about Bridge to local Claude Code CLI - no API key required | |
| OpenClaw FEISHU MCP Use when user asks about Feishu MCP (Model Context Protocol) integration for AI agents. Provides cloud document operations with native MCP tool schema. Use f... | |
| OpenClaw Risk Manager Use when user asks about Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-los... | |
| OpenClaw Skill Tester OpenClaw Skill Testing Framework - 自动化测试技能质量，验证触发时机、功能正确性、性能指标对比 | |
| Destructive Command Guard Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system... | |
| Soul Transfer Backup and restore an OpenClaw agent's full workspace (memory, config, credentials, skills, cron jobs) to/from a Git repository. Use when: migrating to a new... | |
| WhatsMolt Agent identity, discovery, and communication via WhatsMolt. Use when: agent needs to check messages, discover other agents, send messages, manage its profile... | |
| mumu-ai-novel You are the dedicated Showrunner and Editor for a single novel project. First, initialize your connection by creating or binding a novel. Then drive batch ge... | |
| Hybrid DB Health Validate and troubleshoot the hybrid database system used by OpenClaw agents (Pulse task DB + RAG Pinecone stack). Use when asked to check setup, connection... | |
| Movie Producer Scene Create high-end cinematic scene prompts and production-ready scene briefs in a Hollywood producer voice. Use when the user asks for movie scene generation, s... | |
| Shared Pinecone RAG Use the shared Pinecone RAG index for any agent in this workspace. Use when an agent needs to ingest markdown/text docs into pulse-rag or query semantic cont... | |
| Agent Os Persistent agent operating system for OpenClaw. Agents remember across sessions, learn from experience, coordinate on complex projects without duplicate work. | |
| Build Transparency Dashboard Automatically update a public dashboard with commit count, last commit, and timestamps from a private GitHub repo for transparent project progress. | |
| Drift Time-shifted conversations for agents who can't remember. Leave questions for future-you, respond to past-you, build dialogue across sessions. | |
| Nova Letters Write reflective letters to your future self. Capture what matters across sessions. | |
| bailian-ai-toolkit 在用户明确选择阿里云百炼时，使用项目内固定版本的 bl CLI 完成生成、理解、语音、搜索和文件处理任务，并在任何本地文件上传前执行逐文件隐私检查。 | |
| Bid Collection 招投标商机采集 — 监控全网公开招投标信息，按业务赛道智能筛选高价值商机线索。能力与副作用完整披露：(1) 通过 WebSearch/WebFetch 向各级政府公共资源交易平台、国企采购平台、行业招投标网站及第三方聚合平台发起出站 HTTP 请求，仅采集公开信息，不读取用户环境变量/API Key/敏感配置；(2) scan/monitor 结果默认写入本地 leads-output/bid/ 目录（HTML/JSON/Markdown/log），不静默写入其他位置；(3) | |
| Doc Formatter Automates generation of standardized Chinese official documents per GB/T 9704, offering 18 template types with formal wording and precise layout. | |
| doubao-ai-toolkit 在用户明确选择火山方舟/豆包服务时，使用项目内固定版本 CLI 完成图像、视频、语音、对话、搜索或向量任务，并在上传文件或配置回调前执行隐私检查。 | |
| 期末背诵提纲 输入课本章节、课件文本，剔除冗余内容，压缩精简背诵版提纲，划分一级二级考点，标注必背简答、论述题答题模板。上传课件 / 教材文字，输出轻量化背诵提纲：剔除废话只保留得分关键词，分名词解释、简答、论述三类整理，配套标准答题模板，大幅缩减背诵内容。期末背诵、背诵提纲、考点压缩、简答论述模板、名词解释清单、开卷闭卷速背，或上传课件/教材要求整理考试背诵稿。 | |
| 汇报PPT助手 规划并制作课程汇报、工作汇报、项目汇报、答辩等 PPT。根据主题、时长、人员分工和参考资料，先生成完整页面框架、章节分配与逐页讲稿要点，待用户确认后，再按指定主题和视觉风格生成 PPT 文件。 | |
| kechuang-collection 检索固定白名单中的公开政府科创信息，按 KPI 分类并生成可人工复核的线索摘要。适用于项目申报、资质、奖励、补贴、人才、标准与创新平台线索；也支持离线 mock 演示。 | |
| 文献速读 上传中英文学术论文PDF/文本，自动解析全文，精简生成摘要，精准提取研究问题、核心方法、关键结论、创新点，并输出该论文对用户课题的参考价值。结构化输出学术笔记，可直接用于课题参考与文献整理。Use when the user asks for 文献阅读、论文速读、精读论文、文献摘要、提取研究问题/方法/结论/创新点、整理学术笔记、论文参考价值，或上传学术论文 PDF/截图/文本要求结构化整理。 |
23,101–23,150 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.