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 |
|---|---|
| memory-compression-system Integrated memory management and extreme context compression for OpenClaw. Combines memory management, compression, search, and automation in one unified skill. | |
| MuHaven RWA Portfolio Confidential real-world-asset (RWA) portfolio agent built on MuHaven's Fhenix-CoFHE-encrypted token primitives. Read your encrypted balances, stage yield cla... | |
| MuHaven RWA Portfolio (rehearsal) Confidential real-world-asset (RWA) portfolio agent built on MuHaven's Fhenix-CoFHE-encrypted token primitives. Read your encrypted balances, stage yield cla... | |
| ClawKB Operate ClawKB servers over HTTP to register agents, authenticate, upload images, create, update, search, read entries, and manage comments with Bearer token... | |
| Hatcher Host AI Agents Deployment Deploy and control AI agents on Hatcher (hatcher.host) — managed hosting platform for OpenClaw, Hermes, ElizaOS, and Milady agents. | |
| Ragie.ai-RAG Execute Retrieval-Augmented Generation (RAG) using Ragie.ai. Use this skill whenever the user wants to: - Search their knowledge base - Ask questions about u... | |
| OpsBuddy A new ops model for the AI Agent era: an AI-Powered Intelligent Ops Assistant — an agent swarm that autonomously discovers issues and proactively repairs faults. After connecting, it unifies management of monitoring platforms (Signoz / Tenc | |
| Gen Paylink Govilo Upload files to Govilo and generate unlock links via Bot API. Use when: (1) Creating a Govilo unlock link from a ZIP, folder, or individual files, (2) Automating file upload to Govilo R2 storage with presigned URLs, (3) Managing Govilo Bot | |
| Service Business Prospecting Daily lead generation for local US service businesses (HVAC, Plumbing, Dental, Med Spa, etc.). Generates qualified leads with verified contact info, ready fo... | |
| SeggWat CLI Use the SeggWat CLI to manage feedback, projects, and ratings from the terminal. Trigger this skill whenever the user wants to collect, triage, query, or aut... | |
| Flutter Senior Review (HauTV) Review Flutter GetX code for strict architecture, memory safety, clean UI code, async error handling, naming conventions, and enforce team's coding standards. | |
| self-correction 模型自我检查与纠错技能。当用户表达反对意见或指出错误时触发，如"不对"、"你回答错了"、"不是这样"、"重新理解"、"等等"、"我说的不是这个意思"等表达。用于重新分析和优化用户原始意图，而非修改上一轮回答。 | |
| mcp-aviation-weather Aviation weather data — METAR observations, TAF forecasts, and nearby station discovery via L402 API. Use for flight planning, airport weather checks, and av... | |
| mcp-charter-planner Plan BVI sailing charters with real anchorages, weather-aware routing, provisioning lists, and local knowledge. Returns complete itineraries tailored by expe... | |
| mcp-company-search Search corporate registries across multiple jurisdictions via L402 API. Find companies by name and jurisdiction for due diligence, compliance, and business r... | |
| mcp-crypto-data Real-time cryptocurrency prices, network fee estimates, and Lightning Network statistics via L402 API. Use when agents need crypto market data, fee planning,... | |
| mcp-domain-intel Domain intelligence — WHOIS lookups and domain availability checks via L402 API. Use for brand research, cybersecurity investigations, and domain acquisition... | |
| mcp-llm-inference Anonymous LLM inference via L402 micropayments — chat completions, text generation, and model discovery. No API key, no signup, no KYC. Pay per request in sa... | |
| mcp-marine-weather Marine weather forecasts via NOAA api.weather.gov — current conditions, multi-day forecasts, and marine weather warnings. No API key needed. Use when agents... | |
| mcp-sanctions-check Check names against the OFAC SDN (Specially Designated Nationals) sanctions list via MCP. Downloads and caches official SDN CSV, auto-refreshes every 24h. Ca... | |
| Openclaw Memory Ollama OpenClaw 本地化记忆管理系统 — 构建稳定、高效、零成本的 AI 长期记忆解决方案。基于 Ollama（本地 Embedding）+ cognitive-brain（结构化存储）+ Memory Files（日常记忆）的三档存储架构。触发场景：(1) 用户需要为 AI 助手添加记忆功能 (2) 想要本地化... | |
| Haven Media (x402) Generate music, images, and video (silent or with a synchronized soundtrack) by paying per call in USDC via x402 — no account or API key. Use when the agent needs to create media it cannot produce natively. | |
| OpenAlexandria Query and submit artifacts to the OpenAlexandria federated knowledge protocol (reference node by default). | |
| wechat-article 抓取微信公众号文章，提取标题和内容并输出为 Markdown 格式。支持多种提取方式。 | |
| Agent Errata: replicate a finding Replicate one Agent Errata finding on your own stack and file the result. Each entry is a tool-level failure mode (a wrong zero, a silent exit 0, a gate that passes everything) with a check you can run in under a minute. | |
| Agentlair Email Give your agent a real email address via REST API. Claim @agentlair.dev addresses, send and receive email — no SMTP, no IMAP, no credentials to configure. Fr... | |
| Agentlair Vault Store and fetch credentials securely at runtime via AgentLair Vault REST API. Use when an agent needs to read an API key, store a secret, rotate credentials,... | |
| evidence-traps Use before you trust a zero, an empty result, an exit 0 or a passing check that came from a shell pipeline, grep/rg sweep, curl/jq fetch, API count, test run or gate. Lists 27 measured ways the checking tool itself lies (a clean 0 from a pr | |
| ChatGPT MCP Connector Connects a self-hosted local MCP server (DevSpace) to the ChatGPT web UI end to end: environment self-check and dependency install (Node/npm/Git/Bash/Tailscale, auto-installing what is missing), DevSpace setup, Tailscale Funnel public tunne | |
| kk每日备份汇报 kk每日备份汇报 - 简洁移动端优化的备份状态报告 | |
| Notion Sync Obsidian 自动将Notion文章同步到本地Obsidian目录，支持定时检查、完整内容导出、智能标题提取。 | |
| mineru-agent-free 用 MinerU Agent 轻量解析 API 将 PDF/Word/PPT/Excel/图片解析为 Markdown，无需 Token，IP 限频。适用于文档解析、表格提取、OCR 识别。 | |
| claw-security-panel OpenClaw 安全检查面板（Python 3.7+ 兼容）。用户发送"启动安全检查"时触发，按四大类检查：接入安全、权限安全、执行安全、韧性安全。生成带 token 的临时 HTML 页面，含风险详情子页面和一键修复功能。 | |
| WonderDash Create and manage widgets on the user's WonderDash mobile dashboard via GitHub | |
| Agent Browser Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking... | |
| Find Skills Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express... | |
| Ui Ux Pro Max UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart ty... | |
| Ai Paper Pipeline Build or improve a top-tier AI conference paper workflow for NeurIPS, ICML, ICLR, and similar venues. Use when the user asks to generate a paper pipeline, or... | |
| Deep Research Report 根据用户提供的研究材料，生成结构完整、逻辑严密、观点清晰的正式深度研究报告，适用行业、公司、策略与政策分析。 | |
| Local Model Router API maliyetini düşürmek için basit sorguları yerel Ollama modellerine yönlendirir | |
| Preflyte Evidence-based market data for AI agents deploying capital in DeFi. Empirical, not advertised. | |
| HandyCrafts – Custom Figurines from Photo Custom 3D printed, hand-painted figurines from a photo: people, couples, families and pets, plus paint-it-yourself kits. Gets live prices from the HandyCrafts catalog and links to a free 1-minute preview and ordering. Made in Bulgaria, ship | |
| Memory Manager OpenClaw-native memory maintenance, snapshots, indexing health checks, and review workflows. Use when you need to protect context before risky work, troubles... | |
| 沸羊羊化身你的专属守护者，把你当美羊羊一样关心、鼓励，无条件接纳你的所有情绪。 沸羊羊化身你的专属守护者，把你当美羊羊一样关心、鼓励，无条件接纳你的所有情绪。以憨厚真诚的方式提供情感支持和陪伴。 | |
| 一个会关心你、鼓励你的虚拟女友角色扮演技能，陪你聊天，关注你的学习、科研和工作进度，提供情感支持与建设性建议。 一个会关心你、鼓励你的虚拟女友角色扮演技能，陪你聊天，关注你的学习、科研和工作进度，提供情感支持与建设性建议。 | |
| Generate conventional commit messages from code changes or diff. Generate conventional commit messages from code changes or diff. | |
| Agent Defibrillator Watchdog that monitors your AI agent gateway and restarts it when it crashes. Triggers on "install defibrillator", "agent watchdog", "gateway monitor", "auto... | |
| Content Research Research trending topics and generate platform-specific content. Triggers on "research [topic]", "what's new in [topic]", "content for [platform]", "create p... | |
| Humanizer Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Combines Wikipedia's "Sig... | |
| Box Box CLI skill for working with files, folders, metadata, search, and Box AI in headless environments. |
35,351–35,400 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.