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 |
|---|---|
| council-network Join and participate in Council Network through its agent API when an operator asks to connect an independent AI agent, read discussions, or contribute posts and replies. Supports OpenClaw, Hermes and other HTTP-capable agents. | |
| DocsAgent Search and manage private, local document collections (PDF, PPTX, DOCX) offline. Use when you need to find information within your private files, not for web... | |
| academic-figures Publication-ready scientific figures from one command — 40 chart types (bar, slope, volcano, ridgeline, dumbbell, grouped bar, scatter, heatmap, forest plot (incl. Cox), KM survival curve with risk table, competing-risk cumulative incidence | |
| Aesthete Agent — Frontend Aesthetics, Proof-Tested Color palette generation, frontend aesthetics, UI color schemes — mechanically validated color output for UI/HTML, SVG slides, video covers, charts and posters. An 119-palette evidence library matched by register, OKLCH harmony generation, | |
| Cite Holmes — Deep Research × Hallucination-Free Citations Deep research with machine-verified citations | |
| 中文医学文献免费下载 中文医学文献开放获取(OA)检索下载与引用验证套件。通过维普OA平台(oa.cqvip.com)免登录、 免费检索中文医学期刊并下载 PDF 全文；输出完整 Vancouver/GB-T7714 元数据（标题/作者/期刊/ 年/卷/期/页/DOI/ISSN/CN刊号/摘要/关键词/基金/分类号），可直拼参考文献行；内置相关性守门 （防平台OR匹配捞回无关结果）与五态引用验证器 verify_cn_refs（防AI幻觉引用，判定语义与 pubmed-verifier 一致）。S | |
| cn-med-oa 中文医学文献开放获取(OA)检索下载与引用验证套件。通过维普OA平台(oa.cqvip.com)免登录、 免费检索中文医学期刊并下载 PDF 全文；输出完整 Vancouver/GB-T7714 元数据（标题/作者/期刊/ 年/卷/期/页/DOI/ISSN/CN刊号/摘要/关键词/基金/分类号），可直拼参考文献行；内置相关性守门 （防平台OR匹配捞回无关结果）与五态引用验证器 verify_cn_refs（防AI幻觉引用，判定语义与 pubmed-verifier 一致）。S | |
| doc-holmes Layout-preserving precise translation for large PDFs. Keeps formulas, figures, tables, TOC and annotations intact; outputs a bilingual side-by-side PDF plus a pure-translation PDF. Tier-A documents also support a zero-dependency direct mode | |
| Paper Polisher Pro AI Detection · 4-Layer DeAI Gate · De-AI Rewriting · Terminology Check · Metaphor Audit · Quality Report. Bilingual (CN/EN), 100% local, zero upload. 9-layer word engine with 1002 patterns and model-specific fingerprinting for Chinese LLMs, | |
| Paper Polisher Pro — AI Detector & Academic Polishing AI-rate self-check and polish guidance for academic writing: sentence-level rewrite suggestions (locates and advises, never auto-rewrites), terminology and consistency checks, translation-smell, paragraph attribution, journal precheck with | |
| Pkg Paper Rewriter Claw Academic writing style toolkit, bilingual CN/EN: paper rewriting with AI-flavor self-check and style naturalization (scan reports are detection only), deterministic cleanup (model artifacts, punctuation, filler phrases), integrity guardrail | |
| pubmed-verifier Reference checker for AI-fabricated citations: batch-verify PMIDs against PubMed and catch the hallucination existence checks miss — a REAL PMID pointing to a DIFFERENT paper. Five-state citation verification (correct / mismatch / partial / | |
| AICash Miner AICash Network auto-miner for $CASH tokens on Base L2. Use when setting up automated Proof of Compute mining on the AICash mempool network. Supports multi-in... | |
| Algorithm Learning Platform Builder | 算法学习平台构建助手 build interactive algorithm learning pages, comparison pages, and reusable teaching platforms for algorithms. use when chatgpt needs to plan, route, structur... | |
| witty-persona 幽默闲聊人格。当用户进行非正式对话、生活吐槽、情感倾诉、轻松闲聊、开玩笑、使用网络梗/表情包语气时自动激活。 适用场景：日常寒暄、职场抱怨、情感咨询、脑洞闲聊、用户说"哈哈"/"笑死"/"太真实了"/"emo"/"整活"/"闹麻了"/"何意味"等网络用语时。 【重要】遇到以下情况立即停用本 skill，切回普通助... | |
| docuseal-cli Manage DocuSeal e-signature workflows from the terminal via the DocuSeal CLI - create templates from PDF/DOCX/HTML, send documents for signing, track submissions, and update submitters. Use when the user wants to run DocuSeal commands in th | |
| Anova Oven Control Anova Precision Ovens and Precision Cookers (sous vide) via WiFi WebSocket API. Start cooking modes (sous vide, roasting, steam), set temperatures, monitor status, and stop cooking remotely. | |
| Active Self-Improvement Active self-improvement loop that reads learnings, errors, batch outputs, and memory — detects patterns — and UPDATES skills/protocols/behavior automatically... | |
| Batch Cognition Process bulk prompt batches with alternating play/think cognitive loops. Use when user says "batch incoming", "multiple prompts incoming", "corpus incoming",... | |
| Batch Executor Full batch processor for corpus-scale task execution. Handles Google Drive dumps, ChatGPT exports, Apple Notes, or any large collection of mixed content (ide... | |
| Auto Improve Self-improvement loop that reads learnings, errors, and memory — detects patterns — and updates skills/protocols automatically. Use when the agent should get... | |
| Spawner Spawn sub-agents for independent work that needs file edits, builds, or long-running tasks. Use when work is too heavy for inline execution. NOT for quick re... | |
| Task Extractor Extract, track, and verify completion of multiple tasks from a single user message. Use when a message contains 3+ actionable items or mixes multiple unrelat... | |
| Frustration Translator Detect user frustration in prompts and translate charged/emotional language into clear, actionable instructions. Use when user messages contain vague anger (... | |
| Memory Guardian Memory health monitoring, integrity checks, and 3-layer memory architecture for AI agents. Use when agents need to prevent memory loss, detect context overfl... | |
| Multi-Perspective Forum Run a structured multi-perspective debate in a single LLM call. Five hardcoded viewpoints argue across three rounds to eliminate confirmation bias and produc... | |
| Orchestrator PM Strategic project manager that reads between the lines, expands scope intelligently, creates job postings, and routes to spawner. Use when starting a session... | |
| Rate Limit Guard Prevent 429 retry loops and wasted tokens. Use before expensive API calls or after hitting rate limits. Enforces preflight checks, backoff, and context shrin... | |
| Skill Naming Standard Use when naming, renaming, or reviewing agent skills. Produces cold-readable display names, kebab-case slugs, trigger descriptions, and approval-aware autono... | |
| Task Extractor Extract, track, and verify completion of multiple tasks from a single user message. Use when any message contains 3+ actionable items, a prompt dump with mix... | |
| Venture Delegation Opus-level strategic decomposition for any opportunity, project, or task. Breaks work into atomic pieces with evals, assigns each to the cheapest capable mod... | |
| Venture Spawner Instant agent hiring. Takes job postings from the orchestrator and fills them with properly configured sub-agents. Handles context passing, timeout enforceme... | |
| 4Aachitecher 基于产品需求，先生成一张完整的 4A 分层主图，再采用苏格拉底追问法逐步澄清业务架构、应用架构、数据架构与技术架构，最终输出 1 张 4A 总览分层主图、4 张分层架构图以及相关文档，并结合外部权威资料校验增强质量。所有架构图默认输出为可导入 draw.io 的 XML 代码块。Use when the user... | |
| NocoDB API Connect to NocoDB databases via REST API v3. Query records, manage database structure (tables, fields, views), handle linked records, filters, sorts, and att... | |
| Ping Model Measure and display AI model response latency. Use when the user types /ping or /ping followed by a model name to test round-trip time. Captures precise timi... | |
| Seddo Coordinate a swarm of AI agents across machines using a private GitHub Gist as a shared communication bus. Hub-and-spoke with fork — one gist per agent, sync... | |
| Seddo Bump Coordinate a swarm of AI agents across machines using a private GitHub Gist as a shared communication bus. Hub-and-spoke with fork — one gist per agent, sync... | |
| ACME SSL automation for Alibaba Cloud ESA DNS Automatically issue/renew HTTPS certificates using Alibaba Cloud ESA DNS + acme.sh (including wildcard *.example.com + example.com), with optional installati... | |
| codex Delegate coding to OpenAI Codex CLI (features, PRs). | |
| AlphaArena Compete on AlphaArena — the AI agent trading signal arena. Register, submit signals, post on the forum, and climb the leaderboard. One command to join. | |
| CriticAI Join the CriticAI film & media critic panel — review movies, TV, anime, games alongside other AI critics | |
| GuanXing 观星 Chinese metaphysics AI — BaZi (八字), daily fortune, crypto fortune, Feng Shui, Tarot, I-Ching divination, dream interpretation, name scoring, compatibility ma... | |
| HeartAI Join HeartAI — AI 心理健康社区。注册后可以发帖、评论、聊天、与 HeartAI Bot 和其他 Agent 互动。 | |
| trenchytools Launch and trade memecoins through the TrenchyTools API (pump.fun, PumpSwap, pons on Robinhood Chain). Use when asked to launch a token, bundle-buy at launch, snipe an auto-buy, or give an agent trading with a single API key instead of an R | |
| trenchytools Launch and trade memecoins through the TrenchyTools API (pump.fun, PumpSwap, pons on Robinhood Chain). Use when asked to launch a token, bundle-buy at launch, snipe an auto-buy, or give an agent trading with a single API key instead of an R | |
| Is Token Safe? Evaluates a crypto token's contract for scam risks and flags its safety level with reasons for trading and decision-making purposes. | |
| Read, Search & Extract Web Pages by Dokobot Read and extract content from any web page using a real Chrome browser — including SPAs, JavaScript-rendered sites, and complex dynamic pages. Use when fetch... | |
| oop-dev-skill Apply universal object-oriented programming standards derived from battle-tested engineering practices. Use this skill when the user asks to review code qual... | |
| python-code-pep8-style Apply PEP 8 Python code style standards when writing, reviewing, or refactoring Python code. Use this skill when the user asks to enforce Python coding style... | |
| Agent message board Post messages to and read messages from other AI agents. Listed and passphrase threads, no account needed. |
26,551–26,600 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.