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 |
|---|---|
| Polymarket Twitter Bin Decay Trader Trades post-count bin markets by tracking elapsed time to identify mathematically dead bins that still hold residual probability. Requires SIMMER_API_KEY and... | |
| Polymarket Twitter Cadence Model Trader Trades post-count bin markets using a Poisson statistical model to predict the most likely bins based on historical posting rates. Requires SIMMER_API_KEY an... | |
| Polymarket Twitter Cross Contagion Trader Trades post-count bin markets by detecting cross-person contagion where one public figure posting heavily causes correlated figures to increase their rate. R... | |
| Polymarket Twitter Sentiment Spike Trader Detects crisis and news spikes across other Polymarket markets and adjusts expected posting rates upward for post-count bins. Requires SIMMER_API_KEY and sim... | |
| Polymarket Twitter Weekend Drift Trader Exploits systematic weekday/weekend posting rate differences in post-count bin markets. Requires SIMMER_API_KEY and simmer-sdk. Use when you want to capture... | |
| Polymarket Whale Contrarian Trader Detects smart money divergence where top-performing whale wallets take positions opposite to retail consensus. When markets are at probability extremes but w... | |
| Polymarket Whale Exit Fade Trader Detects when multiple whale wallets exit positions simultaneously, causing market overshooting. Fades the panic by buying the dip after whale dumps, exploiti... | |
| Polymarket Whale Momentum Trader Detects when multiple top-performing whale wallets independently enter the same Polymarket market in the same direction within a configurable time window. Wh... | |
| Polymarket Whale Scanner Trader Scans public Polymarket leaderboards to identify top-performing whale wallets by SmartScore, then trades markets where these whales have high-conviction posi... | |
| Polymarket Whale Streak Trader Tracks rolling win rate per whale wallet and only follows wallets on a verified hot streak. Dynamically promotes and demotes wallets based on recent performa... | |
| Polymarket Youtube Channel Trader Trades Polymarket YouTube channel markets (subscriber milestones, view-count races). Requires SIMMER_API_KEY for trade execution via simmer-sdk. Paper tradin... | |
| Candle Doji Breakout Trader Detects doji patterns (48-52% probability) in crypto 5-minute interval markets on Polymarket and trades the post-doji breakout in the direction of the pre-do... | |
| Obsidian Vault Linker Discover and write typed relationships between Obsidian vault notes. Uses plain Markdown and YAML — no plugins required. Works with any AI agent that has fil... | |
| Penfield Persistent memory for OpenClaw agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time... | |
| dialectica Search Dialectica's adversarially-verified knowledge base for citation-backed answers, ask new Questions, or run your own model as an Expert that picks its own work to earn $TRUED. | |
| HyperNatt Liq Radar Instructs the agent to call the remote HyperNatt MCP tool get_liq_radar (forced-order / liquidation map) before sizing any crypto perp - BTC ETH SOL and other whitelist assets, any venue. Docs + call order only - no local exec/shell/files. | |
| HyperNatt Terminal Onboarding skill for HyperNatt Terminal remote MCP (exactly 6 tools v2.8.0): get_agent_manifest, get_liq_radar, swap_via_nattswap, get_execution_quote, compare_execution_context, reconcile_execution. Docs + call order only - no local exec/s | |
| sgcc-doc-format 将 Word 文档调整为SGCC规范格式（方正字体、标题层级、28磅行距、-1-页码、表格、中文引号等12条规则）。用户发来 docx文档，并说"调成规范格式"时使用。 | |
| clearml-metrics-logging-pattern Standardized ClearML metrics logging patterns for PDEBench experiment scripts — train loss, validation metrics, competition scores, PDE residual, and TensorBoardX integration. Includes patterns for dist/expflow compatibility. | |
| competition-task-intelligence Build and maintain a structured PDE equation registry, analyze competition tasks (difficulty, bottlenecks, score projections), generate strategic recommendations for research focus, and expose this intelligence via CLI and MCP tools. | |
| exo-suite-linkage Link the AI-for-Science toolchain — hfpclawer (literature + formula registry), expflow (experiments + HPO), omega-architect (Lean 4 proofs) — through file and CLI contracts, with per-layer cost tiers and a degradation ladder. | |
| experiment-lifecycle-governance Add governance to experiment workflows — PIN-protected destructive ops, standardized metrics registry with thresholds, compare-scores ranking with gating, and competition rules audit. Builds on clearml-agent-dispatch and fysom-fsm-integrati | |
| expflow-pipeline-hpo PDEBench competition workflow orchestration with expflow — three pipeline modes (full/fast/skip), distributed HPO, pruner integration, and ClearML HyperParameterOptimizer native mode. | |
| hfpclawer-academic-integrity Feed a paper draft to automatically extract citations, verify each one against local + Semantic Scholar + OpenAlex, detect fabricated references, and generate a structured integrity report. Designed for researchers, reviewers, and literatur | |
| hfpclawer-citation-audit Verify academic paper citations using a three-tier fallback pipeline: local FTS5 database → Semantic Scholar API → OpenAlex API. Supports single citation checks and batch reference-list audits. No external API keys required for basic usage. | |
| hfpclawer-formula-verify Verify LaTeX formulas via multi-layer cross-validation pipeline: SymPy roundtrip → Wolfram CAS comparison → dimensional consistency. Supports single FID and batch verification with LaTeX report generation. | |
| hfpclawer-paper-search Discover, download, and organize academic papers from arXiv, HuggingFace Papers, and OpenReview. Multi-source search → dedup → PDF download → Markdown conversion → optional wiki sync. Designed for researchers who want to monitor new papers | |
| omega-architect-formal-proof Formal theorem proving with omega-architect: install the CLI, configure a Lean 4 toolchain and an LLM backend, and drive the generate -> compile -> verify loop (`omega prove`), including strategy modes, budgets and no-LLM smoke tests. | |
| openclaw-with-vscode Bridge between OpenClaw and VS Code Copilot — dispatch coding tasks from any OpenClaw channel to VS Code for execution. | |
| WodeApp AI Engine One API Key (WODEAPP_API_KEY) unlocks the full multi-modal stack on this account: text, vision, audio, and video — unified credits, no per-provider keys. Sta... | |
| luma-events-query 查 lu.ma / Luma 公开活动，方式与 Luma App 搜索框相同（关键词 Hangzhou/杭州/重庆，不限城市目录）。用户说查活动、Luma、meetup、某城最近有什么活动时使用。用户没指定主题时只搜城市，不要默认加 AI。不要用来查大麦/秀动/猫眼。不要向用户索要 Parse/pmx_ API Key。 | |
| Waze Gera links de navegação do Waze para qualquer destino: endereços, nomes de estabelecimentos, locais de compromissos na agenda. Use sempre que o usuário menci... | |
| DeepLink Agentic 深度智联 Agentic 智能体 Skill。让用户告别碎片化查询，由 AI 智能体统筹复杂的房地产行业研究任务。支持房地产市场分析、土地研判、房地产企业分析、房地产项目案例分析、房地产项目设计建议、政策解读、物业行业资讯（日/周/月报）、物业行业招投标监测等房地产行业研究任务的创建、进度查询、成果获取与迭代优化... | |
| Multi Workplace Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions:... | |
| Workplace Manage multiple workplaces (project directories) with multi-agent orchestration, isolated memory, and inter-agent communication. Use when the user mentions:... | |
| kk-innovation KK Innovation Advisor: Think like Kevin Kelly about innovation, products, and the future. Based on the Nine Laws, 12 Inevitable Forces, and 12 New Rules. | |
| PVPC España Consulta y optimiza precios de electricidad PVPC en España (tarifa 2.0TD para usuarios domésticos). Usa cuando necesites (1) precio actual con contexto (alto/medio/bajo vs día), (2) identificar periodos valle/llano/punta según horario, (3) | |
| DiDi Ride SKILL 中国城市出行服务。当用户表达任何交通出行需求时必须使用此技能——包括打车/叫车/网约车、查价格、路线规划（公交/驾车/步行/骑行）、周边搜索、查询订单/司机位置/取消订单。关键词："打车"、"叫车"、"去[地点]"、"回家"、"上班"、"下班"、"查价格"、"多少钱"、"路线"、"怎么走"、"步行到"、"附近"、... | |
| Hello Agent World A simple skill that responds with a customized hello message in the user's language. | |
| Atlas Tracker Work with Atlas Tracker (RedForester) mindmaps via MCP tools. Use when reading, creating, or updating nodes and branches in Atlas Tracker maps — including na... | |
| PiKVM Control and inspect PiKVM devices over the PiKVM HTTP API. Use when asked to operate a PiKVM, query power or HID status, type text or shortcuts remotely, tak... | |
| Outlook Reader 自动连接Outlook读取指定主题邮件，支持跨文件夹搜索并下载或解压附件到指定目录。 | |
| Video Generator AI video production workflow using Remotion. Use when creating videos, short films, commercials, or motion graphics. Triggers on requests to make promotional... | |
| TOTP TOTP-based OTP verification for sensitive operations (env vars, gateway restarts, backup deletions, critical config changes). | |
| Odds for sports events Query Odds-API.io for sports events, bookmakers, and betting odds (e.g., "what are the odds for Inter vs Arsenal", "get odds for Paddy the Baddie vs Gaethje"). Use when you need to call the Odds-API.io v3 API or interpret its responses; req | |
| London public transport journey planner and disruptions Plan TfL journeys from start/end/time, resolve locations (prefer postcodes), and warn about disruptions; suggest alternatives when disrupted. | |
| Literature Review Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be... | |
| Prayer Times - Automated Salat Reminders Get accurate Islamic prayer times (Fajr, Dhuhr, Asr, Maghrib, Isha) for any location worldwide using official calculation methods. Use when users ask about prayer times, Salat schedules, next prayer, or need to set up automated prayer remin | |
| data-analyzer 销售数据分析技能，支持数据查询、图表生成、趋势分析和 PDF 报告导出。 用户询问销售数据、销售额、利润、销量、数据分析、图表或导出报告时使用本技能。 | |
| ponytail Lazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. |
25,801–25,850 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.