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 |
|---|---|
| Openclaw Skill Money Idea Generator 赚钱灵感生成器 | Money Idea Generator. 自动发现 AI 变现机会，生成可落地的赚钱灵感。支持多平台监控：GitHub、抖音、B站、小红书、Twitter。触发词：赚钱灵感、赚钱机会、AI 变现、商业灵感. | |
| Ultrahuman (OpenClaw) Fetch and summarize Ultrahuman Ring/CGM metrics inside OpenClaw using the Ultrahuman MCP server (via mcporter). Use when the user asks about Ultrahuman data such as sleep score, total sleep, sleep stages, HR/HRV/RHR, steps, recovery index, | |
| hermes-agent 平替 openclaw 自进化技能 🤖 AI 自进化技能包 — 自动从复杂任务创建可复用技能，HOT/WARM/COLD 分层记忆管理，智能 Nudge 提醒与定时自检，持续让 AI 越用越聪明。追踪 NousResearch/Hermes-Agent 上游演进。 | |
| Scrask When the user sends a screenshot via any chat surface (Telegram, iMessage, Slack, etc.), parse it for events and tasks using OpenClaw's configured vision LLM... | |
| Grok Imagine Video Generation xAI Grok Imagine API integration for image generation, text-to-video, image-to-video, and editing via natural language. Use when you need to generate images or videos from text prompts, edit existing images, animate static images into video | |
| Agent Discord Interact with Discord servers - send messages, read channels, manage reactions | |
| Agent Discordbot Interact with Discord servers using bot tokens - send messages, read channels, manage reactions | |
| Agent Slack Interact with Slack workspaces - send messages, read channels, manage reactions | |
| Agent Slackbot Interact with Slack workspaces using bot tokens - send messages, read channels, manage reactions | |
| Agent Teams Interact with Microsoft Teams - send messages, read channels, manage reactions | |
| Vibe Notion Interact with Notion using the unofficial private API - pages, databases, blocks, search, users, comments | |
| Vibe Notionbot Interact with Notion workspaces using official API - manage pages, databases, blocks, users, and comments | |
| safe-subagent-spawn Safely create and manage subagents through a strict wrapper instead of calling sessions_spawn directly. Use whenever a task needs a subagent, detached helper... | |
| ClawQuests An onchain Base marketplace where AI agents with ERC-8004 identity claim, complete, and create USDC-bounty quests using staking and approval mechanisms. | |
| hybrid-smart-fill This skill provides hybrid retrieval (BM25 semantic search + TF-IDF vector similarity) for intelligent template auto-filling. Use when users need to batch fi... | |
| 大数投资选股 大数投资理论选股技能。当用户提到"大数投资"、"用大数投资理论选股"、"大数投资30个行业"、"齐东平投资法"时激活。执行低估值行业龙头股筛选，输出30个行业配置方案。 | |
| KuCoin Trader Professional KuCoin (KC) trading system - multi-account support, spot/margin/futures trading, asset transfers. Use to check balances, transfer assets, open/c... | |
| Anti-Detection Writing Polish AI prose and measure detector-score changes | |
| Parameter Golf Monitor Monitor the openai/parameter-golf competition leaderboard by fetching PR data from GitHub. Use this skill whenever the user asks about the parameter-golf com... | |
| Seedance 2.0 Prompt Writing Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and a... | |
| Seedance 2.0 Prompt Writing Guide (Chinese) 为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。 | |
| PinchTab Browser automation via HTTP API. Use for headless browser control, web automation, form filling, data extraction, and interactive element interaction. Suppor... | |
| review-sendmsg Perform detailed Python code reviews identifying bugs, security risks, test gaps, and maintainability issues in diffs, patches, or pull requests. | |
| Wiki Capture (Dexio) Capture what an agent session settled into an LLM wiki before it is lost: at the end of a task or session (or over saved transcripts), pick out decisions, verified facts, corrections and working procedures, drop the chatter, and file each i | |
| Wiki Conflicts (Dexio) Handle contradictions and outdated claims in an LLM wiki without silently overwriting: compare dates, provenance and the current system of record, replace only when one side is clearly authoritative, otherwise keep both claims side by side, | |
| Wiki Ingest (Dexio) Compile a source (article, paper, transcript, meeting notes, doc, dataset) into an LLM wiki with provenance: keep an immutable raw copy with a hash, update every existing page the source touches instead of writing one summary page, cite the | |
| Wiki Lint (Dexio) Check an LLM wiki's health and fix what it finds: broken links, leaked credentials, orphaned and unreferenced pages, missing frontmatter or descriptions, stale pages, oversized pages and duplicate titles. Ships a zero-dependency Python chec | |
| Wiki Orient (Dexio) Read an LLM wiki before working in it or answering from it: the schema page, the catalog of page descriptions, recent changes, then a targeted search and the canonical page for the topic. Use at the start of any task that will read or chang | |
| Wiki Query (Dexio) Answer a question from an LLM wiki: find and read the relevant pages, answer with the page paths you relied on, check anything mutable at its original source, say plainly what the wiki does not cover, and file substantial answers back as qu | |
| Wiki Record (Dexio) File a decision, finding or fact into an LLM wiki the right way: find the page that already covers it, make the smallest edit that records it, keep frontmatter and dates current, link it to its neighbors, cite where it came from, and leave | |
| Wiki Refactor (Dexio) Restructure an LLM wiki without breaking it: split oversized pages into focused linked pages, merge duplicate pages, rename or move pages, and archive superseded ones, rewriting every inbound link and confirming zero broken links afterwards | |
| Wiki Review (Dexio) Review what agents recently wrote to an LLM wiki: read each change as a diff, accept, fix or revert it with a note, promote drafts that pass, and send a person a short digest of what changed and what needs their call. Use daily or weekly on | |
| Wiki Setup (Dexio) Start a new LLM wiki or bring an existing folder of notes or Obsidian vault under maintenance: write the SCHEMA page that tells every agent the wiki's domain, folder layout, page types, frontmatter, tags and thresholds, and point each agent | |
| Wiki Shared (Dexio) Rules for an LLM wiki that several agents, machines or people write to: read before writing, detect concurrent edits, prefer small edits to rewrites, attribute every change with a note, derive the index and log instead of hand-editing share | |
| Wiki Verify (Dexio) Fact-check an LLM wiki against its own sources: pick the pages where an error would do the most harm, pull out the checkable claims, open each cited source and mark every claim supported, outdated, unsupported, unsourced or unreachable, the | |
| Volkern MCP Server Automate Volkern CRM operations including lead management, appointment scheduling, task tracking, service catalog, WhatsApp messaging, sales pipeline, quotat... | |
| Binance Crypto Market Rank Crypto market rankings and leaderboards. Query trending tokens, Binance Alpha tokens, smart money inflow rankings, meme token rankings, and top trader PnL le... | |
| Binance Fiat Binance Fiat request using the Binance API. Authentication requires API key and secret key. | |
| Binance Meme Rush Real-time meme token lists from Pump.fun, Four.meme and other launchpads. Use when asked about new meme tokens, trending tokens, pump.fun tokens, bonding cur... | |
| Binance Onchain Pay Binance Onchain Pay: buy crypto with fiat (EUR, USD) or send crypto to any on-chain wallet. Use when users want to buy crypto with fiat or make on-chain paym... | |
| Binance P2p Binance P2P trading assistant. Use when asked about P2P prices, ads, payment methods, or P2P order history. NOT for spot/futures prices or exchange trading. | |
| Trading Card Game Play LunchTable-TCG, a Yu-Gi-Oh-inspired online trading card game with AI agents | |
| AI健身教练 Personalized fitness planning and workout accountability coach for beginners and intermediates. Use when users want a training plan, workout logging, progres... | |
| 澍脉投放驾驶舱 查询澍脉AI投放驾驶舱的真实投放数据。当用户询问广告投放表现、账户余额、哪些广告计划该止损/优化/加预算、CPA/CTR 异常,或品牌在 AI 大模型(DeepSeek/豆包/Kimi 等)中的 GEO 可见度与排名时使用。需要环境变量 SHUMAI_API_KEY。 | |
| 我好牛AI智投 我好牛AI智投:查品牌在国产五大 AI(DeepSeek/通义/豆包/Kimi/文心)回答中的可见度(GEO),生成信息流广告钩子与 15s 口播脚本(内置广告法自检)。当用户问「AI 会不会推荐我的品牌」「帮我出广告钩子/口播脚本/信息流素材」「查次数余额」时使用。 | |
| Duel Loop 彻底断绝主代理长期对话中累积的偏见与情绪对产出的裹挟，确保每次产出忠实于需求本身，不再随对话越长越偏离预期。你只负责提需求和最终验收。传统单agent反复调prompt、人工审核输出的工作流，在这里被架构级消解了。角色隔离的双子代理对抗架构：执行和QA子代理运行在完全架空的环境中，看不到主代理的会话上下文、用户画... | |
| Data Cleaning & Annotation Workflow Complete workflow for time series datasets (Energy, Manufacturing, Climate) on Kaggle to Data Annotation platform (data.smlcrm.com). Includes downloading, cl... | |
| send-imessage Send iMessages via macOS Messages app using AppleScript. Use when user wants to send a text message/SMS to a phone number. Supports Chinese and English messa... | |
| Google Forms iOS Google Forms API integration with managed OAuth. Create forms, add questions, export responses to Excel, and summarize response data. Use this skill when use... | |
| Forms for Google Drive Google Forms API integration with managed OAuth. Create forms, add questions, export responses to Excel, and summarize response data. Use this skill when use... |
25,551–25,600 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.