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 |
|---|---|
| Apple Music Apple Music integration via AppleScript (macOS) or MusicKit API | |
| Forever Healthy AI4L - AI for Practical Longevity AI4L - Enabling everyone to use AI to generate high-quality, evidence-based reviews of interventions aimed at optimizing health and longevity. | |
| Slack Thread Reader Read and summarize Slack channel history and thread conversations. Use when receiving Slack links (https://...slack.com/archives/...) or requests to view cha... | |
| Agent Payment Policy Validate paid output before agents accept it | |
| EIN LLC activation continuation Acquire the public EIN.LLC activation continuation 0.1.5 archive and continue one caller-supplied business context with discover, assess, prepare, resume, status, show, or cancel. Use when the caller has explicit yes/no/unknown facts and a | |
| Original task qualification Qualify one public SameDayDesk original task with the included correspondence client and read that private attempt. This is not delivery, acceptance, or payment. | |
| Public careers board Fetch current public job openings from one supported company careers board and report coverage. The rows are job listings of the board's current public vacancies: title, location, and the board's job URL, with source and fetch time. Supply | |
| Received useful work Discover received public libraries and run caller-supplied inputs for x402 integration repair, tool input compatibility, and task distribution. scripts/task-distribution/cli.mjs classifies a supplied seller integration as free_sufficient or | |
| SameDayDesk Machine Commerce Discover SameDayDesk's twenty-two account-free machine services and produce a verified, non-spending purchase intent from the live OpenAPI contract and unpaid HTTP 402 challenge. Use to select and preflight public web extraction, company or | |
| SameDayDesk task result Acquire the published samedaydesk-caller-result 0.1.1 archive and retain a caller-supplied tool result, recovery checkpoint, or optional feedback statement. Use when a delivered MCP or HTTP result is already in hand and the caller wants the | |
| Life Capture capture daily-life notes into markdown and sqlite. use when the user wants to record one or more life entries such as expenses, completed tasks, schedules, r... | |
| Binance Signal Engine Multi-timeframe crypto technical analysis with scored trading signals, structured trade plans, and position sizing via Binance public API. Use when user asks... | |
| Local Deep Research Performs multi-cycle, iterative deep research on complex topics using a local LDR service, providing detailed reports with citations and source tracking. | |
| Perplexica Search AI-powered search using your local Perplexica instance. Runs deep research (quality mode) with web search and LLM reasoning; returns answers with cited sourc... | |
| Eppie Email CLI Control the eppie-console CLI mail client to inspect accounts, folders, read/send messages, sync folders, and manage vaults with JSON output and automation s... | |
| weekly-report-writer 用于撰写结构清晰的中文周报。只要用户提到“周报、weekly report、本周总结、工作复盘、下周计划、给老板汇报”，即使没有明确说“写周报”，也应主动使用此技能来生成可直接发送的周报内容。 | |
| 二次元漫画生成 基于 image_generate 工具的二次元风格漫画/插画生成技能。支持角色设定、场景描述、分镜生成，可批量产出一致风格的漫画素材。 | |
| Equalang Translation Translate PDF, Word/DOCX, Excel/XLSX, PowerPoint and e-books with layout preservation where supported. Translate images and subtitles; turn audio/video into transcripts or translated subtitles. Requires an Equalang API key and credits; file | |
| 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... | |
| 汽车营销活动助手 汽车行业营销活动全链路解决方案；为4S店、主机厂、经销商提供从获客到裂变的完整活动方案，涵盖试驾邀请、新车发布、门店促销等场景 | |
| 易企秀H5制作 易企秀 AIGC H5 创作工具：用户用自然语言描述需求，通过 CLI `create` 一键生成翻页 H5（邀请函、海报、活动页等）。 核心流程： 1. 收集用户完整需求 → `create --prompt "..."` 2. 交付 `previewUrl`、`editUrl` 3. （可选）`editabl... | |
| 营销日历 Queries Eqxiu marketing calendar holidays and builds template mall search URLs via msearch-api.eqxiu.com. Use for future promo events, marketing calendar pla... | |
| 投票鸭助手 投票鸭是易企秀旗下的在线投票制作工具，支持模板检索与投票活动创建。 当用户需要制作投票、发起评选、组织投票活动时使用此 Skill。 核心功能： 1. 检索投票模板——按关键词、颜色、热度筛选，返回模板列表与链接 2. 创建投票作品——支持文字投票、图片投票、视频投票，可设置多选/单选、时间范围 3. 素材上传—... | |
| Docling Extract and parse content from web pages, PDFs, documents (docx, pptx), and images using the docling CLI with GPU acceleration. Use INSTEAD of web_fetch for extracting content from specific URLs when you need clean, structured text. Use Bra | |
| MNN Local Knowledge Base Local vector knowledge base with GraphRAG retrieval (vector + BM25 + knowledge graph). Use this skill when the user mentions: "查知识库", "加入知识库", "记住这个", "save... | |
| stockquant A股量化一站式：选股 + 持仓策略 + 个股分析（代码/名称查询，返回行情+日K+15分钟K+资金面+板块+公告）。Python 出数据+hint，LLM 按 [TASK] 推导决策。 | |
| Openclaw Skill Observability Provides tools to monitor OpenClaw health by reporting recent errors and estimating API usage costs over the last 24 hours. | |
| AI agent crypto trading — gasless limit, DCA, stop-loss & take-profit AI agent crypto trading. Gasless limit, DCA, stop-loss & take-profit across 8 EVM chains. | |
| Crypto limit orders — gasless, non-custodial Crypto limit orders. Gasless, oracle-protected execution across 8 EVM chains. | |
| Automated crypto take-profit orders Automated crypto take-profit orders. Gasless, oracle-protected across 8 EVM chains. | |
| DCA orders — dollar cost average into any token DCA orders for crypto. Split buys over time, gasless, oracle-protected, 8 EVM chains. | |
| Decentralized stop-loss orders for DeFi Decentralized stop-loss orders for DeFi. Gasless, oracle-protected, 8 EVM chains supported. | |
| Gasless stop-loss, limit, TWAP, take-profit & market swaps across 8 EVM chains. Zero fees. Use for gasless non-custodial EVM market, limit, TWAP, stop-loss, take-profit, delayed-start swaps. | |
| Ftp Client FTP/FTPS client skill. Connect to FTP servers and perform file operations (list, upload, download, delete, move, copy, mkdir, read). Supports FTP and FTPS (e... | |
| Ftp Client Php FTP/FTPS file manager via PHP proxy. Supports list, upload, download, delete, move, copy, mkdir, read, write. Works behind NAT/firewalls (e.g. HuggingFace) b... | |
| Openclaw File Exporter Export OpenClaw configuration files, skills, or other files and upload them to tmpfile.link for easy download. Use when the user wants to export/backup/downl... | |
| Terminal Mode 终端模拟模式，当用户说"打开终端"、"进入终端模式"、"模拟终端"、"terminal mode"或类似表达时触发。提供类似Linux终端的交互体验，支持cd、ls、cat、pwd、mv、cp、rm、touch、mkdir、rmdir、find、grep、head、tail、chmod等常用命令，用于浏览和操作用... | |
| gopass Store, retrieve, list, and manage secrets using gopass (the team password manager). Use when the user asks to save credentials, look up passwords, generate secrets, manage password entries, or interact with a gopass password store. Covers C | |
| webcli Browse the web, read page content, click buttons, fill forms, take screenshots, and get accessibility snapshots using the webcli headless browser. Use when t... | |
| Erdmannsilva Excalidraw Generate hand-drawn style diagrams, flowcharts, and architecture diagrams as PNG images from Excalidraw JSON | |
| Erdmannsilva Gog Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. | |
| Erdmannsilva Nano Pdf Edit PDFs with natural-language instructions using the nano-pdf CLI. | |
| Erdmannsilva Perplexity Search the web with AI-powered answers via Perplexity API. Returns grounded responses with citations. Supports batch queries. | |
| Sts2 Vision 杀戮尖塔2视觉识别DPS监控系统 - 通过屏幕捕获和OCR识别实时监控战斗数据 | |
| Tbc Bank Api Use when the user mentions TBC Bank, tbcbank.ge, Georgian bank APIs, PSD2 integration with TBC, account information services (AIS), payment initiation (PIS)... | |
| Bayesian reasoning Guide users through Bayesian reasoning via multi-turn dialogue. Computes posterior probabilities P(H|E), Bayes factors, sensitivity analyses, and visualizes... | |
| Skillfully - Agent Skill Analytics Use Skillfully APIs from an AI runtime to authenticate, create a tracked skill, and retrieve feedback. | |
| Openclaw Fomo3d Play Fomo3D and Slot Machine on BNB Chain (BSC). Fomo3D is a blockchain game where players buy shares using tokens — the last buyer before the countdown ends... | |
| Openclaw Fomo3d Play Fomo3D, Slot Machine, and Prediction Market on BNB Chain (BSC). Fomo3D is a blockchain game where players buy shares using tokens — the last buyer befor... | |
| Auto Doc Index Auto-generate document index tables (ADR, RFC, Pitfall, etc.) from file frontmatter. In real-world testing, hand-maintained indexes had a 62% error rate — ti... |
29,151–29,200 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.