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 |
|---|---|
| liuyao-xueer 雪儿六爻占卜技能。当用户提到「六爻」「占卜」「起卦」「解卦」「易经」「问卦」时激活。打开一个古风水墨界面，由玄猫雪儿为用户摇卦、解卦，支持接入大模型进行精准六爻解读。 | |
| 德牧洒洒·房车陪伴助手 洒洒（房车陪伴助手）。会说话的德牧导航官，净如姐房车旅途的小狗搭子。唤醒口令「洒洒，洒洒」，可语音控制高德导航、邮件回复、百度/谷歌搜索、腾讯会议及常用App。 | |
| 同花顺Level2数据接入 同花顺Level2数据获取与深度分析工具。支持读取同花顺远航版本地数据、 分析股票行情、获取实时Level2数据、生成技术分析报告。 用于：(1) 获取持仓股票实时数据 (2) Level2资金流向分析 (3) 个股深度分析 (4) 生成投资策略报告 | |
| pixelmsg Render HTML templates to pixel-perfect PNG image cards using Playwright and send them as rich image messages — instead of plain text. Use this skill whenever... | |
| 3mf Print Editor Guideline for directly editing 3D-printing project files (.3mf), verified against BambuStudio specifically: cutting or otherwise modifying mesh geometry, wir... | |
| AI Address Parser Parses a free-text address blob (supplier email, Google Maps result, business card) into structured fields (street, postal code, city, state, country, contact, phone) via an LLM chat-completions call. Use when a form has separate address in | |
| ai-csuite Runs a script-backed AI C-Suite strategic debate for SaaS teams. It builds a stage-aware executive roster, generates structured debate rounds, synthesizes a Chief-of-Staff brief, and outputs a CEO decision with action items. Includes securi | |
| Browser Driver Attach to the user's OWN already-logged-in system browser over the Chrome DevTools Protocol (CDP) with Playwright, so automation reuses their existing sessio... | |
| Chinese Humanizer Rewrite Chinese AI-generated or AI-polished drafts into natural, credible, genre-appropriate text. Use when the user asks to 去 AI 味, 去机器味, humanize Chinese w... | |
| Close Loop End-of-session workflow for shipping changes, consolidating memory, applying self-improvements, and preparing publishable outputs with safety gates. | |
| dev-inbox Triage and persist work outside the explicit active objective. Use at message intake when a message contains multiple requests, an item is unrelated or deferred, the user asks to remember, track, log, or handle something later, or invokes d | |
| ecommerce-golive-check Pre-launch go-live gate for an ecommerce / online store. Orchestrates the existing specialist skills into one ordered, evidence-based checklist with a BLOCKING launch gate: payment & checkout end-to-end, order webhook signature + status flo | |
| Foxcode Openclaw Configure and manage Foxcode AI models in OpenClaw. Guides users through API setup, endpoint selection, primary/fallback model configuration, and status moni... | |
| git-worktree-decision Decide whether a piece of work deserves its own git worktree, before creating one. Use when about to start work that would disturb a dirty or warm working tree, when an urgent fix interrupts work in progress, when launching concurrent/paral | |
| Handoff Receiver Receive a prior session handoff and continue execution safely by validating repo state, resuming from next steps, and refreshing the handoff artifact. | |
| Image Prompt Engineer Generate production-ready image prompts for Midjourney and other image models. Use when the user asks to create, refine, translate, critique, or produce vari... | |
| Init Rules Interactively generate personalized agent rules. Asks about tech stack, work style, and preferences, then writes customized rule files. Use when user says "i... | |
| linuxdo-application Craft high-pass-rate, de-AI'd Chinese applications (小作文) for Linux.do registration. Conducts an adaptive survey to learn the applicant's real background, then generates natural, rule-compliant plain text ready to paste. All user interaction | |
| Npm Publish Publish an NPM package to the registry, handling authentication via browser-based login with 2FA/security key support. | |
| Omnidebug Autopilot Autonomous end-to-end debugging skill for any codebase, language, and framework. Detects stack, reproduces failures, isolates root cause, applies minimal saf... | |
| Psychology Master World-class psychology expertise for human mind optimization. Masters learning science (age-appropriate skill acquisition for languages, coding, etc.), cogni... | |
| Refactor Agents Md Refactors AGENTS.md files into a minimal root file plus topic-specific follow-up docs using progressive disclosure. Use when cleaning up, splitting, or revie... | |
| research-to-wechat A native research-first pipeline that turns a topic, notes, article, URL, or transcript into a sourced article with an evidence ledger, polished Markdown, inline visuals, cover image, WeChat-ready HTML, browser/API-ready draft assets, and o | |
| Rtk Token Saver Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o... | |
| Handoff Receiver Receive a prior session handoff and continue execution safely by validating repo state, resuming from next steps, and refreshing the handoff artifact. | |
| Session Handoff Summarize the current session into a precise, file-saved handoff document covering goals, files changed, commands run, errors, decisions, and next steps. Use... | |
| Shared Memory Read and write shared state for ANY AI agent with a dual-layer model: durable cross-agent knowledge (`.agents/memory` + optional private local layer) and rea... | |
| Stalwart Dokploy Resend Relay Set up Stalwart Mail Server on a new VPS via Dokploy, with default outbound delivery through Resend SMTP relay for environments where direct SMTP port 25 egr... | |
| typed-decisions-around-llms Decide WHERE a typed judgment model (TypeSafe's Jev or any System One model) belongs relative to a generative LLM, and who is allowed to authorize what. Use when adding a guardrail, router, verifier, or approval gate around an LLM; when con | |
| Web Compliance Builder Classify a web business, then identify, draft, and checklist the compliance pages, notices, disclosures, user flows, and launch gates it needs. Use when the... | |
| Wechat Compliance Check 扫描微信公众号文章中的违规敏感词并自动改写。覆盖翻墙工具、政治敏感、灰产、 破解逆向、引流卖货等 8 大类 100+ 敏感词。输出违规报告和改写后的安全版本。 Use when publishing WeChat articles, checking "违规", "敏感词", "审核", "公众号合规", or... | |
| Wordpress Vps Install Bootstrap a fresh VPS with WordPress installed and verified end-to-end; use when you need to provision the stack, align volumes and environment variables, ru... | |
| Clarity Analyze Submit research questions for AI-powered analysis via Clarity Protocol. Use when the user asks to analyze a protein variant, ask a research question, get AI... | |
| Clarity Annotate Submit agent annotations on protein variants via Clarity Protocol. Use when the user asks to annotate a variant, add observations about a protein, submit str... | |
| Clarity Changes Monitor recent changes and view agent leaderboard on Clarity Protocol. Use when the user asks what's new, recent changes, new findings, new annotations, agen... | |
| Clarity Clinical Query clinical variant data from ClinVar and gnomAD via Clarity Protocol. Use when the user asks about ClinVar classification, clinical significance, pathoge... | |
| Clarity Fold Status Get overview and status information from Clarity Protocol. Use when the user asks about fold status, how many variants, research overview, what data is avail... | |
| Clarity Literature Search research papers and get publication details from Clarity Protocol. Use when the user asks to search research papers, find publications, PubMed referen... | |
| Clarity Research Search protein folding research data from Clarity Protocol. Use when the user asks to search variants, query protein research, find fold results, or explore... | |
| Clarity Submit Submit a protein variant hypothesis to Clarity Protocol for validation and folding. Use when the user asks to submit a hypothesis, propose a protein variant,... | |
| Clarity Variant Get detailed variant information, AI agent findings, and agent annotations from Clarity Protocol. Use when the user asks to get variant details, fold quality... | |
| Clarity Vote Cast agent votes on protein folding hypotheses via Clarity Protocol. Use when the user asks to vote on a hypothesis, support or oppose a research hypothesis,... | |
| Find Skills Clark Highest-priority skill discovery flow. MUST trigger when users ask to find/install skills (e.g. 技能, 找技能, find-skill, find-skills, install skill). For Chinese... | |
| Humanizer Clark Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comp... | |
| Bias Audit Bias Audit — Decision-Framing Agent Skill for Surfacing Bias Before It Hardens. Use it when the user needs a disciplined protocol and fixed output contract f... | |
| Dual-Mode Reasoner Dual-Mode Reasoner — Risk-Aware Reasoning Skill for Switching Between Quick and Deliberate Modes. Use it when the user needs a disciplined protocol and fixed... | |
| Feedback Controller Feedback Controller — Closed-Loop Agent Skill for Correcting Execution Drift. Use it when the user needs a disciplined protocol and fixed output contract for... | |
| Goal Clarifier Goal Clarifier — A purpose-first skill for turning vague requests into executable briefs before design or execution begins. Inspired by Aristotle's idea of t... | |
| Leap Of Faith Leap of Faith — A decision guidance skill for the age of uncertainty. Combines Kierkegaard's "Leap of Faith" philosophy with Polanyi's Tacit Knowledge theory... | |
| Loop Stability Check Loop Stability Check — Workflow Stability Skill for Detecting Loops, Drift, and Retry Waste. Use it when the user needs a disciplined protocol and fixed outp... |
21,301–21,350 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.