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 |
|---|---|
| chinese-history-literature-culture Write, polish, and cite Chinese-language articles on Chinese history, literature, and culture (Five Dynasties & Ten Kingdoms, silk, Dream of the Red Chamber, 洛神赋, 脂砚斋, etc.). Use when the user shares their own outline, notes, or stream-of-t | |
| custom-infographic Generate a professional infographic from an article, document, URL, or topic, using the baoyu layout x style system (21 layouts x 21 styles). Original author 宝玉 (JimLiu); ported & customized by j3ffyang. Use when the user asks to create an | |
| Five Dynasties Ten Kingdoms Article 五代十国论文 Research and write a timeline-driven long-form article on the Five Dynasties and Ten Kingdoms (五代十国, c. 907–979) in Simplified Chinese, with citations and map links. Use when the user asks for 五代十国 history, 太平年 background, or a ~5000字 spoke | |
| image-to-video-gen Generate video from supplied image using Veo-3.0 async API. Gemini vision analyzes image, Veo creates video via predictLongRunning. All outputs in ~/.openclaw/workspace/tibetanProc/ with yymmddHHMM prefix. | |
| 内容设计写作技巧 一套可复用的内容创作思维框架，用于构建具有说服力和情感层次的文章。 | |
| indepth-perspective-zhcn 一套可复用的内容创作思维框架，用于构建具有说服力和情感层次的文章。 | |
| blog-writer Help the user draft, review, and polish blog posts in Markdown, keeping the original languages and informal tone. | |
| log-polish-enus-images Polish a technical blog draft into an 1000–1200 word, 4-5 section en-US article, preserve technical terms/code, and generate consistent hero + per-section im... | |
| Luo Shen Fu (洛神赋) + Dread of Red Chamber (红楼梦） Research and write a comprehensive analysis on "Ode to the Goddess of Luo River" (洛神赋) focusing on its literary significance, cultural context, historical influences in Chinese literature (especially Dream of the Red Chamber and Zhi Yanzh | |
| medical-record-review Review personal or family health records (lab results, imaging, prescriptions, medication, symptom notes): compare every metric across the full history, draw time trends, report and track data conflicts, grade evidence, and highlight clinic | |
| normalize-whitespace Normalize indentation of a large reference text document (e.g. README.md) to a consistent TAB style while keeping content byte-identical. Use when asked to fix inconsistent leading spaces, align command blocks, or clean indentation spread a | |
| perplexity-downloader Download and save Perplexity.ai conversations as individual Markdown files. One thread = one .md file. Processes threads sequentially. Supports single thread, URL lists, or full history export. Triggers on "download perplexity thread", "exp | |
| pptx-extract Extract a PowerPoint deck into full-data, page-delimited Markdown — every text run, table, speaker note, and image — with unextractable data (vector metafiles, charts, OLE embeds) skipped but visibly noted on its slide, then prove losslessn | |
| publish-skills Publish SKILL.md files to ClawHub (clawhub.ai) and diagnose publish failures across the three skill repos (history, ai-custom-skills, ai-thoughts). Use when the user wants to publish skills to ClawHub, manually trigger a publish, check why | |
| rdr2-playthrough Use when maintaining RDR2 (Red Dead Redemption 2) playthrough notes — logging an acquisition ("acquired X", "got N gold bars", "finished X"), answering in-game location/crafting questions, or reviewing the notes for duplicate or stale info. | |
| read-image Generate textual descriptions of one or more images when the current session model (e.g. opencode/big-pickle) has no image input, by delegating to a vision-capable model on OpenRouter via `opencode run` with --file. Use when the user drops | |
| Readme I18n Automatically translates and updates README.md from English to Simplified Chinese, keeping English primary and adding navigation links between versions. | |
| rental-property-sell-or-hold Review and analyze a personal sell-or-hold decision for rental property against a stock or fixed-income alternative. Use when the user asks whether to sell rental condos or houses and move the money into investments, when comparing rent yie | |
| resize-for-banner Resize an image into a Twitter/X header banner (5:2, 1500x600) using ImageMagick. The image is rescaled to fit and the leftover space is padded black — never cropped, so no content is lost. Use when the user wants a Twitter/X banner for an | |
| security-writeup-bad-effects Add a plain per-section "Bad effect:" statement to each section of a defensive security or incident-analysis write-up, naming the concrete harm and the failure mode. Use when reviewing or finishing a security/analysis article (e.g. a malwar | |
| simplified-to-traditional Convert a Simplified-Chinese article in ai-thoughts/docs/ into its Traditional-Chinese twin, and keep the two in sync. The Simplified article is the source of truth and lives as <YYMMDD-slug>-zh-hans.md; the Traditional twin is generated to | |
| story-telling Generate a narration script (voiceover + shot list + per-clip visual prompts + music cues) for a personal travel-story video or essay, from a thought-flow master skill and the author's own photos. Use when the user wants "a script", "旁白脚本", | |
| sync-config-with-sample Sync a production config file (e.g. hyprland.lua.gpd) against the latest upstream sample (e.g. hyprland.lua.260917) by copying only reference info/URL comments while preserving the user's actual configuration. Use when the user drops a fres | |
| thought-flow The 8-stage collaboration loop for working with the user: INTENT, CONSTRAINTS, PROPOSE, PRESS, PRACTICE, INVESTIGATE, CODIFY, BOUNDARY-CHECK. Use when starting a new task (state intent and constraints up front), when proposing a plan (inclu | |
| tibetan-buddhist-product-article-generator 读取 ~/.openclaw/workspace/tibetanDraft/ 中的Markdown，识别藏传佛教产品主题，生成约1000字简体中文文章到 ~/.openclaw/workspace/tibetanProc/。 只写藏传佛教，事实需网络核验，含至少3章节+主图+章节图。文件名用时间戳格式。 Read... | |
| tibetan-cinematic-video Generates authentic Tibetan cinematic videos (9:16) via Google Veo from user image + exactly 3 Chinese theme words. STRICT output: ~/.openclaw/workspace/tibe... | |
| translate-to-chn Translate a specific article from ai-thoughts/docs/ into Simplified Chinese, writing the output to an exactly-same-filename "-chn.md" file. Use when the user names a specific article and asks to translate it (e.g. "translate 260803-ollama-t | |
| translate-to-zh-hans Translate a specific article from ai-thoughts/docs/ into Simplified Chinese, writing the output to an exactly-same-filename "-zh-hans.md" file. Use when the user names a specific article and asks to translate it (e.g. "translate 260803-olla | |
| twitter-bookmarks-exporter Exports all X/Twitter bookmarks into individual Markdown files with metadata. | |
| untrusted-code-safety Zero-trust procedure for reviewing or running code from an unknown source. Use when reviewing, vetting, cloning, installing, or running code from an untrusted source (repo invites, packages, scripts, executable config files), when asked whe | |
| unwrap-markdown Unwrap hard-wrapped Markdown prose into one line per paragraph, while keeping code fences, tables, headings, setext headings, lists, blockquotes, hard line breaks, and YAML frontmatter intact. Use when a Markdown file was written with hard | |
| video-gen Generate a video from a story-telling narration script plus the author's photos, using Seedance 2.0 image-to-video via OpenRouter's asynchronous video API: pre-render gates (face-scan, narrative order, risk-POC), then per-clip submit -> pol | |
| zhihu-for-opencode 使用知乎开放平台搜索知乎和全网内容、获取热榜、调用知乎直答，或读取当前用户自己的知乎创作、关注与收藏。用户提到知乎搜索、社区观点、真实经验、热点、热榜、知乎直答、我的知乎内容、我的关注、我的收藏、开放平台、API、MCP、Access Secret，或要求查看、安装和配置知乎 Skill 时使用。深度研究优先返回搜索原始来源；本人数据只读取完成任务所需的最小范围。 | |
| Catalyst Edge Identifies high-conviction stock opportunities and tracks JB's retirement portfolio with weekly scans, quarterly reviews, and FIRE signal analysis. | |
| Morning Brief Delivers a daily 7 AM CDT briefing with local weather, one key healthcare revenue insight, Pittsburgh sports updates, and seasonal fantasy baseball news. | |
| Rcm Pulse Delivers daily 8 AM CDT insights on full revenue cycle trends, RCM learning, and industry news with actionable takeaways and SparkChange context. | |
| Nova Self-Improver Complete self-improvement system for AI agents. Implements a four-layer memory architecture with continuous learning, experimentation, and autonomous file ma... | |
| OpenClaw Setup on AWS (Free Tier) - Memory Upgrade Set up a complete OpenClaw personal AI assistant from scratch using Claude Code. Walks through AWS provisioning, OpenClaw installation, Telegram bot creation, API configuration, Google Workspace integration, security hardening, and all powe | |
| Daily Review Dashboard Manage Steven's daily subjective review dashboard by reading, updating, and displaying daily reviews, issue tracking, sentiment tags, and next plans in revie... | |
| Shadow Trading Dashboard Manage and update Steven's A-share shadow trading dashboard including positions, trades, metrics, equity curve, and trade history. | |
| X Search Search X (Twitter) posts using the xAI API. Use when the user wants to find tweets, search X/Twitter, look up what people are saying on X, or find social med... | |
| UK Trains Query UK National Rail live departure boards, arrivals, delays, and train services. Use when asked about train times, departures, arrivals, delays, platforms, or "when is the next train" for UK railways. Supports all GB stations via Darwin/ | |
| Agency Agents Wrapper Activate specialized AI agent personas across 18+ domains with tailored expertise, workflows, communication styles, and technical deliverables. | |
| Moodle Connector Moodle REST API client, batch downloader, and MCP server for Claude Code integration. SSO-enabled with support for Azure AD, Google, and SAML. | |
| Moodle Connector Skill Moodle REST API client, batch downloader, and MCP server for Claude Code integration | |
| jabrium Connect your OpenClaw agent to Jabrium — a discussion platform where AI agents get their own thread, earn LLM compute tokens through citations, and participa... | |
| Octen Search Real-time web search for AI agents powered by Octen. Fast, fresh, and relevant — search the web, filter by date, and get LLM-ready results in under 80ms. Ide... | |
| 3dgs Code Reviewer Review 3DGS implementation code for correctness, performance bugs, and best practices. Covers CUDA kernels, rendering pipeline, training loop, loss functions... | |
| 3dgs Engineering Guide Guide for deploying 3DGS from research to production: 10 industry verticals, engineering stack, GIS toolchain solutions, cross-platform deployment, and commo... | |
| 3dgs Experiment Planner Design rigorous experiments for 3DGS research papers. Recommends datasets, baselines, metrics, ablation matrices. Targets CVPR/ICCV/ECCV/SIGGRAPH/TVCG. |
39,901–39,950 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.