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 Manager Deploy, harden, and operate OpenClaw across local and hosted environments (Fly.io, Render, Railway, Hetzner, GCP) with secure defaults, channel setup guidanc... | |
| Website Manager Create, recreate, redesign, publish, and operate websites managed from Notion, including blogs, CMS-driven sections, widgets, filtering/search interactions,... | |
| PRD-review 自动化审查商业化产品需求文档的逻辑准确性与闭环性，提取界面/功能/商业化设计要点并划分高-中-低优先级，输出设计师友好的标准化梳理文档；当用户需要审查PRD、梳理设计要点、划分设计优先级或快速对接开发时使用 | |
| Agent Memory Cleanup Clean and audit long-term agent memory files such as user.md, memory.md, memories.md, profile.md, preferences.md, and agent_memory.md. Use when the user expl... | |
| Agent Workspace Hygiene Use this skill only when the user explicitly asks for a dry-run cleanup inventory, disk-space cleanup, deletion review, or recoverable archiving of generated... | |
| Hermes Continuation Maintainer Diagnose and repair Hermes Agent runs that silently stop and require manual "continue" messages even though no user input is needed. Use this skill when Herm... | |
| Academic Reader (Holli) An AI-powered academic reading assistant that helps you read, summarize, and reflect on technical books using the methodology from Qian Xuesen's "Engineering... | |
| BlogWatcher (Holli) Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI. | |
| Financial Fraud Analyzer Lite 财务造假风险分析技能。基于财务报表（利润表、资产负债表、现金流量表）评估盈余操纵与会计舞弊概率，输出结构化风险结论与证据链。支持单公司深度分析和批量筛查。Use when user asks to detect financial statement fraud, earnings manipulation, a... | |
| Code Audit Use this skill only when the user explicitly asks for a code audit, security audit, risk-focused PR/diff review, repo or module audit, regression-risk review... | |
| Long Task Handoff Ultra-light automatic handoff manager for long-running agent sessions at context-boundary moments. Use this skill when a runtime reports context compaction/s... | |
| Trinity Evolution Audit and operate the Trinity/OpenClaw evolution loop by validating status, preflight, capability gates, repair fallback, and user progress reports. | |
| Universal Document Ingestion Router Document parsing and knowledge-base import router. | |
| Search Search the web using multiple engines (Tavily, multi-search-engine, or SearXNG) | |
| Bilibili All In One 1.0.12 A comprehensive Bilibili toolkit that integrates hot trending monitoring, video downloading, video watching/playback, subtitle downloading, and video publish... | |
| codex-mcp-dev Use the local Codex CLI through mcporter and codex-mcp-server for real coding work in the current project. Use when the user asks to build features, fix bugs... | |
| Biomedical Literature Search Search biomedical literature from PubMed and bioRxiv for research papers. Use this skill when: (1) Finding research papers on a specific topic or disease, (2... | |
| ChEMBL Query Query ChEMBL database for bioactivity data on drug-like compounds. Use this skill when: (1) Finding compounds active against a protein target (target-based s... | |
| KEGG Query Query KEGG database for drug information, pathway analysis, and disease-drug-target discovery. Use this skill when: (1) Looking up drug information including... | |
| My PubMed Search 简易PubMed搜索技能。使用web搜索和API调用检索PubMed文献。当用户要求"搜索PubMed文献"、"查找医学论文"、"医学文献检索"时使用。 | |
| STRING PPI Query Query STRING database for protein-protein interactions with confidence scores. Use this skill when: (1) Finding interaction partners for a protein of interes... | |
| UniProt Query Query UniProt database for protein sequences, metadata, and search by criteria. Use this skill when: (1) Looking up protein information by UniProt accession... | |
| Echo - OpenClaw Perplexity Ultimate Async Deep Researcher Perform deep, concurrent web research using the Perplexity Search API. | |
| snipit.sh Share code snippets and files securely via snipit.sh with AES-256 encryption. Use when sharing code, configs, logs, diffs, or secrets with password protection, burn-after-read, or auto-expiration. Supports CLI (snipit) or curl API fallback. | |
| AI开发者日报 AI开发者日报 - 每天整理国际和中国AI/开发者新闻，国际在前、中国在后。支持编号回复展开详情。自动定时推送或用户主动触发。 | |
| OpenClaw 新手训练营 OpenClaw 新手训练营 - 通过闯关游戏逐步掌握 OpenClaw 的各项功能。适合刚完成 onboarding 的新用户。触发词："新手训练营"、"bootcamp"、"开始闯关 | |
| 添加QQBot账号 Add new QQ Bot accounts to an existing OpenClaw Gateway instance. Use when a user provides a new QQ Bot appId and clientSecret (or app token) and wants to ru... | |
| DFMEA - Design Failure Mode and Effects Analysis Provides tools to create DFMEA worksheets, calculate risk priority numbers, identify failure modes, and generate reports for smart hardware design risk asses... | |
| TRIZ Systematic Innovation Method Systematically analyze technical problems and generate innovative solutions using TRIZ's Five Bridges methodology with user experience insights and automated... | |
| Coze-Power Bridge your Coze bots to local machine capabilities. Coze bots run in the cloud and can't access local files, run commands, or control your machine — Coze-Po... | |
| ternivo-connect Use Ternivo Connect from OpenClaw for controlled social-media account health, capability checks, preflight, publishing, scheduling, verified delivery receipts, retries, diagnostics, analytics, inbox/community, listening and calendar workflo | |
| 平台视频转md 从 B 站、YouTube 等视频网站下载视频或音频，再用 MarkItDown 在本机转写成 Markdown。当用户给出视频链接并提出“下载视频”“把视频/网课/会议录像/播客转成 md、文字稿、笔记”，或要批量整理在线课程时使用；不做媒体格式转码，也不代替网页搜索与研究。 | |
| morrisons Automated search and insertion of grocery items to your active Morrisons supermarket trolley, viewing basket contents, listing delivery slots, reserving slots, managing shopping lists, and viewing previous orders. | |
| Starloop Analyzes StarFocus todo folder to recommend the top 3 tractable tasks based on priority, star role, and urgency, noting any blocked tasks with fixes. | |
| summarize-outstanding-work Summarize all outstanding work not merged into main/default branch (including unmerged branches, open PRs, uncommitted changes, and stashes) | |
| Agentic Engineering AI Agent 工程化实践框架。以协调型范式为核心，在任务交付型（端到端交付）与状态维持型（事件触发）之间做出正确选择，并按分支执行。触发场景：（1）涉及多 Agent 协作的系统设计；（2）需要选择架构范式的决策场景；（3）coding/composing/supervising/量化交易 任意分支的任务执行。 | |
| Agentic Beehive MCP Server 蜂巢动态调度中枢 MCP Server — 为 AI Agent 提供态势感知、分支调度、外在群落管理。金鱼脑模型的体外记忆和群体能力骨架。 | |
| Lyrics Search Search song lyrics by title and artist using the LrcApi public API. Use when the user asks to find, display, or print lyrics for a song. | |
| API Doc Generator Automatically generate OpenAPI/Swagger API documentation by analyzing function signatures and extracting parameter and return types from Python, JavaScript,... | |
| Clawra Selfie (MiniMax) Generate AI images using MiniMax or fal.ai (Grok Imagine) and send to messaging channels via OpenClaw | |
| Code Flow Visualizer Convert Python, JavaScript, or TypeScript functions into Mermaid flowcharts to visualize code logic and structure clearly. | |
| Data Format Converter Convert data efficiently between CSV, JSON, XML, YAML, and TOML formats including batch processing for CSV↔JSON, JSON↔YAML, XML↔JSON, and TOML↔JSON conversions. | |
| Dockerfile Generator Automatically generate optimized Dockerfiles for various app types with multi-stage builds and best practice performance enhancements. | |
| Doubao Image Use Zhipu (智谱) web search API for searching the internet. Use when user asks for web search, latest news, or needs current information. | |
| Error Message Decoder 解析常见错误代码，提供错误原因及对应解决方案，支持多语言显示。 | |
| Git Flow Helper Assist with Git branch management, merging, rebasing, cherry-picking, and cleaning merged branches for smoother workflow. | |
| JSON Formatter Format, validate, compress JSON data, and extract JSON paths for improved readability and structure verification. | |
| Log Anomaly Detector 智能实时分析日志文件，识别错误、警告、安全威胁和性能问题，并提供异常检测与优化建议。 | |
| Minimax Tts Use Zhipu (智谱) web search API for searching the internet. Use when user asks for web search, latest news, or needs current information. | |
| Minimax Video Use Zhipu (智谱) web search API for searching the internet. Use when user asks for web search, latest news, or needs current information. |
36,251–36,300 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.