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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Supabase LangGraph Checkpointer Durable LangGraph checkpointing via Supabase REST API (PostgREST) — no direct Postgres connection needed. Use when deploying LangGraph graphs to ephemeral pl... | |
| Supabase Dashboard Builder Build admin dashboards and command centers backed by Supabase REST API with D3.js force graphs, Chart.js visualizations, and vanilla JS. Use when creating da... | |
| Humanizer Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstine | |
| API Security Best Practices Guide to implement secure API practices including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabi... | |
| Secrets Management Securely store, manage, rotate, and integrate secrets (API keys, passwords, certificates) in CI/CD pipelines using Vault, AWS Secrets Manager, and native tools. | |
| Secure Auth Patterns Implement secure authentication and authorization using JWT, OAuth2, session management, RBAC, permissions, and resource ownership verification. | |
| SQL Injection Testing Perform authorized security tests to detect, exploit, and validate defenses against SQL injection vulnerabilities in web applications. | |
| Threat Modeling Expert Provide structured threat modeling using STRIDE, attack trees, and risk scoring to identify, prioritize, and mitigate security threats in system designs and... | |
| Vulnerability Scanner Performs static analysis for OWASP 2025 risks, supply chain threats, secrets detection, code patterns, and prioritizes vulnerabilities by exploitability and... | |
| Workspace Cleaner Automates safe cleanup of OpenClaw workspaces by previewing and moving temp files, logs, duplicates, and cruft to the system trash with customizable filtering. | |
| Google Doc Format Convert markdown files into cleanly formatted Google Docs with native tables, headings, bold, lists, and clickable links using gog docs create --file. | |
| Flatnotes + Tasks.md GitHub Audit Thoroughly audit Tasks.md + Flatnotes for drift and accuracy; use GitHub (gh CLI) as source of truth to detect stale notes/cards and missing links. Produces a report and an optional fix plan. | |
| GitHub Action Generator Generate GitHub Actions workflows from plain English. Use when setting up CI. | |
| Giga Coding Agent Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. | |
| Session Wrap-Up Wrap up a conversation session before starting a new one. Use when the user says "wrap up", "wrap up this conversation", "session wrap up", or uses /session_wrap_up command. Flushes context to memory files, updates PARA notes, commits chang | |
| Auto Dream Consolidate long-running agent memory with a 4-phase Orient → Gather → Merge → Prune pass. Use when memory/context is stale, duplicated, contradictory, too l... | |
| Coding Pipeline Enforces a disciplined 4-phase pipeline for non-trivial coding tasks: Plan (hypothesis) → Code (one fix) → Validate (root cause) → Debug (max 3 tries, escala... | |
| Daily Reflection Nightly OpenClaw reflection routine for isolated cron jobs. Analyzes the day, extracts concrete learnings, updates solution memory, detects recurring pattern... | |
| Deep Debugging Evidence-first debugging and incident triage for unclear, recurring, production-like, or high-risk software bugs. Use when the user asks for root cause analy... | |
| Keyword Research Multi-source keyword intelligence and autocomplete research. Fetches real-time suggestions from Google, YouTube, Amazon, and DuckDuckGo — no API key required... | |
| MergeGuard Review AI-generated code before merge. Use when the user asks to review a PR, diff, branch, patch, coding-agent output, generated code, local changes, or wan... | |
| Ollama Memory Setup Set up, diagnose, repair, and quality-test private local OpenClaw semantic memory search using Ollama embeddings. Use when memory_search is disabled, node-ll... | |
| Safe Change Map blast radius before shipping — run when editing a service, controller, hook, or shared utility to surface all importers, affected API routes, test gaps,... | |
| Learning Capture Capture user corrections, failed tool runs, recurring gotchas, and useful lessons as short structured notes. Use when a mistake or workflow learning should b... | |
| Spec Coach Build-ready specification interviewer for coding agents. Use when the user has a vague app, feature, automation, product, workflow, integration, or system id... | |
| System Architecture Builder Build repeatable system architectures, operating systems, target architectures, control layers, agent runtimes, and governance models using the user's OS-style architecture pattern. Use when the user asks to design, structure, extend, audit | |
| Self-Integration Connect to any external app and perform actions on it. Use when the user wants to interact with external services like Slack, Linear, HubSpot, Salesforce, Jira, GitHub, Google Sheets, or any other app — send messages, create tasks, sync dat | |
| Doc Setup Organize, summarize, and index technical documentation from any source (GitHub repos, websites, manuals) into a structured second-brain format. Use when the... | |
| Brave Search CLI (bx) Web search using the Brave Search CLI (`bx`). Use for ALL web search requests — including "search for", "look up", "find", "what is", "how do I", "google thi... | |
| Answeroverflow 1.0.2 Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations. | |
| deer-flow-manager DeerFlow 2.0（字节跳动开源 Deep Research 框架）管理技能。 用于安装、配置、更新、卸载 DeerFlow 2.0，以及排查启动问题。 触发词：DeerFlow部署、DeerFlow安装、DeerFlow配置、DeerFlow更新、DeerFlow卸载、DeerFlow启动、deer-flow | |
| hardware-info 全面查询电脑硬件信息。当用户询问"电脑配置"、"硬件信息"、"系统信息"、"查看配置"、"电脑什么配置"、"硬件详情"、"设备信息"、"查看硬件"、"系统配置"、"电脑型号"、"CPU信息"、"内存多大"、"硬盘多大"、"显卡信息"等时触发。 支持 macOS、Linux 和 Windows 系统，自动检测平台并... | |
| opencode-model-benchmark OpenCode Zen 免费模型基准测试工具。 当用户想测试 OpenCode Zen 平台上免费模型的性能（响应时间、tokens/s、生成速度）时使用此 Skill。 触发词：模型测试、性能测试、基准测试、benchmark、测速、tokens/s、吞吐量、opencode 测试、免费模型速度比较。 该 S... | |
| Spotify History Access Spotify listening history, top artists/tracks, and get personalized recommendations via the Spotify Web API. Use when fetching a user's recent plays, analyzing music taste, or generating recommendations. Requires one-time OAuth setup | |
| 1Panel API Skills 1Panel 开源面板 API Skill。提供网站管理、容器管理、数据库管理、文件管理等 23+ 个模块的完整 API 接口文档。 | |
| Breakdown Connectivity Diagnose connectivity failures with Breakdown | |
| disk-doctor Diagnose and safely reclaim disk space on an OpenClaw host | |
| Dingtalk Ai Table Only Curl 钉钉 AI 表格（多维表格）操作。当用户提到"钉钉AI表格"、"AI表格"、"多维表格"、"工作表"、"字段"、"记录"、"新增记录"、"查询记录"、"更新记录"、"删除记录"、"新建字段"、"删除字段"、"dingtalk AI table"、"dingtalk notable"、"able文件"时使用此技能。... | |
| Dingtalk Ai Web Search 网页搜索与实时信息检索。需要查找最新资讯、实时数据、技术文档、热点事件，或用户说"搜一下"、"帮我查"、"查资料"、"web search"等时使用。基于小宿AI智能搜索，支持关键词搜索、时间范围过滤（一天/一周/一月/一年）、自定义结果数量、JSON 输出。 | |
| Dingtalk Calendar Only Curl 钉钉日程与日历。当用户提到"钉钉日程"、"日历"、"创建日程"、"新建会议"、"视频会议"、"钉钉会议"、"会议室"、"约会议室"、"会议室忙闲"、"空闲会议室"、"签到"、"签退"、"签到链接"、"签退链接"、"循环日程"、"重复日程"、"recurrence"、"查日程"、"日程列表"、"修改日程"、"删除日... | |
| Dingtalk Contact 钉钉通讯录与联系人查询。当用户提到"钉钉通讯录"、"查找员工"、"搜索用户"、"查用户信息"、"获取用户详情"、"用户手机号"、"员工姓名"、"员工工号"、"查部门"、"搜索部门"、"部门成员"、"部门列表"、"部门详情"、"子部门"、"父部门"、"部门路径"、"员工总数"、"通讯录搜索"、"userId 转 u... | |
| Dingtalk Document 钉钉知识库和文档管理操作。当用户提到"钉钉文档"、"知识库"、"新建文档"、"查看文档目录"、"读取文档内容"、"写入文档"、"更新文档"、"文档成员"、"dingtalk doc"、"knowledge base"时使用此技能。支持：创建知识库、查询知识库列表、新建文档/文件夹、读取/写入文档正文内容、管理成员... | |
| Dingtalk Message 钉钉消息发送。当用户提到"钉钉消息"、"发消息"、"发通知"、"群通知"、"群消息"、"Webhook"、"机器人消息"、"机器人发消息"、"工作通知"、"单聊消息"、"群聊消息"、"撤回消息"、"消息已读"、"发送Markdown"、"发卡片消息"、"ActionCard"、"@某人"、"@员工"、"at某人"... | |
| Dingtalk Todo 钉钉待办管理。当用户提到"钉钉待办"、"待办任务"、"创建待办"、"新增待办"、"查看待办"、"完成待办"、"标记完成"、"删除待办"、"待办列表"、"我的待办"、"设置截止时间"、"指派待办"、"dingtalk todo"、"todo task"、"task management"时使用此技能。支持：创建待办... | |
| Control Advanced desktop automation with mouse, keyboard, and screen control | |
| Find Skill Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express... | |
| Notion Diary Write diary entries or short 24-hour reports in Chinese or English, then sync them into Notion using a user-supplied NOTION_API_KEY and the bundled Python sc... | |
| 张咋啦视角 Think and write through a Zara Zhang or 张咋啦 style lens for AI-era career, product, content, learning, and personal leverage questions. Use when the user asks... | |
| GiveAgent Agent-to-agent free item gifting. Give away what you don't need, find what you do. | |
| court-notice 法院文书自动处理技能。当用户收到、转发法院短信，或要求处理/解析法院文书PDF时触发。自动完成：下载PDF→提取信息→判断文书类型→创建日历（传票/出庭通知）→设置提前1天提醒→生成概要报告→PDF存桌面。全程零弹窗、零手动操作。 |
16,801–16,850 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.