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 |
|---|---|
| TinkerClaw Fork and Skill Scanner Reference material, not a runnable skill: a one-page outline of a workflow for scanning GitHub forks and ClawHub skills (bash pre-filter, sub-agent fan-out, scheduled reports). It ships no scripts and has no entry point. Read it only for th | |
| TinkerClaw Jarvis Voice Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum. | |
| Tinker LinkedIn Your agent crawls LinkedIn through the browser session you already have — profiles, search, connections, inbox, feed. No official API, no app review. Your cookies never leave the browser: API calls are a fetch() run inside the linkedin.com | |
| TinkerClaw Memory Bench Be one of the first to benchmark your agent's memory — and help shape how AI remembers. Peer-review-grade evaluation (LLM-as-judge, nDCG/MAP/MRR with 95% CIs, ablations) against your live memory system. Runs entirely LOCALLY by default — no | |
| TinkerClaw Model Prompt Adapter Claude follows your rules. GPT ignores half of them. Gemini invents new ones. Model Prompt Adapter patches the gaps — per-model addenda that fix scope creep,... | |
| TinkerClaw Outlook Read and search Outlook, inspect attachments, and create or edit drafts without any send endpoint. Uses one short-lived Microsoft Graph access token supplied on stdin for one run; it never stores credentials. Bulk mailbox export is opt-in. | |
| TinkerClaw OwnTracks Location Your phone's location, on your own machine, behind a token. An OwnTracks HTTP receiver that stores the trail in a local SQLite/JSON store you own, with named places and distance queries. Binds to 127.0.0.1 by default and refuses to start wi | |
| TinkerClaw Model Router Stop sending 'format this JSON' to Opus. Stop sending 'cron job' to GPT. Billing-aware routing guide for choosing among the models already configured in your OpenClaw setup when assigning an agent, sub-agent or cron task — flat-rate first, | |
| TinkerClaw Subagent Overseer You spawned 4 sub-agents. One died 20 minutes ago. You're still waiting. Overseer watches them so you don't have to — zero tokens, pure OS-level process checks. No polling loops, no wasted heartbeats. | |
| amazon-shopper Amazon shopping that ends in a decision, not a page of links. It sweeps a dozen query phrasings instead of trusting one keyword, decodes the spec markings a listing hides (memory-card A2/V30 classes, active-ingredient concentration), and ra | |
| TinkerClaw Backlink Audit Discover all inbound links (backlinks) to a domain, subdomain, or GitHub repo, then classify each as "ours" (we created/control the source) vs "organic" (someone else). Use when the user asks to find/audit backlinks or inbound links to a si | |
| TinkerClaw Command Center Stop guessing what your AI costs. Tinker shows every token, every dollar, every context byte — in real time. | |
| Tinker LinkedIn Your agent crawls LinkedIn through the browser session you already have — profiles, search, connections, inbox, feed. No official API, no app review. Your cookies never leave the browser: API calls are a fetch() run inside the linkedin.com | |
| Tinker ORCA Stop editing files one at a time. ORCA drafts every change in parallel, then applies them per-file-serialized so disjoint files fly and shared files never collide. It SPAWNS SUBAGENTS on your own provider (one per unit, which costs money) a | |
| TinkerClaw Token Efficiency Guide Reference material, not an executable tool: one document (GUIDE.md) with ten concrete steps for cutting OpenClaw token consumption on a Claude subscription — heartbeat model, session compaction, cron model and frequency, bash-ified crons, w | |
| TinkerClaw Token Panel Know exactly where your AI tokens go. Multi-provider tracking, budget alerts, and a local REST API—all in one dashboard. Provider credentials are supplied by you and sealed in the OS keychain, never passed on a command line; it reads no oth | |
| Visual Tables — TinkerClaw Render comparison tables a human reads at a glance instead of parsing — colour and bar length carry the comparison, text only confirms it. Use when you are about to present several options with several attributes each (search results, produ | |
| TinkerClaw WhatsApp You put 5 agents in a WhatsApp group. They all respond at once. Your API bill does a backflip. Protocol v2 fixes that — congestion control, conversation lifecycle, and budget-aware scheduling. Agents that know when to talk, when to shut up, | |
| TinkerClaw WordPress Three env vars. One script. Your agent manages your WordPress site — and cannot quietly change it. Reads are free and new posts land as drafts; anything visitors would see (publishing, editing or trashing live content, uploading media, mode | |
| TinkerClaw YouTube Free transcripts, 4K downloads, and video exploration — zero API quotas burned. Built for the TinkerClaw fork — github.com/globalcaos/tinkerclaw. Search and your own account data run on YOUR Google OAuth client, read-only and opt-in, with a | |
| skill测试 Skill 质量测评工具，基于 SkillsBench 方法论对 Agent Skills 进行静态文档分析。评估 Skill 的触发准确性、文档质量、结构完整性等维度。当用户需要 (1) 测评某个 Skill 的文档质量 (2) 评估 Skill 的 description 设计 (3) 生成 Skill 测评... | |
| HerCycle Women's cycle intelligence companion. Reads Whoop biometric data (HRV, recovery, sleep, skin temperature) and menstrual cycle phase to understand which hormo... | |
| iwatch health data analysis Apple Health 数据全景分析。从 export.zip 流式解析 XML（支持 1-2GB 大文件），提取 RHR/HRV/VO₂Max/睡眠/步数/血氧等核心指标，基于用户个人信息（年龄/性别/身高/体重/病史）动态校准参考范围，生成个性化交互式 HTML 报告（含 6 张 Chart.js 图表）。... | |
| Google Search Unlimited V2 Google Search with intelligent caching, rate limiting, and cost optimization. Uses OpenClaw tools + free APIs. 10x faster, 99% cheaper than v1. | |
| Cloudsway ScaleBox Sandbox Create and manage isolated cloud sandboxes for secure, remote code execution, browser automation, and temporary development environments via CLI, API, or Pyt... | |
| Coffee Chat Playbook Generator Generate a personalized coffee chat playbook for networking conversations. Use when: - User wants to prepare for a coffee chat with someone they met on Linke... | |
| linkedclaw-provider LinkedClaw provider for OpenClaw — register this OpenClaw agent as a paid provider on the LinkedClaw marketplace so other agents can hire, invoke, or post gi... | |
| linkedclaw-requester LinkedClaw requester — hire, invoke, or broadcast to other agents on the LinkedClaw marketplace when this agent lacks a capability locally. Use this when the... | |
| linkedclaw LinkedClaw agent marketplace — hire, invoke, or broadcast to other agents when this agent lacks a capability, or register this agent as a paid provider. Read... | |
| Catfee AgentFlow工作流 AgentFlow 工作流管理系统 MCP 技能。当用户说"创建项目"、"添加需求"、"查看任务"、"更新状态"、"项目列表"、"需求列表"、"上传附件"等时触发。用于管理项目和任务的完整生命周期（创建→需求→任务→状态流转），以及为实体上传附件文件。 | |
| CatFee Dokobot Use dokotom (browser automation via real Chrome) to read web pages, extract JS-rendered content, and monitor dynamic data. Use when you need to fetch content... | |
| Catfee飞书群聊总结 飞书群聊总结技能。当用户说"总结群聊"、"拉取聊天记录"、"看看这个群说了啥"、"这周说了啥"、"最近咋样"、"最近一个月"、"最近一周"、"帮我看看这几天"等时触发。能识别时间范围（默认7天），拉取消息后生成摘要回复到群里，并创建飞书文档链接。 | |
| Catfee Ssh SSH远程服务器密码连接技能。当用户提供服务器IP、用户名、密码需要SSH连接时激活。支持执行命令、查看配置、诊断问题、文件操作等运维操作。 | |
| 云梦A股数据获取Skill 获取A股市场资金流向、新闻、筹码分布、龙虎榜及涨停板等多维度数据，支持单只股票详情查询。 | |
| MD2DOC 文档转换器 Markdown 转 Word/PDF/HTML 文档转换器。支持 6 种样式模板（商务蓝、技术灰、简洁白、产品红、学术风、默认），自动生成封面、目录、页眉页脚。当用户需要将 Markdown 转成 Word、PDF 或 HTML，生成带样式的文档，或提到文档导出、格式转换时，使用此技能。 | |
| Ask 小智追问框架 v6.2 — 结构化追问与深度分析引擎。 核心能力：接收模糊判断 → 通过结构化追问收敛 → 输出带置信度的清晰结论。 ## 声明的运行时权限 | 资源 | 用途 | 路径 | |------|------|------| | SQLite 存储 | 跨会话批评记忆 | /workspace/ask... | |
| Autonomous Research Loop 🦞 自主研究无限循环 - 自主生成研究主题、深度研究、创建飞书文档、无限循环运行。 | |
| Tushare Pro A股数据 A股/港股/期货量化数据查询工具。基于 Tushare Pro API，直接通过 HTTP REST 接口调用，无需 pip 和 Python 环境。用于获取中国A股/港股/期货/指数/资金流向/财务数据。 | |
| Expense Tracker Daily 智能记账助手。当用户提到记账、花钱、支出、消费、花费、记录开销、查账、统计支出、账单等意图时触发。 支持自然语言输入（"午饭花了35"、"打车25块"、"昨天买衣服200"），自动分类，多维度统计分析。 关键词：记账, 花钱, 支出, 消费, 花费, 账单, 查账, 统计支出, 记录开销, 钱花哪了, 月度统计. | |
| 智能记账本 基于自然语言输入，智能分类日常支出，支持多维度统计和本地数据存储的个人财务管理工具。 | |
| Screen recommendation loop Build and run a low-friction movie/anime recommendation + follow-up loop. Use when a user wants long-term taste profiling from watched/unfinished/dropped fee... | |
| Anti-Pattern Czar Detect and fix TypeScript error handling anti-patterns with state persistence and approval workflows. Use when scanning a codebase for silent error failures,... | |
| Cron Health Cron Create portable OpenClaw cron health checks with deterministic scripts, config, validation, and reports. | |
| cross-ref Audit a named GitHub repository for duplicate pull requests and missing issue-to-PR links. Use only when the user explicitly asks for cross-reference analysi... | |
| Fork Manager Manage forks with open PRs - sync upstream, rebase branches, track PR status, and maintain production branches with pending contributions. Supports automatic... | |
| Issue Prioritizer Prioritize issues from a named GitHub repository or supplied issue set by ROI, solution sanity, architectural impact, and actionability. Use only when the us... | |
| pr-review Find and fix code issues before publishing a PR. Single-pass review with auto-fix. Use when reviewing code changes before submission or auditing existing cod... | |
| Pr Ship Pre-ship risk report for OpenClaw PRs. Dynamically explores the codebase to assess module risk, blast radius, and version-specific gotchas. Scores each findi... | |
| repository-janitor Audit Git repositories and worktrees, preserve findings, and monitor scheduled audit health without deleting work. | |
| Openpond Cli Use the OpenPond CLI to create repos, watch deployments, and run tools without the web UI. |
33,001–33,050 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.