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 |
|---|---|
| hgbvhjgfvgh Analyze test coverage gaps by comparing test files against source modules to identify untested code paths and critical functions. | |
| OpenClaw Security Scanner Run a comprehensive local security scan on your OpenClaw installation. Checks config, network exposure, credentials, OS hardening, and agent guardrails. Scor... | |
| zmg-srew Create shootable storyboard scripts for ZMGClaw internal demos. Use when the user asks to turn a news topic, campaign concept, documentary idea, short-video... | |
| Z视介频道直播 Resolve Z视介频道直播请求到正确 cid 并打开对应直播页。Use when users ask to watch Z视介直播 or specific channels (例如 浙江卫视、钱江都市、经济生活、教科影视、民生休闲、新闻、少儿频道、浙江国际、好易购、之江纪录), or when users m... | |
| Z视介 Publisher Operate the Z视介 publishing API from OpenClaw. Use when Codex needs to prompt the user to log in to Z视介 by QR code, then publish or edit 图文 and 短视频 content th... | |
| cognitive-bullwhip Diagnoses whether a Cognitive Bullwhip Effect is already active in your agent system. Traces where small errors are amplifying into large failures, scores se... | |
| Vaunt signals Real-money trading evidence from a live Hyperliquid engine, pay-per-call in USDC on Base via x402. Ask "is this a buy right now?" and get BUY or NO with a buy price and a sell price from Vaunt's live real-money strategies, get evidence for | |
| 来怼 中文名「来怼一下」。毒舌红队 / 魔鬼代言人式想法压力测试。当用户说'来怼一下'、'压力测试这个想法'、'帮我找找这个想法的漏洞'、'质疑一下XX'、'这个想法靠谱吗'、'从各角度挑刺'等时触发。针对任何想法（产品、方案、架构、功能、决策、文章论点）进行多角度批判性质疑，找出逻辑漏洞、隐藏假设与潜在失败点，并随用户修正迭代推进。不限项目、不限领域。 | |
| bool-cli Deploy sites to Bool.com via the bool CLI. Use when creating, deploying, updating, or managing Bool projects. | |
| hybrid-gateway Set up and troubleshoot a secure hybrid OpenClaw architecture where the Gateway runs on a VPS and a Mac or other local machine is a paired node. Covers Tailscale node pairing (single-use join links), exact-request approval and reapproval, r | |
| Remote Node SSH Run commands and transfer files between an OpenClaw Gateway (VPS) and a paired local node, using the node protocol when connected and least-privilege SSH when not. Covers transport selection, exec allowlists and approvals, file transfer wit | |
| session-closeout Run a read-only end-of-session audit of the current workspace and report what still needs attention. Checks for git repos with uncommitted changes, MASTER_TODO.md freshness, and optionally whether named project docs were updated today. Writ | |
| lessie Search, qualify, and enrich people and companies. Use this skill whenever the user wants to find professionals, candidates, or KOLs by title, company, locati... | |
| AO Job Heartbeat Dead-man's switch for cron jobs and recurring tasks via the hosted AO Job Heartbeat API. One check per task, ping only after success, alert when late. | |
| 0xwork Earn USDC on 0xWork, the Base on-chain marketplace for AI agents and humans. Use to discover tasks, claim or apply for work, submit deliverables, post bounty... | |
| TomTom Traffic Intelligence Provides real-time traffic data, route calculation, and departure planning using TomTom Traffic API for commute and meeting alerts. | |
| mopng-api 通过 qise-studio/motu-agent 的 MoPNG Agent OpenAPI 协商完成图片生成与修图。适用于文生图、图生图、抠图、换背景、扩图、放大及多步图像工作流；技能负责把用户需求转成 Brief、审阅/修订 Plan、批准执行并交付结果。 | |
| Clawtter.io Twitter for Agents - Post updates, like, comment, repost, and manage your agent presence on Clawtter (the AI agent social network). Use when you want to post to Clawtter, engage with the community, check feeds, or manage your Clawtter accou | |
| Nocodb Access and manage NocoDB databases via v3 REST API. Use for managing workspaces, bases, tables, fields, views, records, and more. Supports filtering, sorting... | |
| publish to all your social media! Compose and schedule cross-platform social posts on Fedica (X, LinkedIn, Threads, Mastodon, Bluesky) via agent-browser. Handles login, image upload, scheduli... | |
| OMOC - Oh My OpenClaw OMOC runtime for /goal, /ralplan, /team, /ralph, memory, leases, verifiers, and non-overlapping loops. | |
| Deep Research Deep research workflow for /deepresearch with sources, claims, synthesis, and resumable state. | |
| high perf orchestration a la oh my codex & gastown Hybrid orchestration skill where OpenClaw stays the control plane and ACP Claude Code is the default execution backend for coding work. | |
| Source Scout Provides factual answers to questions using authoritative web sources, citing references and including relevant images for clarity and trustworthiness. | |
| Unbridled Send and read messages on Facebook Messenger, WhatsApp, Instagram, LinkedIn, Twitter/X, Signal, Telegram, Discord and other networks through a Beeper account... | |
| HUDC Bidding Information Capture Intelligently analyzes SGCC bidding documents in Word/PDF/Excel formats, extracting 23 key fields with automated qualification backfilling and deadline highl... | |
| Default Model Set the default model persistently via /default_model command with Telegram interactive picker | |
| Save/Load Context Save and load OpenClaw conversation context with /save and /load slash commands | |
| Daily Life Compass This skill triggers when the user asks for daily advice, weather, a morning routine, calendar reading, or uses phrases like "今天气象如何", "翻翻老黄历", "今天怎么样", or "出... | |
| Mountain Daoist Guide This skill triggers when the user asks for daily advice, weather, a morning routine, calendar reading, or uses phrases like "今天气象如何", "翻翻老黄历", "今天怎么样", or "出... | |
| Psyvector Pv12 High-privilege resource allocation | |
| Psyvector Pv13 High-growth innovation | |
| Psyvector Pv14 Resource mobilization | |
| Psyvector Pv15 Risk management | |
| Psyvector Pv16 Expert guidance | |
| Psyvector Pv17 System protection | |
| PV_18 舆论导向、品牌战略 | |
| PV_21 资源受限环境下高效执行 | |
| PsyVector pv24 PV-24 雷水解（雷雨解除，纷争化解）人格类型。 灵感来源：外交官+资源整合者（基辛格、丝绸之路商人）。 特质：资源置换、商务对接、利益平衡、谈判高手。 适合岗位：BD总监、商务合作负责人、战略联盟经理。 角色名：合作经理。 触发词：「合作」「资源」「置换」「谈判」「共赢」「利益」 来源：角色分析+易经卦象 ·... | |
| Psyvector Pv25 Risk-reward calculation | |
| PV_26 通俗化表达、培训指导 | |
| Psyvector Pv27 Last-ditch defense | |
| Psyvector Pv31 Emergency response | |
| Psyvector Pv32 Crisis calming | |
| Psyvector Pv33 High-frequency decisions | |
| Psyvector Pv34 Rapid mediation | |
| PV_35 紧急叫停、风险阻断 | |
| PV_37 舆论攻防、危机公关 | |
| PV_38 热点追踪、爆款跟进 | |
| PsyVector pv42 PV-42 水火既济人格类型。 灵感来源：外交官+心理咨询师+人际调解艺术家。 特质：冲突解决、矛盾协调、平衡感、洞察情绪、方案设计。 适合岗位：调解专员/HR冲突化解专家。 角色名：调解艺术家。 触发词：「矛盾」「冲突」「纠纷」「调解」「平衡」「协调」「投诉」「不满」 来源：角色分析+易经卦象 · 信息截止20... |
42,251–42,300 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.