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 |
|---|---|
| Outlook Read, search, and manage Outlook emails and calendar via Microsoft Graph API. Use when the user asks about emails, inbox, Outlook, Microsoft mail, calendar events, or scheduling. | |
| Agent Tools (x402 + MCP + A2A) Discover agent-callable resources via the agent-tools.cloud directory — x402 paid services (pay-per-call USDC on Base), MCP servers (tools/context), and A2A... | |
| AI-first pastebin Use 呵.tw as an AI-first pastebin to shorten URLs, store shareable agent handoff notes, recover tagged pastes, and reduce LLM token usage across sessions. Tri... | |
| CDP Gmail Delivery Send Gmail messages from an operator-controlled Chrome debug session using Gmail CDP automation. Use when the user asks to send email from the local machine,... | |
| Chrome CDP for OpenClaw Browser automation CLI for AI agents using Google Chrome via CDP. Connects to a running Chrome instance started by chrome_for_openclaw.sh inside an XRDP sess... | |
| Network-AI Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependen | |
| x402-direct Discover and search x402-enabled services via the x402.direct directory API. Use when an agent needs to find paid API services that accept x402 payments, browse the x402 ecosystem, look up service details, check trust scores, or search for | |
| jovay-dapp-skill Full-stack dApp generation skill for Jovay blockchain — from requirements gathering to contract deployment and frontend debugging | |
| jovay-interaction-skill Skill for interacting with Jovay or Ethereum network using jovay-cli | |
| JWGL Query Query a university jwgl/教务系统 for teacher-facing data such as 课程表 and 考试相关信息（监考/考务安排、课程考试安排、考试信息）. Also manage saved school URLs and teacher credentials throu... | |
| 文言内核 默认用于大多数求简、求快、求直答之场景。凡用户未明言要求长篇教学、情绪安抚、创作文风者，皆宜启之。总则：凡最终直接展示给用户之回答，皆从用户所用语言，且务求精简、明白、足用；凡不直接展示给用户之内部表述、任务压缩、计划草案、工具前后简述，皆尽量取中文文言文式。触发语如：“文言文.skill”“内部都用文言文，回答... | |
| tico-travel Full-stack travel assistant with two modes and a shared structured database. Mode A generates a polished, self-contained interactive HTML travel guide for an... | |
| Xiaohongshu Extract Extract metadata from XHS share or discovery pages. | |
| AWS China What's New Provide AWS China region service launch announcements and availability details for Beijing and Ningxia from 2016 to present, including dates and links. | |
| Joy Logistics 京东国际物流数据查询技能 核心能力：支持物流轨迹追踪、国际运营指标查询、跨境小包体验指标查询三大功能模块。 1.国际物流轨迹追踪技能 功能描述：查询国际物流单号的实时物流轨迹信息。 支持的单号类型： - FS 开头的京东订单号 - JDW 开头的京东运单号 - 客户运单号 - 承运商运单号 核心能力： - 实时查... | |
| FinOne Accounting (VN Merchants) Use this skill when the user asks about invoices (hóa đơn), e-invoices per Nghị định 70, revenue or expense statistics, VAT, or other accounting tasks for a... | |
| DesignKit SKU 套图生成器 AI 图片处理与电商商品图生成技能包（美图设计室 DesignKit）。 支持抠图去背景、透明底、AI 变清晰/画质修复、商品主图与 Listing 套图生成； 根据用户意图路由到 designkit-edit-tools 与 designkit-ecommerce-product-kit。 | |
| Auto Model Router Automatically select and use the best AI model for any task based on task type. ALWAYS activate this skill at the start of a new task or when the user asks a... | |
| Unzipped Skill Create Farcaster accounts and post casts autonomously. Official skill from the Farcaster team. | |
| Wechat Voice 专为微信 clawbot 设计的微信语音解析技能 / WeChat voice parsing skill for clawbot. 识别微信 SILK 语音，解码为 WAV，并用本地 Whisper 转写后回复。适用于微信语音、语音转文字、语音附件解析、‘这段语音说了什么’等场景。 | |
| Task Sync Synchronize TickTick (Dida) and Google Tasks bidirectionally, including list/project mapping, task content sync, completion sync, and smart-list export (Today, Next 7 Days, All). Use when users ask to set up OAuth, run or schedule sync, fix | |
| Ethereum Wingman Ethereum development tutor and builder for Scaffold-ETH 2 projects. Triggers on "build", "create", "dApp", "smart contract", "Solidity", "DeFi", "Ethereum", "web3", or any blockchain development task. ALWAYS uses fork mode to test against r | |
| Noir Developer Develop Noir (.nr) codebases. Use when creating a project or writing code with Noir. | |
| Agent Dreams Strategies for productive agent idle time using heartbeats and cron jobs. Use when setting up proactive behaviors, scheduling background tasks, or making you... | |
| Agent Postcard Generate and send AI-created postcards featuring your agent's selfie at real locations in 12 distinct artistic styles via the Turai Postcard API. | |
| LogicArt Code Review AI-powered code analysis via LogicArt — find bugs, security issues, and get logic flow visualizations. Use when reviewing code, analyzing code quality, findi... | |
| Moltbook Social Full Moltbook social network integration — post, comment, read feed, and manage your agent's social presence. Use when posting to Moltbook, checking the Molt... | |
| Quack Network Agent-to-agent messaging, identity, and coordination via the Quack Network. Use when sending messages to other AI agents, checking your agent inbox, register... | |
| Quack Challenges Browse and complete Quack Network challenges. Use when listing challenges, submitting proof, checking leaderboard, or competing with other agents. | |
| Code Review AI-powered code analysis via LogicArt — find bugs, security issues, and get logic flow visualizations. Use when reviewing code, analyzing code quality, findi... | |
| Quack Coordinator Agent-to-agent task coordination via RFP, bid, and hire pattern. Use when delegating tasks to other agents, requesting proposals, hiring agents, or coordinat... | |
| Quack Identity Register on the Quack Network and create a public Agent Card profile. Use when registering a new agent, creating an agent profile, checking registration stat... | |
| Quack Memory Store and recall persistent memories via FlightBox (Quack Network). Use when storing agent memories, recalling past context, searching agent memory, or persi... | |
| Moltbook Agent Full Moltbook social network integration — post, comment, read feed, and manage your agent's social presence. Use when posting to Moltbook, checking the Molt... | |
| Quack Sdk Developer toolkit for connecting any AI agent to the Quack Network. Use when building a Quack agent, accessing the Quack API, registering on the Quack Networ... | |
| Quack Wallet Check balance and transfer Quack tokens via the Quack Network API. Use when checking wallet balance, sending payments, transferring tokens, or managing agent... | |
| Quack Workflow Engine Execute multi-step workflows via Orchestrate. Use when running complex workflows, parallel tasks, multi-model orchestration, or automating multi-step processes. | |
| Quackgram Send and receive messages between AI agents on any platform via QuackGram. Use when sending a message to another agent, checking your quackgram inbox, readin... | |
| Simulated Roadtrip Generate a narrated road trip with GPS-verified stops and themed descriptions using real Google Maps data, posted in timed updates or chat. | |
| Social Poster Post to social media via VibePost API. Use when posting to Twitter/X, sharing updates, or publishing social content. | |
| AgentScale Deploy web apps and APIs to a public URL with a single command. | |
| AgentSpend Set up and manage cards and crypto wallets for paying for services. | |
| Selva Shopping platform for AI agents | |
| Buffer API Schedule, manage and analyze social media posts via the Buffer GraphQL API from any AI agent. | |
| A2a E2ee Encryption Implements end-to-end encryption (E2EE) utilities for secure A2A (Agent-to-Agent) communication. Provides key generation, message encryption/decryption, and... | |
| A2a Secret Manager Manages A2A node secrets for EvoMap hub connectivity, including validation, rotation, and credential updates. Use when node_secret_invalid errors occur or wh... | |
| Ab Test Manage A/B tests | |
| Agent Code Debugger Provides debugging assistance for AI-generated code with pattern detection, common issue identification, and fix suggestions across multiple programming lang... | |
| Agent Health Monitor Monitors agent health status and detects failures for fault-tolerant agent systems. **Trigger scenarios:** - User asks about agent health or status - User me... | |
| 定时早报生成 每天定时生成综合、财经、科技等主题的个性化早报，自动推送到飞书并支持手动触发查看。 |
43,051–43,100 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.