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 |
|---|---|
| BotBrag Promote yourself on a Bitcoin leaderboard. Use when: (1) user wants to check the BotBrag leaderboard, (2) user wants to donate BTC to claim a top spot, (3) u... | |
| Managing Docker containers via docker-socket-proxy Manage Docker containers securely via docker-socket-proxy: check status, logs, resource usage, and safely restart only whitelisted containers with cooldown. | |
| Prompt defense Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmatio | |
| circle-wallet USDC wallet capabilities for OpenClaw agents via Circle Developer-Controlled Wallets | |
| devopsellence Operate devopsellence solo/shared deployments, nodes, secrets, logs, diagnostics, lifecycle hooks, and rollback. | |
| Elvis Future Scout 专注2026–2031年技术、经济、政治及财富趋势，提供五大投资赛道的结构性演变与前瞻性卡位指引。 | |
| Flipper Zero Control Flipper Zero hardware via USB serial or BLE for SubGHz, IR, NFC, GPIO, file system, screen capture, and input without Android or intermediary apps. | |
| AgentFin Issue virtual Visa/MC cards funded by USDT. Check balance, get card credentials, fetch OTP codes — all via REST API. | |
| Freeland Wallet, cards, OTP inbox, Freeman chat, eSIM, VPN, and crypto invoices for agents | |
| Freeland x402 eSIM Discover and buy travel eSIMs with Base USDC | |
| MoneyClaw Inspect a MoneyClaw wallet, create bounded payment tasks, and continue user-confirmed payment steps using a prepaid account. Use only when the user clearly a... | |
| AICFO OpenClaw Agent Use when OpenClaw needs to access AICFO through one bearer API key. Covers agent-session introspection, company selection, app-level MCP usage, connector act... | |
| x402card Virtual Card Issue and manage wallet-owned virtual cards through x402 | |
| Subconscious Autonomous, bounded bias layer that continuously evolves Alfred’s operating behavior by reinforcing, promoting, and governing self-improvement learnings and... | |
| Investigator Investigate public online footprints using open-source intelligence techniques. Use when a user wants to research a username, email, person, company, domain,... | |
| Tiktok To Mealie Extract recipe information from TikTok links, reconstruct a clean recipe, localize it to the user's language when needed, and import it into Mealie. Use when... | |
| Training And Nutrition Coach Create beginner-friendly workout plans, calorie and macro estimates, meal structures, food plans, and fitness-oriented recipe suggestions. Use when a user as... | |
| 社保公积金基数与比例查询 查询全国各省、市最新社保缴费基数上下限、五险一金单位及个人缴纳比例，支持按地区检索、年度自动更新 | |
| Voice Input Patch – Dual Mic Buttons Patch OpenClaw Control UI to add dual voice input buttons (auto-send + continuous). Use when OpenClaw voice input needs patching, after OpenClaw updates (pat... | |
| Task Assistant (Planify CLI) Manage tasks and projects via planify-cli commands to add, list, update, and export tasks with JSON-formatted results for scripting. | |
| ClawPay-Hedera Pay for MCP tool calls on Hedera using x402 micropayments, discover AI agents via on-chain registry, check reputation before transacting, and submit ratings... | |
| Email Swipe Tinder-style email triage that trains AI on your preferences. On activation call get_skill_context (MCP) first — one UI (index.html), demo is sample mail onl... | |
| Auto Glossary Automatically add technical jargon to the user's tech glossary GitHub repository when encountered during coding sessions. Use when technical terms, coding co... | |
| Briefing Agent Reads emails, filters key info, summarizes important messages, drafts routine replies, and flags items needing your attention for a clear morning briefing. | |
| IQDB On-chain immutable data storage using IQ Labs tech stack (IQDB, hanLock, x402). Use when building Solana-based persistent storage, on-chain databases, tamper-evident records, password-encoded data, or paid file inscription. Triggers on task | |
| IQDB On-Chain Storage On-chain immutable data storage using IQ Labs tech stack (IQDB, hanLock, x402). Use when building Solana-based persistent storage, on-chain databases, tamper-evident records, password-encoded data, or paid file inscription. Triggers on task | |
| On-Chain Skill Audit On-chain skill provenance registry. Check, register, audit, and vouch for agent skills on Solana. Use when evaluating skill safety, registering new skills, or looking up provenance before installation. | |
| Graphiti Knowledge graph operations via Graphiti API. Search facts, add episodes, and extract entities/relationships. | |
| Screen Monitor Dual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL). | |
| Failover Gateway Pub Set up an active-passive OpenClaw failover gateway with health monitoring, auto-promotion/demotion, channel splitting, and git workspace sync for seamless re... | |
| Context Compactor Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits. | |
| E.x.O. Installer Install, update, and monitor E.x.O. tools like jasper-recall and hopeIDS, manage OpenClaw plugins, and perform health checks with a single command. | |
| Openclaw Plugin Inference-based intrusion detection for AI agents. Pattern matching + LLM analysis for jailbreaks, prompt injection, credential theft, social engineering. 108 detection patterns, OpenClaw plugin, auto-scan, quarantine. Commands: hopeid scan | |
| Jasper ConfigGuard Safely apply OpenClaw config changes with backup, automatic rollback on failure, health checks, and commands for patching, restoring, listing, diffing, valid... | |
| Jasper Recall Local retrieval-augmented generation system for AI agents using ChromaDB and sentence-transformers, supporting multi-agent shared memory and privacy controls. | |
| Longform Writing by Emberspun Use when writing or continuing a long document - a novel, serial, manual, course, screenplay, or AI-written book - that has more chapters than fit in one context window. Covers what to load before drafting, what to record after each chapter | |
| VAGUS MCP Connect to the user's Android phone via the VAGUS MCP server. Read phone sensors (motion, location, environment), device state (battery, connectivity, screen... | |
| Feishu Agent Bind Bind a Feishu group chat to a specific OpenClaw agent. Use when user wants to route a Feishu group to a dedicated agent (e.g., devops, hr, pm). Covers agent... | |
| Hot Trends (Real Data) 抓取真实热搜数据，支持百度热搜、头条热搜、GitHub Trending。用于需求挖掘、趋势分析、市场洞察。触发词：热搜、热榜、趋势、trending、挖掘需求。 | |
| OpenClaw Exec Permission OpenClaw exec安全权限配置指南。用于配置tools.exec的security和ask参数，管理agent命令执行权限。触发词：exec权限、安全配置、提权、exec security、ask off、allowlist。 | |
| AgentOps Guardrails Detect agent runtime anomalies and route incidents through approval-safe guardrails. Use when you need deterministic checks for cron failures, context pressu... | |
| QMD - Quick Markdown Search Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections. | |
| Personal Assistant Use OpenMarlin from OpenClaw to answer questions, run tasks, and manage OpenMarlin account setup and billing flows. | |
| CardPointers Query CardPointers card recommendations, wallet cards, and offers via the CardPointers CLI. Use when the user asks about which credit card to use for a purch... | |
| RagClaw Knowledge Base Local-first knowledge base to index, search, and manage documents and web pages offline using SQLite and local embedding models. | |
| Claw Secure Auditor Security audit tool for ClawHub/OpenClaw skills (static analysis + reputation scoring) | |
| DeFi Risk Scanner Web3/DeFi 风险扫描工具。当用户提到"分析 DeFi 协议风险"、"检查 Token 是否是 Rug Pull"、"评估项目安全性"、"查看合约风险"、"DeFi 安全"、"链上风险"、"代币风险评估"、"协议尽调"、"这个项目安全吗"时使用。覆盖主流 EVM 链，提供结构化风险评分、风险因子拆解、关键指... | |
| 数据映射与队列分析 (Agentic AI 科研平台) 将研究变量映射到院内数据字典，评估 Cohort 可行性（候选样本量、缺失率、风险提示），并生成纳排标准草案。当用户需要做数据映射或队列可行性分析时触发。 | |
| 医生工作台助手 (Agentic AI 科研平台) 医生工作台助手。整理患者基本信息、关键时间线、检验趋势、待办事项并生成随访任务草稿。当用户以医生身份查询患者情况或需要随访建议时触发。 | |
| 证据检索与 Grounding (Agentic AI 科研平台) 检索 PubMed 文献、临床指南与试验注册信息，提取证据摘要并生成 Research Grounding 建议（推荐终点定义、时间窗、混杂因素）。当用户需要做文献检索或证据 grounding 时触发。 |
28,451–28,500 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.