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 |
|---|---|
| Finxdata Simulated Trading 使用 FinXData 已开放的 A 股与港股模拟交易能力。适用于用户要求管理 A 股或港股自选股、创建或查询对应市场的模拟账户、提交或查询模拟订单、查看持仓、成交、资金流水、资产与收益、撤单或重置账户的场景。港股模拟交易已完整开放：A 股账户使用人民币和 T+1，港股账户使用港币和 T+0。 | |
| FinXData Chinese Stock Data 直接询问股价、公告、热门题材或龙虎榜；优先免 Key 免费查询金融数据。 | |
| johnny Activate the "Johnny" persona — a virtual second designer for design dialogs. Trigger — the user's message starts by addressing "Johnny" (or they ask to "switch on Johnny" / invoke "/johnny"). From then on the whole thread runs in this mode | |
| Shopdora — Shopee Product Selection & Keyword Research Tool This skill should be used when the user wants to perform data analysis on Shopee platforms, including: keyword research,
product discovery & search. | |
| Gog2 Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. | |
| crypto-treasury-ops Safely manage EVM treasury operations and native Hyperliquid trading for OpenClaw agents, including wallet balance checks, guarded token transfers, cross-cha... | |
| security-skiil-scanner Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification L... | |
| Deprecated - AgentPMT AgentAddress + Paid Marketplace Find and install the current canonical AgentPMT skills published under the AgentPMT ClawHub org account. Use when an agent needs the latest AgentPMT setup, x... | |
| Agentpmt Current Clawhub Skills Find and install the current canonical AgentPMT skills published under the AgentPMT ClawHub org account. Use when an agent needs the latest AgentPMT setup, x... | |
| Deprecated - Openclaw Agentpmt Tool Air Quality Pollen Information E89f3f Find and install the current canonical AgentPMT skills published under the AgentPMT ClawHub org account. Use when an agent needs the latest AgentPMT setup, x... | |
| Deprecated Openclaw Agentpmt Tool Binary To From File Converter 9bc86d Find and install the current canonical AgentPMT skills published under the AgentPMT ClawHub org account. Use when an agent needs the latest AgentPMT setup, x... | |
| Deprecated - Openclaw Agentpmt Tool Blockchain Scanner Find and install the current canonical AgentPMT skills published under the AgentPMT ClawHub org account. Use when an agent needs the latest AgentPMT setup, x... | |
| Deprecated - Openclaw Agentpmt Tool Google Calendar 310fca Find and install the current canonical AgentPMT skills published under the AgentPMT ClawHub org account. Use when an agent needs the latest AgentPMT setup, x... | |
| Typhoon Tracker — 台风实时追踪与影响研判 台风实时追踪与影响研判（Typhoon Tracker），经多台风全周期实战验证。当用户询问台风路径/登陆预测/强度、风雨影响、出行安全、交通停运、活动/演唱会/漫展可行性时加载；当用户询问航班/高铁/交通出行与行程规划时**必须加载**——即使未明确提及台风，也要排查台风及其残余环流、冷空气等系统性天气背景对交通的影响（避免仅看当日天气导致误判，如残涡'回马枪'）；当询问停编台风的残涡去向/残余影响/降雨成因时**必须加载**（残涡可停编后重组二次增强）；当近海存在未编号扰 | |
| Ai Daily Report 每日自动生成 AI 资讯日报并发送。使用场景：用户说 “生成 AI 日报” 或者系统通过定时任务触发。关键词包括：AI日报、AI资讯、开源AI项目、每日报告。 | |
| Auto Research Pipeline 从 AutoResearch 到完整项目的全自动流水线（实验 → 多 Agent 编排 → 技能封装） | |
| Luma Events Enhanced Fetch upcoming events from Luma (lu.ma) for any city. Use when the user asks about tech events, startup meetups, networking events, conferences, or things ha... | |
| skill-guard w Snyk Agent Scan Scan ClawHub skills for security vulnerabilities BEFORE installing. Use when installing new skills from ClawHub to detect prompt injections, malware payloads... | |
| DDGS Metasearch via local MCP Use a local DDGS MCP server (SSE) via mcporter to access fast web search tools (text/news/images/videos/books) without API keys. Use when user requests gener... | |
| Wolfram Alpha (LLM API) Delegate precise, formalizable computations and factual lookups to Wolfram|Alpha via its LLM API (HTTP) to get verified results and reduce arithmetic/modelin... | |
| eShop 一个聚合购物与外卖服务的智能平台，帮助用户完成商品搜索、下单购买、外卖点餐、订单查询、优惠券领取等全流程购物体验。支持多平台、多商家、多品牌的统一接入与智能路由。 | |
| Luogang shopping assistant 购物助手 - 商品查询，商品详情，当用户有购物倾向时候，尤其是提到骆岗/骆岗门市部/骆岗电商的时候，可提供有效信息 | |
| Markdown Diagram Renderer Automatically identify diagram code blocks (Mermaid/Graphviz/PlantUML) in Markdown documents, render them as images, and replace them. | |
| HKO Weather 從香港天文台獲取實時天氣、9日預報及天氣警告信號，提供繁體中文格式化報告，適用於Discord發布。 | |
| The Null Epoch Agent Skill Play The Null Epoch, a persistent AI agent MMO. Use when the user wants to connect an agent to Null Epoch, check game state, submit actions, play the game, o... | |
| The Null Epoch Agent Skill Play The Null Epoch, a persistent AI agent MMO. Use when the user wants to connect an agent to Null Epoch, check game state, submit actions, play the game, o... | |
| Vibe Remote Vibe Remote 远程 AI Coding 工具。当用户提到 vibe-remote、vibe remote、远程 coding、iOS 远程控制 Mac 跑 AI 写代码、安装 vibe-remote、配置 vibe-remote、或提交 vibe-remote issue 时使用。 | |
| FRITZ!Box Control AVM FRITZ!Box routers and Smarthome devices via TR-064 and Web API. Use when the user wants to manage their FRITZ!Box router (WLAN, connected devices... | |
| Playwright WS Browser automation via remote Playwright WebSocket server for screenshots, PDFs and testing. | |
| ShapelessAI Drive the user's ShapelessAI account - draft and publish social posts, run durable content jobs, manage standing agents and Brand Memory. Use when the user asks to create, review, schedule, or publish social content, or to check on their Sh | |
| Opencron Skill Repo Visual cron job dashboard for OpenClaw — live countdown timers, run history, calendar view | |
| Opencron Skill Repo Visual cron job dashboard for OpenClaw — live countdown timers, run history, calendar view | |
| pixiv-skill Pixiv 抓榜、搜索、元信息缓存、按需下载与互动操作技能。用于在不自动登录的前提下，通过 config.yaml 的 Cookie 鉴权执行：排行榜抓取、关键词搜索、作品详情/下载、画师监控、点赞收藏关注。优先先缓存元信息，按需再下载图片或回传直链。 | |
| SpielerPlus Scraper Scraper for SpielerPlus/TeamPlus team management platform. Extracts events, members, absences, finances, participation stats, and more. | |
| Knowledge Graph - API Ingestion Connectors Connect to external APIs and ingest data into graph-ready structures for ETL pipelines and knowledge graph construction. | |
| Knowledge Graph - Causal Chain Analyzer Analyze and trace cause-effect chains in knowledge graphs to identify root causes, trace downstream impacts, and understand dependencies. Supports multiple t... | |
| Knowledge Graph - Csv Graph Loader Generator Generate graph database loaders and triple mappings from CSV datasets. Converts tabular CSV data into graph-ready nodes, edges, and triples for graph databas... | |
| Knowledge Graph - Etl Pipeline Generator Generate automated ETL pipelines for transforming and loading data into graph databases or knowledge graphs. | |
| Knowledge Graph - Graph Constraint Generator Generate structural, semantic, and property constraints for knowledge graph schemas including RDF/OWL ontologies and property graph models. | |
| Knowledge Graph - Graph Path Reasoning Analyzer Analyze and discover paths between entities in knowledge graphs to explain relationships, identify indirect connections, and provide reasoning over traversal... | |
| Knowledge Graph - Graph Query Debugging Tool Diagnose errors in Cypher or SPARQL queries and suggest fixes for syntax issues, schema mismatches, and incorrect graph traversal patterns. | |
| Knowledge Graph - Graph Query Optimization Assistant Analyze graph queries and suggest optimizations to improve performance, reduce execution time, and ensure efficient traversal in graph databases. | |
| Knowledge Graph - Graph Rule Engine Builder Create rule-based reasoning systems for knowledge graphs that infer new relationships and facts from existing data using declarative logic rules. Supports de... | |
| Knowledge Graph - Graph Schema Validation Validate knowledge graph schemas and data against defined ontology, RDF/OWL, or property graph schema constraints. | |
| Knowledge Graph - Graph Template Query Generator Generate reusable Cypher or SPARQL query templates for common graph database operations such as finding nodes, relationships, paths, and aggregations. | |
| Knowledge Graph - Graphql Graph Mapping Map GraphQL queries and schemas to underlying graph database operations, enabling applications to access knowledge graph data through GraphQL APIs. Translate... | |
| Knowledge Graph - Janusgraph Connector Connect to JanusGraph distributed graph database to query, manage, and analyze graph data using Apache TinkerPop Gremlin traversal language | |
| Knowledge Graph - Json To Triples Converter Convert JSON documents into RDF triples or graph-ready subject–predicate–object statements for knowledge graphs and semantic databases. | |
| Knowledge Graph - Kg Schema From Text Generate a structured knowledge graph ontology or schema from unstructured or semi-structured text sources. | |
| Knowledge Graph - Tigergraph Connector Connect to TigerGraph distributed graph database to query, load, and manage large-scale knowledge graph data using GSQL and REST++ APIs |
30,401–30,450 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.