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 |
|---|---|
| Stock AI Analyzer A股股票基本面投研分析方法论。当用户要求按股票名称或代码分析中国A股、判断公司成长性与核心亮点、评估估值阶段与隐含预期、分析财务质量与业务结构、判断股票是否处于当前市场主线内、做竞争格局分析或风险排查，或基于Tushare/公开市场数据生成股票基本面分析时使用。用户提问形式包括"帮我分析XX股票""XX的基本面怎... | |
| Tushare Daily Market Sense 基于 Tushare Pro A 股 daily 日线数据生成盘后市场研报的方法论 skill。当用户要求做每日盘面趋势、上证/创业板指数趋势、情绪指数趋势、赚钱效应与上涨主线分析、爆量下跌识别、容量上涨/科创板月线突破/10:30前涨停等特征分组分析、历史某日复盘、基于 daily/daily_basic/涨跌... | |
| OKX Trade Kit Setup, install, and use OKX Agent Trade Kit — the official OKX toolkit for AI-powered trading. Use this skill whenever the user mentions: OKX trading, agent... | |
| warehouse Generate warehouse analytics charts, table images, and report-ready visuals from SQLite/CSV data. Use when the user asks for warehouse charts, product table... | |
| Web Builder Build full-stack applications after collecting project requirements. Use when user says Neo App Mode, asks to build/create/scaffold a new app, or wants React... | |
| portal-government-policy-watch Track official government documents in the Chinng AI-Agent Portal — US Federal Register, EU EUR-Lex, and Japanese agency feeds. Use for regulatory monitoring, comment deadlines, effective dates, and primary-source policy reading. | |
| portal-news-triage Research and compare news from the Chinng AI-Agent Portal. Use when finding relevant articles, investigating a topic, or preparing a sourced news summary. | |
| portal-security-watch Monitor CVEs and security advisories through the Chinng AI-Agent Portal. Use for incremental vulnerability checks, package watchlists, and actionable security summaries. | |
| Gamification & XP System XP system for productivity gamification via ClawdBot - track levels, badges, streaks, and achievements | |
| Hyperliquid DEX Integration Query Hyperliquid DEX for account balances, positions, PnL, and margin data via ClawdBot API | |
| Just Fucking Cancel Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and provides cancel URLs. CSV-based analysis with optional Plaid integration for ClawdBot users. | |
| Language Learning Tutor AI language tutor for learning ANY language through conversation, vocab drills, grammar lessons, flashcards, and immersive practice. Use when the user wants to: learn a new language, practice vocabulary, study grammar, do flashcard drills, | |
| Accounting Finance System Research Skill Research and solve "how do I do this?" questions inside accounting and finance software systems (ERP, GL, AP/AR, billing, close, and reporting tools). Use wh... | |
| Bank Recon Skill Perform bank reconciliation between bank statements and general ledger files. Supports bank statement PDF ingestion, conversion of PDF statements into struct... | |
| Review Business Requirement Document Skill Review Business Requirements Documents in `.docx` format by reading the existing BRD, extracting paragraph-level context, drafting clarification questions fo... | |
| Deposition Question Development Develop deposition question sets from Relativity-exported PDF productions using a user-provided legal theory. Use when tasks involve reviewing opponent-produ... | |
| FinResearchClaw Finance, accounting, and investment research automation via the FinResearchClaw repo. Use when asked to run autonomous finance research workflows such as eve... | |
| Redline Review and redline DOCX contracts paragraph by paragraph with tracked changes, clause-level risk analysis, and draft comment responses. Use when a user wants... | |
| Technical Accounting Research Research technical accounting treatment and financial statement disclosure for specific transactions using U.S. GAAP and SEC-focused sources. Use when a user... | |
| US Tax Return Review-1040 Review U.S. individual income tax returns (Form 1040/1040-SR) for the most recent tax year, compare major return items against current-year tax rules, check... | |
| Angus Bounty Hunter Automated smart contract bug bounty hunting. Scans Immunefi/Code4rena targets with Slither static analysis, triages findings with local LLMs, and generates P... | |
| Academic Paper Analysis 对学术论文（流行病学、生物统计学方向）进行深度结构化解析。当用户说"分析这篇论文"、"对这篇文献进行分析"、"论文分析"或类似话语时，自动激活此技能。 | |
| Mem0 Memory mem0 本地记忆层完整实现（增强版）。语义记忆存储/检索/管理，WAL 协议，SESSION-STATE，多级记忆（User/Session/Agent）。参考 ZejunCao/bilibili_code Mem0框架解读优化。 | |
| Mem0 Status Check 检查 mem0 本地记忆系统的功能完整性和运行状态。每次被问到 mem0 功能、状态、是否完整时触发。 触发词：mem0状态、mem0功能、检查mem0、mem0正常吗、mem0完整性 | |
| Method Repository 将论文分析中提取的流行病学研究设计和统计方法存入本地知识库数据库，支持去重。当用户说"存入数据库"、"保存到知识库"、"记一下这个方法"时激活。 | |
| Wopdpress AI Blogger Create, edit, and publish WordPress posts via REST API with full Gutenberg block support. Use when Codex needs to automate WordPress content publishing, gene... | |
| Mythos Recurrent-depth reasoning via iterative refinement. Use for complex analysis, multi-hop problems, design decisions, strategic planning — any question where s... | |
| ClawdCall Orchestrate outbound AI voice calls and asynchronous call results through ClawdCall from OpenClaw. Use when: placing outbound voice calls, creating call task... | |
| Empathic Trinity Core 面向 OpenClaw 工作区的低上下文占用记忆系统安装、迁移与配置技能。用于把任意工作区改造成 Memory V8 运行方式：会话优先、daily 摘要、精简 `MEMORY.md`、按需检索，并保留用户状态察觉、关系温度与更有情商的长期协作能力。适用于安装新记忆体系、迁移旧记忆规则、压缩上下文占用、规范 da... | |
| VeriGlow Agent Map Look up VeriGlow Agent Map for any website URL to discover its data functions, internal APIs, browser automation recipes, and agent reliability reports. Use... | |
| groupchat-host Prevent accidental participant pings and endless groupchat loops. | |
| groupchat-participant Reply once per round and never create participant loops. | |
| Intiface Direct Control 750+ BLE intimate devices via Intiface Central using direct Buttplug v4 WebSocket protocol | |
| Skill Safe Install Skills 安全安装工具 - 整合 Vetter 代码审查 + ClawHub 评分 + ThreatBook 沙箱扫描三层验证 | |
| Save To Email Send emails through the Resend API. Use when the user wants to send an email, deliver a report by email, forward generated content to an inbox, or trigger an... | |
| Kuaipu Skill 自动化快普系统登录、验证码识别、自动操作和审批流程查询等。 | |
| article-bookmarker Save and organize web articles as bookmarks with AI summaries and auto-tagging. Use when the user wants to bookmark or collect articles. | |
| task-orchestrator Unified Task Orchestration Hub v2 - Integrates Heartbeat, Cron, Subagent and Task Management. Provides task identification, standardized setup, execution tracking and best practice templates. Supports dynamic config loading, deadlock preven | |
| Agent Budget Controller Control LLM API spending per agent. Set daily/weekly/monthly limits with real-time tracking and alerts. | |
| Airkorea Cli Korean real-time air quality (PM10, PM2.5, O3, NO2, CO, SO2) and 1–3 day forecasts via 한국환경공단 에어코리아 OpenAPI (apis.data.go.kr/B552584). Six subcommands wrap g... | |
| Bank of Korea ECOS CLI Command-line client for Bank of Korea ECOS API to list statistic tables and fetch time series data in JSON by code and frequency. | |
| Auto README Generator (ChloePark85) Generates a professional README.md file for a project, including name, description, installation, usage, and license sections based on project contents. | |
| Credential Vault Encrypted credential storage for OpenClaw agents. Stop storing API keys in plaintext. | |
| errand-ai Send a real person to a physical place in Seoul (Gangnam area) to check, photograph, verify, queue, or pick something up, and get GPS+photo evidence back. Use when the user needs eyes or hands on site — "is this store open?", "how long is t | |
| Finance Automation Automates payments, invoices, expenses, and financial reports with Stripe webhooks and real-time Telegram notifications for streamlined finance management. | |
| G2b Cli Korean public procurement (나라장터 g2b.go.kr) command-line wrapper for the 조달청 OpenAPI surface — three subcommands cover BidPublicInfoService (입찰공고 per 업무구분 thn... | |
| Imgur CLI Imgur API CLI for agents. Upload images by file path or URL, fetch image metadata, delete uploads via delete-hash, create and manage albums. Anonymous upload... | |
| Juso Address Cli Search and resolve Korean road addresses (도로명주소) via the official juso.go.kr OpenAPI. Keyword search with zip codes, English address lookup, and address-to-c... | |
| kakao-local-cli Command-line tool for Kakao Local API supporting keyword/category place search, geocoding, and reverse geocoding with JSON output and API key authentication. | |
| Kamis Cli Korean agricultural/livestock/aquatic wholesale & retail price data via the official KAMIS (한국농수산식품유통공사) OpenAPI. Use for daily 도매가/소매가 lookup, 7-day & month... |
20,301–20,350 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.