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 |
|---|---|
| MCP TypeScript Simple Template chenreuven/mcp-ts-simple-template A foundation for creating custom Model Context Protocol servers that can integrate with AI systems, providing a simple BMI calculator tool as an example implementation. | |
| cocos-mcp chenshengbiao/cocos-mcp A headless MCP server that enables AI to create complete 2D/3D games in Cocos Creator without opening the editor or writing TypeScript code, featuring 184 tools for scene building, physics, UI, and automated testing. | |
| MCP-Server chenshuai2144/mcp-server A Model Context Protocol implementation that enables large language models to call external tools (like weather forecasts and GitHub information) through a structured protocol, with visualization of the model's reasoning process. | |
| agent-fde chenshuai9101/agent-fde A methodology-driven MCP server that guides enterprise AI rollouts through a 5-phase pipeline with layered memory for experience reuse, enabling agents to manage engagements and crystallize skills. | |
| Windbg-MCP chensiling/windbg-mcp Enables AI-driven WinDbg kernel debugging via the Model Context Protocol, allowing agents to send debug commands and receive results. | |
| schwab-mcp chensirui2008/schwab-mcp Production-grade, safety-first Charles Schwab MCP server self-hosted on Cloudflare Workers. Real-time quotes, options Greeks, zero-trust OAuth 2.1, and anti-hallucination guardrails. | |
| Schwab Read-Only MCP chensirui2008/schwab-readonly-mcp MCP server for read-only access to Charles Schwab market data and account information. It provides quotes, price history, technical indicators, fundamentals, option chains, market hours, movers, and account/transaction data via the official | |
| Acmezone Data MCP chensy115/mcp Read-only MCP server for internal Amazon business data, exposing 19 tools to query sales, inventory, and financial metrics. | |
| Cloudflare Playwright MCP Worker chenwei791129/playwright-mcp-worker Enables AI assistants to control a browser for web automation tasks like navigation, typing, clicking, and taking screenshots, with optional API key authentication. | |
| mcp-superset chenwenyu1014/mcp-superset-community A comprehensive MCP server for Apache Superset. Gives AI assistants full control over your Superset instance — dashboards, charts, datasets, SQL Lab, users, roles, RLS, and more — through 137 tools. | |
| risk-analytics-mcp-server chenxi-bot21/risk-analytics-mcp-server Provides AI agents with quantitative risk tools such as VaR, expected shortfall, GARCH volatility, backtesting, stress testing, tail risk analysis, and credit scoring using synthetic or user-supplied data. | |
| AI Daily MCP Server chenxianseng001/ai-daily Enables fetching daily AI news summaries aggregated from multiple sources including GitHub, Hacker News, Product Hunt, YouTube, Twitter, and Chinese AI sites. | |
| Anki MCP Server chenxiaoyao6228/anki-mcp-server Enables interaction with the Anki desktop app for spaced repetition learning. Supports reviewing due cards, creating new flashcards, and managing study sessions through natural language commands. | |
| miband-mcp chenxidawn/miband-mcp Enables AI to query Xiaomi Mi Band health data (steps, sleep, heart rate) from Gadgetbridge SQLite exports via the MCP protocol, allowing natural language questions about daily activity. | |
| VibeDoge MCP Server chenxing3060/vibedoge-mcp Enables interaction with VibeDoge lottery system through comprehensive tools for user profile management, lottery participation, result checking, and activity statistics. Supports secure authentication and real-time lottery operations throu | |
| M365 Copilot MCP Server chenxizhang/m365copilot-mcp Integrates with Microsoft 365 Copilot APIs to enable retrieval of content from SharePoint and OneDrive, document search across M365, and conversational AI interactions with your Microsoft 365 data while respecting access permissions. | |
| Weather MCP Server chenxming/weather-mcp-server Provides global weather information including current conditions, 5-day forecasts, and US weather alerts through OpenWeatherMap and National Weather Service APIs. Offers native support for Chinese city names and multiple temperature units. | |
| free-web-mcp chenxuyaun/free_web_mcp Enables AI agents to search the web and fetch webpage content as clean text via MCP, with optional headless rendering for dynamic pages. | |
| jev-browser chenycl/jev-browser-skill Enables coding agents to control browsers and computers via calibrated judgments from a System One model, with code-based control loops and no vision model. | |
| Sun MCP Server chenycl/sun-mcp Enables automatic conversation summarization by typing -sun command, which analyzes the current chat session and saves structured summaries as .mdc files with key insights, outcomes, and next steps. | |
| web-design-harvester chenycl/web-design-harvester Converts any rendered web page into a complete, LLM-readable design specification—including block screenshots, distilled computed CSS, design tokens, responsive deltas, and alpha-channel-analyzed assets—so models can accurately reproduce th | |
| ios_migration_mcp chenyeju295/ios_migration_mcp MCP服务器用于扫描iOS项目，生成改造计划和Cursor规则，帮助开发者逐步优化代码迁移。 | |
| AI Image Generation MCP Server chenyeju295/mcp_generate_images Enables AI-powered image generation using Volcengine's Doubao model with customizable aspect ratios (1:1, 4:3, 16:9, 3:4, 9:16) and file management. Supports high-quality text-to-image generation with automatic retry, error handling, and fl | |
| logic-analyzer chenyingchun0312/logic-agent Enables AI agents to capture and analyze digital signals from DSLogic Plus and sigrok-supported devices, with archived captures, channel statistics, edge excerpts, and deterministic protocol decoding. | |
| vision-qc-agent chenyingying0924/vision-qc-agent Enables agents to run checklist-driven e-commerce image quality inspection with auditable local rules, returning pass/needs-work/fail verdicts, actionable fixes, SKU consistency checks, report files, threshold advice from reviewer overrides | |
| dsh-kanban-mcp chenyinrusi/dsh-kanban-mcp Exposes a filesystem-driven four-lane kanban board as a read-only MCP server, enabling agents to inspect board state, card details, and lane counts. | |
| repo-health chenyinrusi/dsh-repo-health Provides read-only repository health scanning tools for drift detection, module reachability, prompt bloat, evidence calibration, and registration completeness, enabling agents to diagnose repositories via MCP. | |
| Writable Figma MCP Bridge chenyiwanshishen-source/figma-connector-figma- Enables MCP-compatible AI clients to read and modify the user's currently open Figma file by executing JavaScript in Figma's sandbox, all through a local bridge with status monitoring, node jumping, and automatic rollback on errors. | |
| Codex MiMoCode Bridge chenyk1992/codex-mimo Bridges Codex with MiMoCode as a coding agent for planning, implementation, and review via MCP tools. | |
| kb-metabolism chenyk2016/kb-metabolism A knowledge base MCP server that manages notes with digestion and excretion features, supporting search, read, and stats tools. | |
| mcp-server-memos chenyqthu/mcp-server-memos Enables to interact with Memos note-taking service, allowing search, creation, retrieval, and updating of notes through natural language. | |
| mcp-server-weread chenyqthu/mcp-server-weread An MCP server enabling LLMs to access WeChat Reading bookshelf, notes, highlights, and reviews via tools like get_bookshelf, search_books, and get_book_notes_and_highlights. | |
| Photo Shoot Planner chenyuan99/photo-shoot-planner A Claude-compatible MCP server for planning both outdoor photography trips and professional photoshoot productions, with tools for location scouting, astronomy, weather, budgeting, and production management. | |
| postgres-mcp chenz4027/postgres-mcp Enables Claude to interact with a local PostgreSQL database through SQL queries, schema inspection, and CRUD operations. | |
| PCB Weaver chenzehaoo/pcb-weaver Enables constrained KiCad layout, autorouting orchestration, ECO revision analysis, and manufacturing evidence packaging through MCP tools and persistent engineering jobs with native DRC/ERC verification. | |
| minecraft-mcp-server-blueprint chenzelongknight/minecraft-mcp-server-blueprint Enables AI agents to control Minecraft characters and build structures from blueprint files via MCP, with tools for listing, parsing, building, and verifying schematics. | |
| CapCutAPI-Complete MCP Server chenzhaohua11/capcutapi-complete Enables video editing operations such as trimming, merging, adding audio/text/effects, and exporting via MCP protocol, leveraging CapCut core functionalities. | |
| discord-mcp chenzhaoxuan0/discord-mcp MCP server for Discord communications, enabling listing guilds and channels, reading and sending messages, creating threads, and adding reactions. | |
| intercom-mcp chenzhaoxuan0/intercom-mcp Enables to search, view, and interact with Intercom contacts and conversations, including sending customer-visible replies and internal notes. | |
| pagerduty-mcp chenzhaoxuan0/pagerduty-mcp Enables PagerDuty incident response operations including listing incidents, acknowledging and resolving incidents, looking up on-call schedules, and listing services. | |
| tavily-mcp chenzhaoxuan0/tavily-mcp A web search and extraction MCP server powered by Tavily, providing tools for AI-powered search, content extraction from URLs, and Q\&A with source citations. | |
| telegram-mcp chenzhaoxuan0/telegram-mcp Enables interaction with Telegram Bot API for sending messages, photos, editing messages, answering callbacks, and fetching updates. | |
| twilio-mcp chenzhaoxuan0/twilio-mcp MCP server for Twilio communications, enabling SMS/MMS sending, message listing, outbound calls, and phone number lookup. | |
| zendesk-mcp chenzhaoxuan0/zendesk-mcp MCP server for Zendesk support workflows that enables ticket search, lookup, creation, commenting, status updates, and user listing through natural language. It uses OAuth authentication and supports both internal notes and public comments. | |
| feishu_mcp_server chenzhi-ana/feishu_mcp_server Enables Claude/Cursor to interact with Feishu (Lark) bots through MCP, allowing LLMs to execute business logic via Feishu robot APIs. | |
| eodiseobwa-mcp cheoljae-ee/eodiseobwa-mcp Recommends fair and enjoyable meeting places for group gatherings by balancing travel distance equity and nearby amenities like restaurants, cafes, and cultural facilities. | |
| 2025 Tax Law Amendment MCP Server cheolminbae/mcp-server-sample Enables users to search and query information from the 2025 Korean tax law amendment PDF documents using natural language. Provides document indexing and retrieval capabilities through ChromaDB vector storage and LangChain integration. | |
| MCP AgentRun Server cheongqinxue/mcp-agentrun Enables safe Python code execution in isolated Docker containers through the AgentRun framework. Provides automatic container lifecycle management and comprehensive error handling for secure and reproducible code execution. | |
| assets-cdn-mcp chepelevigor/cdn-mcp Enables AI agents to manage static assets on S3-compatible CDNs through natural language, including partial uploads, manifest rebuilds, header fixes, and deferred deletions. | |
| Calibre Librarian MCP Server chepetime/calibre-librarian-mcp Surfaces your Calibre e-book catalog to Claude via the Model Context Protocol, enabling search, metadata management, and library maintenance through natural language. |
38,251–38,300 of 115,409
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.