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 |
|---|---|
| Flower Control fallen-blossom/flower-control Enables AI agents to operate websites and Windows desktop applications by reading and acting on webpage elements, exposed UI controls, and screenshots with mouse and keyboard input. Combines browser, desktop, and computer-control channels i | |
| GeoGebra MCP Server fallenangels520/geogebra-mcp Provides access to GeoGebra's mathematical computation, geometry construction, and visualization capabilities. Enables mathematical calculations, CAS operations, geometric constructions, and exporting results as PNG or PDF images. | |
| Google Workspace MCP Server fallenone1701/mcp-server-1 Enables MCP-compatible AI agents to create Gmail drafts, send Gmail email, and append text to Google Docs while keeping OAuth tokens inside the server. | |
| auchan-ro fallenreds/auchanmcp Enables AI assistants to search the Auchan Romania catalog, resolve shopping-list descriptions to exact products or available analogs, and create and manage anonymous carts through emulated public VTEX REST APIs. | |
| Lanhu MCP falling502/design-context-mcp Enables AI clients to read design pages, screenshots, original assets, styles, and workflows from Lanhu, Figma, and Mockplus, inspect elements, download resources, and build local page-flow maps. | |
| Fusion MCP Server fallsef/fusion_mcp Enables AI to analyze and transform data using fusion algorithms with statistical, machine learning, or hybrid methods. Provides seamless data format conversion and enhanced analytical capabilities through the Model Context Protocol. | |
| canopy-mcp falmiron-strsdev/canopy-mcp MCP server for the Get Canopy WordPress site, giving AI agents context over ACF blocks, content, Yoast SEO, menus, HubSpot tooling, and the running change journal. | |
| entropos-mcp falsable/entropos Exposes Entropos's entropy-based LLM routing to any MCP host, letting agents execute prompts on the optimal cost/quality model, query the recommended model and complexity tier for a prompt without running it, and inspect cumulative cost sav | |
| Laravel MCP Server falzz1010/laravel-mcp-server Secure bridge between AI clients and local Laravel projects, enabling AI to run artisan commands, read logs and routes, and safely read/write code with layered security protections. | |
| MCP Server Office famano/mcp-server-office A server providing tools to read, write, and edit Microsoft Word (docx) files through the Model Context Protocol, allowing operations like complete document reading, content creation, targeted paragraph editing, and text insertion. | |
| apk-preview-mcp famel-svg/apk-preview-desktop Enables installing, launching, and inspecting Android APKs on a dedicated emulator, with screen capture, UI tree inspection, and touch/navigation control via MCP tools. | |
| Perplexity MCP Server family-it-guy/perplexity-mcp A custom Model Context Protocol implementation that integrates Perplexity AI with Claude Desktop, allowing users to access Perplexity's AI models for both single questions and multi-turn conversations. | |
| Famma AI MCP Auth famma-ai/mcp-auth Enables developers to build OAuth-protected MCP servers on Cloudflare Workers with pluggable authentication adapters, allowing user-specific access control and secure token exchange. | |
| Zendesk MCP Server famousdrew/zd-mcp-server A Model Context Protocol server that enables AI assistants like Claude to interact with Zendesk Support through natural language for searching, creating, updating, and managing tickets. | |
| W3 MCP FalkorDB Server famtong8-dev/w3-mcp-server-falkordb Enables graph database operations on FalkorDB via MCP, allowing Cypher queries, node retrieval, and graph listing. | |
| W3 MCP LSP Server famtong8-dev/w3-mcp-server-lsp Provides JavaScript/TypeScript code intelligence via LSP, enabling goto definition, hover info, and find references through MCP tools. | |
| w3-mcp-server-qdrant famtong8-dev/w3-mcp-server-qdrant Python MCP server for vector search using Qdrant vector database and Ollama embeddings, with advanced query techniques like query expansion, HyDE, and reranking. | |
| local-mcp fan-67/local-mcp A lightweight, stdio-based MCP server enabling AI assistants to perform local file system operations like reading, writing, searching, and executing commands. | |
| advisor-mcp fan-chou/advisor-mcp Enables any MCP-capable coding agent to request an independent, read-only second opinion from a stronger model at consequential decision points such as planning, debugging, risk review, and handoff. It exposes consult, session-state, reset, | |
| AskAlign fan-dev-sktch/askalign Provides adaptive question cards and guided multi-round interviews inside Codex, letting users clarify requirements one decision at a time and automatically sending chosen answers into the conversation. | |
| wechat-msg-mcp fan-wang-driscolls/wechat-msg-mcp Provides AI clients read-only access to WeChat chat history by extracting and decrypting the local Mac database, enabling search, summary, and analysis of messages. | |
| qt-mcp fan1959/qt-mcp A local stdio MCP server that wraps Qt 5.14.2 + MinGW toolchain into Python tools, enabling AI assistants to scaffold, build, run, test, format, deploy, and analyze Qt C++ projects directly in conversation. | |
| yuque-local-mcp fanb129/yuque-local-mcp 本地语雀 MCP 服务器，通过浏览器登录态访问语雀，支持读取、创建和编辑文档，具有知识库白名单和只读模式等安全特性。 | |
| runninghub-audio fancy5166/runninghub-audio-connector Enables users to generate speech, music, cloned voices, lyrics, and separated vocal/instrumental stems through 50+ audio model APIs from providers such as MiniMax, Suno, Mureka, Doubao, and Qwen TTS. | |
| runninghub-image fancy5166/runninghub-image-connector Enables text-to-image, image-to-image, image editing, and 4K upscaling across 90+ image models with Chinese prompts supported. | |
| runninghub-mcp fancy5166/runninghub-mcp Enables any MCP client to search and submit tasks across 350+ multimodal image, video, audio, and 3D models, run ComfyUI workflows and AI apps, upload/download files, and chat with LLMs. It supports stdio MCP integration and optional scope | |
| runninghub-video fancy5166/runninghub-video-connector Enables generation and enhancement of videos through a unified entry point to 200+ video models (Kling, Hailuo, Seedance, Vidu, Wanxiang), covering text-to-video, image-to-video, start-end frame interpolation, reference-to-video, video upsc | |
| auto_video_mcp fancyboi999/auto_video_mcp One-stop automated video generation MCP service integrating digital human cloning, voice cloning, video/audio creation, and web content aggregation for LLMs. | |
| capcut-mcp fancyboi999/capcut-mcp Automates CapCut video editing through an HTTP/MCP API, enabling draft creation, material addition (video, audio, text, images), effects, and AI-powered enhancements via natural language. | |
| Daily Hots MCP fancyboi999/daily-hot-mcp A Python-based MCP server that aggregates real-time trending topics and news from over 30 sources including social media, technology, and finance platforms. It enables AI applications to retrieve the latest hot searches and news from major | |
| douyin-video-mcp fancyboi999/douyin-video-mcp A Model Context Protocol server that downloads watermark-free videos from Douyin (TikTok China) share links, extracts audio, and transcribes speech to text using ASR APIs. | |
| goofish-cli fancyboi999/goofish-cli MCP server for automating Xianyu (Goofish) marketplace operations: publish, manage items, handle IM messages, and more via CLI or AI agents. | |
| Xiaohongshu (Little Red Book) MCP Server fancyboi999/xhs-auto-mcp A server that allows interfacing with the Chinese social media platform Xiaohongshu through HTTP requests, enabling searching notes, retrieving note content and comments, and posting comments. | |
| ida-free-mcp fandomuser/ida-free-mcp Enables agents to interact with IDA Free 9.5 through 96 tools for live disassembly, decompilation, debugging, editing, byte patches, and multi-instance routing over stdio or Streamable HTTP, without requiring IDAPython. | |
| Google Search Console MCP Server fandungptit/mcp-server-gsc Provides access to Google Search Console to retrieve and analyze search performance data including queries, pages, and rankings. It enables users to perform rich data analysis through customizable reporting periods and dimensions using the | |
| ci-watch-mcp faneraiy14/ci-watch-mcp MCP server with the watch_ci tool that polls GitHub Actions until a commit's CI run finishes, then returns the outcome and failed log tail in one call. | |
| minecraft-rcon-mcp faneraiy14/minecraft-rcon-mcp Lets an AI assistant control a live Minecraft server over RCON: list players, broadcast chat, teleport, give items, change weather/time, kick, or run any raw vanilla/plugin command. | |
| nyxilum-memory-mcp faneraiy14/nyxilum-memory-mcp Enables AI coding sessions to persist the reasoning behind work — decisions and their justifications, rejected options, side findings and nuances — as append-only Markdown records with reversible review, archive and human-confirmed purge. R | |
| nyxilum-mcp faneraiy14/nyxilummcp Enables AI assistants to compile, run, lint, and format NyxilumLang code directly through NyxilumNode without manual terminal commands. | |
| workspace-status-mcp faneraiy14/workspace-status-mcp Provides MCP tools to get a single-call snapshot of git and GitHub Actions CI status across all repositories in a folder, flag missing or stale architecture docs, write doc files, and detect release drift between source and release reposito | |
| dsh-life-kernel fanfan14543/dsh-life-kernel Enables DSH characters to track and update their current mood, energy, activity, rest, growth notes, and things they care about, with persistent state and daily journal archiving. | |
| dsh-local-rag fanfan14543/dsh-local-rag Enables full-text search and contextual lookup across local DSH session logs, workspace documents, skills, and persona files using an offline SQLite FTS5 index with Chinese bigram tokenization, plus incremental indexing and status statistic | |
| skore-mcp fanfcorp/skore-mcp Community MCP server for Skore that exposes tools for projects, evaluate, compare, train_test_split, configuration, and a dispatcher for report methods like metrics, inspection, and data analysis. | |
| MCP Trenitalia fanfulla/mcp_trenitalia An MCP server for real-time Italian railway data, enabling natural language queries about train schedules, delays, departures, arrivals, and live tracking via the Viaggiatreno API. | |
| article-mcp fangfuzha/article-mcp Enables multi-source literature search, full-text retrieval, reference analysis, and journal quality assessment across Europe PMC, PubMed, arXiv, CrossRef, OpenAlex, and EasyScholar via the MCP protocol. | |
| design-review-mcp fanghaoling/brainregion Multi-model adversarial design review MCP server that distributes design documents to multiple LLMs, retrieves project knowledge, and produces calibrated consensus summaries. | |
| Doc-Mind-Search fangkai00/doc-mind-search Provides MCP tools to count, list, and read local documents in formats like PDF, DOCX, Excel, HTML, and TXT, enabling natural language-driven document statistics and content inspection via qwen_agent. | |
| Time MCP fangmd/time-mcp Provides time-related tools for LLM applications, enabling retrieval of current UTC time in ISO 8601 format and Unix timestamps. | |
| Fangorn MCP Server fangorn-network/mcp Enables AI agents to query Fangorn subgraph schemas and conformant data from published data sources via the Model Context Protocol. | |
| kimi-bridge fangshanzizhi/workbuddy-kimi-bridge An MCP server that enables WorkBuddy to invoke the kimi-code CLI locally via MCP protocol, allowing remote task execution through QQ messages. |
49,551–49,600 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.