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 |
|---|---|
| SocialDataX 抖音 Douyin MCP devinchen2014/douyin-mcp Read-only Douyin / 抖音 MCP by SocialDataX for hot search, work search/details, comments and replies, creator profiles, creator works, and creator series. | |
| SocialDataX Instagram MCP devinchen2014/instagram-mcp Instagram MCP by SocialDataX for public post search and details, comments and replies, creator profiles and posts, and video or Reels speech-to-text. | |
| SocialDataX Kuaishou MCP devinchen2014/kuaishou-mcp Kuaishou MCP by SocialDataX for hot search, work and user search, work details, comments and replies, creator profiles, and video speech-to-text transcripts. | |
| SocialDataX TikTok MCP devinchen2014/tiktok-mcp TikTok MCP by SocialDataX for video and image post search, post details, comments and replies, creator profiles and posts, and video speech-to-text. | |
| SocialDataX WeChat Channels MCP devinchen2014/wechat-channels-mcp WeChat Channels MCP by SocialDataX for videos and image posts, comments, creator profiles, speech-to-text transcripts, and WeChat Official Account articles. | |
| SocialDataX Weibo MCP devinchen2014/weibo-mcp Weibo MCP by SocialDataX for hot search, post search and details, comments and replies, creator profiles and posts, and video speech-to-text transcripts. | |
| SocialDataX X Twitter MCP devinchen2014/x-twitter-mcp X and Twitter MCP by SocialDataX for public post search and details, comments and replies, user profiles, and user post lists with pagination. | |
| SocialDataX 小红书 Xiaohongshu XHS RedNote MCP devinchen2014/xiaohongshu-xhs-rednote-mcp SocialDataX（社媒数据助手）is a read-only MCP for 小红书 / Xiaohongshu / XHS / RedNote. Hosted version 0.1.15 provides 35 tools for note and user search, details, comments, creator data, products, and video transcripts. Search video notes with xhs_sea | |
| SocialDataX YouTube MCP devinchen2014/youtube-mcp YouTube MCP by SocialDataX for video search and details, comments and replies, channel profiles and uploads or Shorts, and speech-to-text transcripts. | |
| SocialDataX Zhihu MCP devinchen2014/zhihu-mcp Zhihu MCP by SocialDataX for hot lists, cross-type content search and details, comments and replies, creator profiles, and creator article lists. | |
| Golf Pro TrackMan MCP devinertel/golf-pro-trackman-mcp Lets an AI assistant read a user's own TrackMan activities and shot-level data, including recent sessions, measured and normalized shot values, and summaries grouped by club and drill tags. | |
| Maître d'MCP devingoodsell/matire-d-mcp An MCP server for restaurant discovery and booking across Resy and OpenTable via natural language. It integrates Google Places data with dietary preferences, visit history, and weather awareness to provide personalized dining recommendation | |
| aceternity-mcp devinoldenburg/aceternity-mcp MCP server for Aceternity UI components, enabling AI assistants to discover, search, install, and generate page layouts with 106 components. | |
| hetzner-mcp devinoldenburg/hetzner-mcp Model Context Protocol server for full Hetzner Cloud + Storage API automation. Exposes all official Hetzner operations as MCP tools so AI agents can manage servers, networking, load balancers, firewalls, volumes, DNS zones, and storage boxe | |
| Shannon Lite MCP devinoldenburg/shannon-mcp MCP server for Shannon Lite security workflows, enabling configuration, scan orchestration, workspace management, and report reading. | |
| discord-py-self-mcp devinosolutions/discord-mcp Enables an AI assistant to drive a personal Discord account as if it were the user: reading and sending messages and DMs, managing servers, channels, roles, permissions, threads, invites and friends, joining voice, and clicking buttons, men | |
| Weixin Agent Bridge devinqiu888/weixin-agent-bridge Enables a ChatGPT dot to receive Weixin ClawBot messages through signed MCP Events and reply to the original conversation using authenticated MCP tools, via a self-hosted Cloudflare Workers bridge. | |
| Living Screener MCP devinraylittle-boop/living-screener-mcp Review-only MCP server for stock, options, and crypto screening, trade planning, risk checks, backtesting, and journaling, designed to work alongside Robinhood's Trading MCP without placing orders. | |
| ScanRook MCP Server devinshawntripp/scanrook-mcp Enables AI assistants to perform vulnerability scanning on Docker/OCI images, check CVE details, analyze licenses, and compare scan results via ScanRook. | |
| MCP Talk devinvenable/mcp-talk A lightweight messaging system that enables real-time communication between different AI agents through a shared, file-based message queue. It provides tools for sending, checking, and broadcasting messages to facilitate coordination across | |
| gdrive-mcp-server devinxiong97/gdrive-mcp-server Enables MCP-compatible AI assistants to interact with a user's Google Drive, including listing, searching, reading, creating, updating, and deleting files, with authentication via Google OAuth. | |
| LanternFS deviprasadshetty-dev/filesystem-mcp Enables MCP clients like ChatGPT to securely access and manage a controlled local directory over a remote, OAuth-protected endpoint, with configurable filesystem roots and ngrok tunneling. | |
| Task MCP Server devirokkam/mcp_github_deployment A simple task management server that allows users to add, list, complete, and delete tasks directly within Claude Desktop. It provides a suite of tools for efficient personal task organization using the Model Context Protocol. | |
| Tuba Workflow MCP Server devisionx/tuba-workflow-mcp-server This MCP server bridges to the Tuba.ai platform, enabling programmatic control of AI vision workflows through callable tools such as running workflows, checking status, fetching results, and updating workflow blocks. | |
| docs-mcp devista-consulting/docs-mcp Gives AI agents full-text search over any Markdown/MDX documentation folder. | |
| mcp-ha devitek/mcp-ha MCP server for Home Assistant that lets you control and query your smart home through natural language via MCP clients. Provides tools for entities, devices, services, automations, scripts, history, add-ons, and system info, with read-only | |
| devitway-rag-starter devitway/devitway-rag-starter Minimal local RAG stack with an MCP server that provides document search for any agent. | |
| mcw deviykee/mcw Multi-chain wallet MCP server that enables AI agents to manage Bitcoin, Ethereum, Solana, and Tron wallets via tools for addresses, balances, transactions, and token operations. | |
| macOS Notification MCP devizor/macos-notification-mcp macOS Notification MCP enables AI assistants to trigger native macOS sounds, visual notifications, and text-to-speech. Built for Claude and other AI models using the Model Context Protocol. | |
| mcp-tool-server devjason41/mcp-tool-server A TypeScript prototype for an MCP-style registry providing local utility tools for shell command execution, filesystem access, and search functionality. It features Zod input validation and project manifest resource exposure for embedding i | |
| Continuum devjoaocastro/continuum Automatically extracts architectural decisions, patterns, and insights from Git commits to build a local, structured project memory. It exposes this living context to AI tools via MCP, allowing them to understand the historical reasoning an | |
| lashing devjoinedthechat/lashing It enables AI agents to propose and apply container shipment bookings, amendments, and cancellations via DCSA standards, with every write validated, authorized, and logged in a hash-chained ledger. It also provides tracking and schedule loo | |
| music-assistant-mcp devjourney/music-assistant-mcp Enables AI assistants to control Music Assistant for music search, library browsing, playback, queue management, and playlist curation. | |
| UniFi MCP devjourney/unifi-mcp Enables AI assistants to manage UniFi Network, Protect, and Access infrastructure through MCP tools, with support for local controllers and cloud relay. | |
| MCP Internet Server devk86/mcp-internet-server Enables web search and webpage content fetching with SSRF protections, returning structured results. | |
| open-source-contribution-mcp-server devkamani9313-lab/open-source-contribution-mcp-server An MCP server that enables AI clients to autonomously discover, analyze, fix, test, submit, and track open-source contributions on GitHub through specialized tools. | |
| knowledgebased devkanro/knowledgebased Provides semantic search and a tag-based knowledge graph for any project, auto-discovering local markdown knowledge bases with YAML frontmatter. | |
| Jarvis-local devkewalramani/jarvis-local Enables a local, cost-controlled voice assistant for macOS that routes requests between local and Claude models, provides draft-only email and calendar access via Thunderbird and Granola with a restricted allowlist, and supports meeting fol | |
| notes-mcp-server-l16 devkievskiy/notes-mcp-server-l16 A Model Context Protocol (MCP) server that gives Claude a persistent personal notebook. Notes are stored on disk as JSON, so they survive restarts and are shared across every tool and resource. | |
| Remote MCP Server Authless devkotab/remote-mcp-server-authless A deployable MCP server on Cloudflare Workers that provides tools without requiring authentication, allowing users to connect from Cloudflare AI Playground or Claude Desktop. | |
| DotBot MCP Server devl0rd/discordinator Enables authenticated MCP clients to control a real Discord bot through 78 typed tools, including messaging, moderation, channel, role, event, and AutoMod operations. Access is restricted by whitelisted triggers, explicit capability scopes, | |
| Agent Commerce Gateway devlab-group/agent-commerce Enables AI agents to discover, call, and pay for existing HTTP APIs over MCP with x402 paywalls, non-custodial settlement, and no code changes to the backend. | |
| hebros-mcp devladinci/hebros-mcp Provides coding agents with a compact map of a TypeScript/TSX codebase, enabling direct answers about symbol locations, imports, dependencies, and references while reducing token usage. | |
| Not Obvious devladpopov/not-obvious Enables users to map the clichéd answers LLMs give to a prompt, generate and remix ideas away from them using structured creativity techniques, and measure originality and usefulness with embedding-based scoring and web-prevalence checks. | |
| windows-admin-mcp devladpopov/windows-admin-mcp An MCP server that enables AI assistants to manage, monitor, and diagnose Windows systems through 42 tools across 8 modules, including services, event viewer, task scheduler, processes, network, diagnostics, observability, and safety featur | |
| linkedin_mcp devleads/linkedin_mcp MCP server for automating LinkedIn actions such as reading feeds, sending messages, creating posts, and managing connections. Uses browser automation with proxy and stealth support. | |
| mcp-discord devli13/mcp-discord An MCP server providing 26 tools for Discord API interactions, enabling message management, moderation, channel operations, and server inspection through Claude Code, Paperclip agents, or other MCP-compatible clients. | |
| mcp-granola devli13/mcp-granola An MCP server that provides AI agents access to Granola meeting notes. It enables searching notes, retrieving full content with transcripts, and paginating through meeting history. | |
| Firestore MCP Server devlimelabs/firestore-mcp Provides secure, permission-controlled access to Firebase Firestore databases with full CRUD operations, advanced queries, batch operations, and transactions through a standardized MCP interface. | |
| Lulu Print MCP Server devlimelabs/lulu-print-mcp Provides integration with Lulu Print API for print-on-demand services through Claude Desktop and other MCP clients, enabling users to create and manage print jobs, validate files, calculate costs, and handle shipping for books and printed m |
44,051–44,100 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.