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 |
|---|---|
| understudy barry-lenhart/understudy Enables MCP clients to delegate routine coding tasks to a local model in isolated git worktrees, using test results as a gate and the client as the reviewer before changes are merged. | |
| OpenGrok AOSP MCP barryhsia/opengrok-aosp-mcp Enables intelligent code navigation and analysis for AOSP development using OpenGrok, with 18 tools for searching definitions, references, AIDL, Binder, system services, and more. | |
| ai-model-selector-mcp barrymister/ai-model-selector-mcp Provides AI assistants with structured access to metadata for 76+ AI models across Ollama, Claude, and OpenRouter, enabling capability queries, compatibility checks, model comparisons, and task-based recommendations. | |
| Aider RepoMapper MCP Server barrynerd/mcp-repomapper Generates optimized repository maps and enables identifier search with graph-ranking, designed for efficient LLM context caching and codebase navigation. | |
| Freedom Commerce Protocol barrypmarshall/freedom-commerce The Agent-Native Marketplace — where AI agents discover, negotiate, and purchase services without a single line of HTML.
Freedom Commerce is an open protocol and reference implementation for agentic commerce | |
| MCP-Discord barryyip0625/mcp-discord A Discord Model Context Protocol server that enables AI assistants to interact with Discord, providing functionality for sending messages, managing channels, handling forum posts, and working with reactions. | |
| billingo-mcp bartadaniel/billingo-mcp MCP server for the Billingo V3 Hungarian invoicing API. Manage invoices, partners, products, spendings, and bank accounts from any MCP client. | |
| nano-banana-mcp bartadaniel/nano-banana-mcp MCP server for generating and editing images using Google Gemini API. Supports text-to-image generation, image editing, and image description. | |
| web-search-mcp bartdorlandt/web-search-mcp Provides a web search tool with citations by running Claude Code CLI in an isolated Docker container, enabling search even in environments without direct Anthropic web search support. | |
| Keep Mac Awake bartdudzic/keepmacawake Lets an AI agent keep a MacBook awake with the lid closed while a long task runs, through the Keep Mac Awake app on the Mac. Three tools: status, start (1 to 168 hours or no time limit after the user agrees) and stop. | |
| Gemini Thinking Server bartekke8it56w2/new-mcp An MCP server implementation that leverages Google's Gemini API to provide analytical problem-solving capabilities through sequential thinking steps without code generation. | |
| mcp-git-ingest bartest5/adhikasp_mcp-git-ingest MCP server that reads GitHub repository structures and important files, enabling exploration and analysis of codebases. | |
| Azan-MCP bartest5/ahmedeltaher_azan-mcp An MCP server providing comprehensive Islamic utilities, including prayer times, azan, Hijri calendar, du'a, zakat, and the 99 Names of Allah. | |
| Alpaca MCP Server bartest5/alpacahq_alpaca-mcp-server A comprehensive Model Context Protocol server for Alpaca's Trading API that enables natural language trading operations through AI assistants, supporting stocks, options, crypto, portfolio management, and real-time market data. | |
| Excel MCP Server bartest5/haris-musa_excel-mcp-server An MCP server that enables creating, reading, and modifying Excel workbooks, including formulas, formatting, charts, and pivot tables, without requiring Microsoft Excel. | |
| MiniMax MCP Server bartest5/minimax-ai_minimax-mcp Official MiniMax MCP server enabling AI clients to generate speech, clone voices, create videos and images, compose music, and design custom voices via MiniMax APIs. | |
| Ebook-MCP bartest5/onebirdrocks_ebook-mcp Enables natural language interaction with e-books, supporting EPUB and PDF formats. Provides APIs for metadata extraction, table of contents, and content retrieval for AI-powered reading and learning. | |
| Prometheus MCP Server bartest5/pab1it0_prometheus-mcp-server MCP server that enables AI assistants to query and analyze Prometheus metrics through PromQL, with support for metric discovery and authentication. | |
| mcp-server-qdrant bartest5/qdrant_mcp-server-qdrant An MCP server that provides semantic memory on top of Qdrant vector search, with tools to store and retrieve information using embeddings. | |
| MCP Server for LinkedIn bartest5/stickerdaniel_linkedin-mcp-server An MCP server that lets AI assistants like Claude read LinkedIn data through your own logged-in browser session. Access profiles and companies, search for jobs, or get job details. | |
| Stealth Browser MCP bartest5/vibheksoni_stealth-browser-mcp Provides undetectable browser automation for AI agents, bypassing Cloudflare and other anti-bot systems. Includes 97 tools for navigation, scraping, network interception, and element cloning. | |
| JADX-MCP-SERVER bartest5/zinja-coder_jadx-mcp-server Fully automated MCP server built to communicate with JADX-AI-MCP Plugin to analyze Android APKs using LLMs like Claude — uncover vulnerabilities, parse manifests, and reverse engineer effortlessly. | |
| champollion-sulcal-mcp barthelemy-drabczuk/champollion_sulcal_mcp Exposes each stage of the Champollion sulcal embedding pipeline as MCP tools, enabling agents to run, monitor, and debug the pipeline without manual shell commands. | |
| MediaHub bartholomewtj/mediahub-mcp Enables an agent to run a whole home media stack — Plex, Sonarr, Radarr, Prowlarr, qBittorrent, and Bazarr — by conversation: requesting shows and films, seeing what's downloading, fixing stuck torrents, getting recommendations, and freeing | |
| yt-media-info-mcp bartivs/yt-media-info-mcp An MCP server that extracts rich metadata (title, description, duration, chapters, subtitles, statistics, etc.) from media URLs across thousands of sites using yt-dlp, and also provides transcript fetching and search capabilities. | |
| Fantopy MCP Server bartjhv/fantopy-mcp-server Enables AI agents to connect to Fantopy Arena, browse and enter fantasy football contests, build validated lineups, and claim payouts on Solana. | |
| obsidian-mcp-server bartk1990/obsidian-mcp-and-rest Enables local MCP clients to list, read, write, and search notes in an Obsidian vault via an HTTP server running inside Obsidian. | |
| Company Email Assistant bartlomiejnoszka/company-email-assistant Enables authorized users to manage the versioned company YAML configuration and preview generated email responses through an OAuth-protected MCP interface. It supports approved-knowledge-based drafting while keeping prices, conditions, and | |
| kmd bartolli/kmd MCP server for structured markdown knowledge vaults that provides validation, FTS5 search, and wikilink cross-references. Enables AI agents to prime context and search across vaults using two MCP tools and template resources. | |
| Daash bartolome69/garmin-mcp Daash connects Garmin Connect to ChatGPT and Claude. Your assistant reads your runs, splits, sleep, HRV, Body Battery and recovery, and writes structured workouts and whole training plans to your Garmin calendar, so they're on your watch at | |
| Markdownify MCP Server bartoseludwiczuk/markdownify-mcp Converts various file types (PDF, images, audio, DOCX, XLSX, PPTX) and web content (YouTube videos, web pages, Bing search results) into Markdown format for easy reading and sharing. | |
| honest-calendar-mcp bartosz-kuc/honest-calendar-mcp A local MCP server that provides read/write access to Google Calendar without data passing through third parties, enabling AI assistants to manage events directly via the Google Calendar API. | |
| honest-drive-mcp bartosz-kuc/honest-drive-mcp A local Google Drive MCP server with full permission management (share, list, remove permissions), enabling AI agents to manage file sharing and access beyond the official connector. | |
| nfz-mcp bartosz-kuc/honest-nfz-mcp Enables querying the Polish National Health Fund (NFZ) public API for medical waiting lists and service dictionary, allowing AI to compare wait times and find providers. | |
| nip-krs-mcp bartosz-kuc/honest-nip-krs-mcp MCP server for Polish company registries that enables looking up companies by NIP or KRS using public government APIs with no authentication required. | |
| rss-mcp bartosz-kuc/honest-rss-mcp Local MCP server for reading and searching RSS and Atom feeds, enabling AI assistants to fetch feed contents, search entries by keyword, and view feed metadata without any cloud intermediary. | |
| MCP Python Interpreter bartosz1038/mcp-python-interpreter Enables LLMs to manage Python environments and packages, execute Python code or scripts, and read or write files within a secured working directory. It also provides prompts for common Python tasks such as function creation, refactoring, an | |
| read-website-fast bartosz1038/mcp-read-website-fast Enables AI agents and MCP clients to fetch webpages, strip noise, and convert them into clean, token-efficient Markdown. Supports optional crawling, caching, robots.txt compliance, and link preservation. | |
| loci bartoszaktas689/loci Enables AI clients to search and ask questions over local notes, docs, and agent memories with cited answers, while also storing or retracting durable memories, exploring links, and refreshing indexes through shared MCP tools. | |
| io.github.morluto/flameox bartoszchristou83/flameox Enables coding agents to coordinate profilers, benchmark tools, trace processors, and direct local targets on explicit artifacts or commands, returning bounded typed runtime evidence with provenance, coverage, and limitations. Supports anal | |
| Claude IPC MCP bartoszcosta/claude-ipc-mcp Enables different AI assistants to exchange persistent messages with each other across platforms and sessions using simple natural language commands like registering an instance, sending a message, and checking an inbox. This allows multi-a | |
| DSH Crew bartoszfontana82488/dsh-crew Enables orchestrator hosts such as Claude Code, Codex, Antigravity, and Grok to dispatch tasks to DeepSeek Harness agents that appear as native subagents with live progress, tier/effort presets, failure escalation, and workspace dispatch gu | |
| MS 365-21V MCP Server bartoszm96234/ms-365-21v-mcp-server Enables MCP-capable AI clients to access and act on a user's 21Vianet Microsoft 365 resources—mail, calendar, OneDrive, SharePoint, Teams, contacts, and search—via Microsoft Graph China while preserving delegated permissions, confirmations, | |
| Financial Modeling Prep MCP Server bartoszozkan/financial-modeling-prep-mcp-server Enables AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights through 250+ tools covering stocks, ETFs, crypto, forex, commodities, and economics. | |
| Korean DART MCP bartoszqureshi6452/korean-dart-mcp Enables AI assistants to query Korea's OpenDART electronic disclosure system, turning 83 APIs into 15 tools for filings, financials, ownership, and XBRL, plus analyst-style frames for insider signals, accounting risk, quality checklists, an | |
| MCP Memory Keeper bartoszronto/mcp-memory-keeper Provides a persistent memory layer for Claude coding assistants, enabling users to save, search, organize, and restore context, decisions, and progress across sessions using channels, checkpoints, and git-aware tracking. Multiple sessions c | |
| Charlotte bartoszwatson669/charlotte Enables AI agents to browse the web through a persistent headless Chromium session that returns compact, structured page summaries and targeted queries instead of full accessibility-tree dumps. Agents can navigate, observe, search, and inte | |
| duzenbaz bartuabihd/duzenbaz An MCP server that lets AI assistants preview and apply file organization, duplicate cleanup, and batch renames inside folders you explicitly allow, plus read screen-time statistics and optionally search clipboard history. Every file-changi | |
| anwb-mcp bartwaardenburg/anwb-mcp MCP server for ANWB traffic information, route planning, and location search in the Netherlands. Provides real-time traffic incidents, route calculation with turn-by-turn directions, and location search via natural language. | |
| bol-mcp bartwaardenburg/bol-mcp MCP server for the bol.com Retailer API that enables managing orders, offers, shipments, returns, invoices, and commissions via natural language. |
33,051–33,100 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.