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 |
|---|---|
| GSC-MCP digitalaiseo/gsc-mcp Enables natural language analysis of Google Search Console data through Claude, with pre-built tools for quick wins, cannibalization detection, content decay, and more. | |
| digitalassetscan-mcp digitalassetscan/digitalassetscan-mcp Enables interaction with the public Digital Asset Scan API to analyze digital assets, list assets, retrieve methodology, and poll asynchronous analysis jobs over MCP. | |
| Shufersal MCP Server digitalbastard103/shufersal-cart Enables AI assistants to build and edit a Shufersal online grocery cart from a text list, a past order, or a saved list — searching products, adding items by code, setting quantities, removing items, viewing line prices and totals, and pick | |
| Murder Mystery MCP Server digitalboopltd/murder-mystery-mcp A procedurally-generated murder mystery game engine that enables AI agents to generate mysteries, interrogate AI suspects with memory and emotions, search for clues, and solve crimes through MCP tools. Features RAG-powered investigation too | |
| @playbykey/theory-mcp digitalbrewllc/playbykey-dev-tools An MCP server exposing @playbykey/theory as AI-callable music theory tools. Compute chords, scales, progressions, transpositions, and MIDI/frequency conversions instead of having your AI assistant guess at music theory from training data. | |
| service-economics digitalcoreapp/dg-mcp-free Free service management tools — playbooks, benchmarks, and instant service health analysis.
DigitalCore MCP gives you free access to service management expertise directly in your AI assistant. Run a Service Reality Check to score your serv | |
| desk-mcp digitaldog1/desk-mcp Enables AI clients to see and control a Windows desktop through screenshots, built-in OCR, mouse and keyboard input, and accessibility trees read via UI Automation, MSAA and Chrome DevTools Protocol. It also manages windows, virtual desktop | |
| explee-mcp digitaldrreamer/explee-mcp MCP server wrapping the Explee B2B data API, enabling AI agents to search companies and people, enrich contact data, run AI agents, and manage deduplication lists. | |
| MCP Dolibarr Expert digitalfactorysn/mcp-dolibarr A complete MCP server for Dolibarr ERP/CRM, enabling AI assistants to perform billing, accounting, CRM, project, stock, and contract management. | |
| MCP Weather Server digitalgreenorg/agmcp Enables AI agents to access real-time and historical weather data through multiple weather APIs including OpenMeteo, Tomorrow.io, and OpenWeatherMap. Provides comprehensive meteorological information including current conditions, forecasts, | |
| Bouncie MCP Server digitalhen/bouncie-mcp An MCP server that connects Bouncie OBD2 vehicle tracking data to AI assistants. It enables users to retrieve real-time vehicle stats, health diagnostics, and detailed trip history through the Bouncie API. | |
| SuperFaktura MCP Server digitaliko/superfaktura-mcp Enables AI assistants to interact with the SuperFaktura invoicing system for managing invoices, clients, and expenses via natural language. | |
| Stellwerk digitalisierungswerkstatt/stellwerk-business-os Self-hosted back office for a one-person business (Flask + SQLite, German UI). Six MCP tools let Claude manage tasks and time entries; each write returns a preview first. | |
| DigitalOcean MCP Server digitalocean/digitalocean-mcp A server that exposes DigitalOcean App Platform functionality through standardized tools, enabling AI assistants to directly manage your DigitalOcean apps without writing code or memorizing API endpoints. | |
| AgentCost digitalpromptmarket-beep/alphaforensics-mcp MCP server that analyzes AI agent session logs to find token waste and optimization opportunities. | |
| Google Ads API v20 MCP Server digitalrocket-biz/google-ads-mcp-v20 Provides comprehensive access to Google Ads API v20, enabling AI assistants to manage campaigns, accounts, assets, and reporting through natural language. It features automatic retry logic, GAQL query support, and advanced functionality for | |
| Digital Samba Embedded API MCP Server digitalsamba/embedded-api-mcp-server Enables managing video conferencing platform tasks like creating rooms, managing recordings, and controlling live sessions through natural language with AI assistants. | |
| Lead Cleanup MCP Lite digitalsolutionsmagic/lead-cleanup-mcp-lite Enables users to clean and de-duplicate sales lead lists locally without API keys or network calls. It normalizes names, emails, phone numbers, and website domains, drops invalid emails, removes duplicate leads by email, and validates email | |
| smart-mcp-server digitalsqr/smart-mcp-server Enables AI assistants to securely interact with FHIR R4 servers for clinical decision support workflows, including PlanDefinition execution, FHIR resource management, terminology services, and Questionnaire/StructureMap transformation via M | |
| Telecom Event Oracle digitaltiffany1/telecom-event-oracle-mcp Provides real-time LNP/WLNP (Wireless Local Number Portability) and LRN auditing. Features specialized congestion logic for 2026 global events. Essential for routing agents managing wireless and wireline transit. | |
| Genesys MCP digitalvanguardsolutions/genesys-mcp Enables AI agents to interact with Genesys Cloud platform through MCP tools, resources, and prompts, supporting queues, conversations, users, presence, and analytics with production-ready features like Streamable HTTP and per-request authen | |
| resolve-mcp digitalworkflowcompany/resolve-mcp Enables AI-driven DaVinci Resolve 21 automation with 88 tools for project management, timeline editing, color grading, AI analysis, rendering, and dailies creation. | |
| DB Schenker Shipment Tracker digitalxenon98/sendify-dbschenker-mcp Tracks DB Schenker shipments by reference number, providing detailed shipment information including sender/receiver details, package information, and complete tracking history with automatic rate limiting and caching. | |
| Fluxito Community digitalxperiments/fluxito-community Connects AI assistants to 27 marketing and analytics platforms, enabling read-only access to data, built-in tracking audits, and KPI context for informed answers. | |
| MCP Apps Playground digitarald/mcp-apps-playground A demo MCP server showcasing interactive HTML UIs for tools like list sorting, flame graphs, and feature flags, enabling bidirectional communication between user and agent. | |
| AutoMac MCP digithree/automac-mcp An experimental MCP server providing full control over the macOS user interface through mouse, keyboard, and window management tools. It enables AI assistants to automate desktop tasks by utilizing native accessibility APIs and OCR for real | |
| teamhood-mcp digiti/teamhood-mcp A read-only MCP server that enables querying Teamhood workspaces, users, boards, items, and time logs through the Teamhood Open API, running locally via stdio so your API key stays on your machine. | |
| bunnycdn-mcp digitizers/bunny-mcp Enables AI assistants to manage Bunny.net services such as pull zones, DNS, storage, video streaming, edge scripting, security, and Magic Containers through natural language. | |
| nanoGentzen digitlib/nanogentzen-mcp Enables AI agents to be governed by formal Gentzen sequent calculus proof trees, with human-in-the-loop approval gates and cryptographic audit trails for consequential actions. | |
| MailInApp for Claude Desktop digitload/mailinapp-mcpb Enables Claude Desktop to interact with MailInApp projects, campaigns, and contacts. Allows designing and reading interactive email results with explicit confirmation for sending real campaigns. | |
| anymd digitopvn/anymd Enables AI agents to read public web content as clean Markdown, search a private library of previously read documents, and access these tools via MCP, REST API, CLI, and WebMCP. | |
| Motion MCP digitopvn/motion-mcp Enables MCP clients to produce motion videos from a brief, using frontier models for creative direction and cheaper models/tools for rendering and finishing. | |
| Property MCP Server digitsouler/property-mcp-server Enables AI assistants to operate property management systems via natural language, covering repair orders, owner info, payments, notices, and inspections. Features a full agentic workflow with human-in-the-loop and observability. | |
| context-killer-mcp dignitas00/context-killer-mcp Enables Claude to offload code generation to Google's Gemini, saving tokens by writing files directly to disk without returning the content to the chat. | |
| ai-crm-engine digoo2008/ai-crm-engine An MCP-native CRM backend for AI agents, enabling customer, opportunity, note, follow-up, and pipeline health management through 15 MCP tools. | |
| obsidian-cli-mcp digster/obsidian-cli-mcp Enables interaction with Obsidian vaults through the official Obsidian CLI, allowing note management, search, and vault operations without plugins or API keys. | |
| Azure MCP Server digvijayyadav93/azure-mcp Provides MCP tools for accessing customer, order, and sales summary data, supporting both SQLite and HTTP API backends. | |
| google-scholar-mcp dihannahdi/google-scholar-mcp Enables AI assistants to search and analyze Google Scholar publications, authors, citations, and download papers. | |
| Mycelium dihannahdi/mycelium An on-call agent for data incidents, built on a bio-inspired context protocol. It triages data quality and freshness issues using DataHub, computing severity, blast radius, and ownership from the catalogue before generating prose. | |
| turath dihannahdi/turath MCP server to search and retrieve passages from a corpus of 7,872 classical Islamic books via the Sahifah API, with full citations and mu'tabar filtering. | |
| MCP Google Sheets Server diitrashed/mcp-google-sheets Provides full programmatic access to Google Sheets, enabling CRUD operations, permission management, formatting, and spreadsheet discovery through a standardized MCP interface. | |
| wsl-chrome-mcp-bridge dijdzv/wsl-chrome-mcp-bridge A bridge to launch Chrome on Windows from WSL2 and proxy Chrome DevTools MCP tools. It enables browser automation via Claude Code in WSL2 by managing Chrome's lifecycle and exposing debugging capabilities. | |
| octagon-mcp-server dijkstra41327/octagon-mcp-server Enables users to ask natural-language questions and receive structured, source-backed answers across SEC filings, earnings transcripts, company financials, stock and crypto market data, and prediction markets news and research. | |
| Typst MCP Server dijkstra5745/typst-mcp Enables AI models to convert LaTeX to Typst, validate Typst syntax, access Typst documentation, and render Typst code as images. | |
| swissdevjobs dijkstra7232/swissdevjobs-cli Lets AI agents search, filter, and apply to salary-transparent tech jobs across nine job boards in eight countries, filtering by pay, remote work, tech stack, and location while tracking applications to avoid duplicates. It returns JSON-fir | |
| Niblet dijkstra846/niblet-skill-mcp Enables coding agents to ground UI work in real product screens by fetching concrete screen references as inline images, along with fonts, icons, and animated-icon materials that include their recorded licenses. It also returns the recorded | |
| telegram-mcp dikaglorya/telegram-mcp Connects an agent to your personal Telegram account over MTProto, exposing 69 tools to read, send, search and manage messages, chats, media, contacts and admin actions without a bot token. Runs locally on stdio with in-chat login and no inb | |
| ai.studio/woocommerce-gold diklaaltman91-ux/09-woocommerce Enables WooCommerce store management via the WooCommerce REST API wc/v3, with tools for products, orders, coupons, customers, reports, bulk operations, variations, categories, SEO meta, BYOK descriptions, and daily digests. | |
| ai.studio/etsy-gold diklaaltman91-ux/16-etsy-gold Enables Etsy sellers to manage their shops via natural language, including listing CRUD, bulk price and quantity updates by SKU, whole-shop A-F grade audits, photo uploads, shipping profiles, conversations, receipts, fulfillment tracking, a | |
| ghl-gold diklaaltman91-ux/17-ghl-gold Enables AI assistants to operate GoHighLevel agencies through the official v2 API, managing contacts, deals, conversations, appointments, tags, custom fields, workflows, and pipeline reports with bulk operations and fail-closed security. |
44,651–44,700 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.