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 |
|---|---|
| blender-studio-pro-mcp cristoferarango/blender-studio-pro-mcp This MCP server enables complete control of Blender from any MCP client, offering 221 dedicated tools and a universal bridge for 1,500–2,500+ bpy.ops operators across 33 modules for modeling, VFX, rendering, simulation, animation, compositi | |
| AutoCAD MCP Server cristoferlabs/mcp---autocad An MCP server that bridges Claude with AutoCAD, enabling to generate architectural floor plans, draw geometry, and export DXF files just by describing what you need in natural language. | |
| compare-mcp cristophereasygoing927/compare-mcp Enables multi-model code review by fanning out issues to multiple LLMs simultaneously, diffing their unique insights, optionally running debate rounds, and dispatching subagents to implement fixes with git commits. | |
| qt-mcp cristopulos/qt_mcp_server An MCP server for capturing screenshots of Qt/desktop windows and performing filesystem operations, enabling AI clients to inspect and modify project files. | |
| MCP FacturaScripts cristotodev/mcp-facturascripts An MCP server that integrates with the FacturaScripts ERP system, providing resources and tools to manage clients, products, invoices, accounting entries, and business analytics through natural language. | |
| hypixel-skyblock-mcp crithitstudio/hypixel-skyblock-mcp Fetches Hypixel SkyBlock data including profiles, economy, and progression, returning compact JSON for AI-powered guides and tips. | |
| Sims3-MCP critical-reynolds/sims3-mcp Connects an AI assistant to a running copy of The Sims 3 so it can observe households and needs, queue interactions through the real pie menu, control time, answer dialogs, manage stats, careers and relationships, shop in buy mode, use buil | |
| wp_criu criustudio/wp-criu-registry Manages multiple WordPress sites through the Codex WP Admin Bridge plugin, offering site inspection, plugin/theme management, option reading/writing, file operations, read-only SQL, REST proxy, translation checks, and WooCommerce checkout f | |
| ultrahuman_mcp crixalis17/ultrahuman_mcp Exposes real-time health data from the Ultrahuman Ring to AI agents via the Model Context Protocol, providing optimized summaries with trend analysis and actionable insights. | |
| RockHound crjiminez03/colorado_rockhound-geospatial-mcp-platform Enables AI agents to query curated spatial data about Colorado rockhounding, including finding vacant mining claims near mineral occurrences and checking land access at coordinates. | |
| mcp-pyatv crlian/mcp-pyatv MCP server for controlling Apple TV, HomePod, and AirPlay devices via pyatv, offering 32 tools for playback, navigation, volume, apps, and more. | |
| gong-mcp crmchattie/gong-mcp Enables querying Gong calls and transcripts through natural language, allowing users to list calls with date filtering and retrieve detailed transcripts with participant context. | |
| plaid-mcp crmchattie/plaid-mcp MCP servers for the Plaid API, providing tools to access Plaid financial data and documentation. Includes an authenticated API server for account, transaction, and investment operations, and an unauthenticated docs server for searching Plai | |
| DrissionPage BetterMCP crmmc/drissionpage-bettermcp An MCP server that wraps DrissionPage to provide comprehensive browser automation tools, including tab management, element interaction, network capture, and more, with AI-friendly tool descriptions and 255 unit tests. | |
| CRMy crmy-ai/crmy Provides AI agents with operational customer context, including typed revenue objects, persistent state, scoped tools, and human-in-the-loop handoffs through MCP, REST, and CLI. | |
| godmod3-mcp crnisamuraj/g0dm0d3-mcp A bridge for G0DM0D3 that exposes advanced AI capabilities through MCP tools, including multi-model racing, hive-mind synthesis, and secure chat options. | |
| Context Engineering MCP Server croakingtoad/context-engineering-mcp Automates Cole Medin's context engineering methodology to generate high-quality Product Requirements Prompts (PRPs) by analyzing existing codebases, asking contextual questions, and synthesizing insights. | |
| MCP Jina Supabase RAG croakingtoad/mcp-jina-supabase-rag Crawls and indexes documentation websites to Supabase with vector embeddings for RAG, using smart sitemap discovery and Jina AI for fast content extraction with multi-project support. | |
| tdlib-mcp-server crocodile-beep/tdlib_mcp_server Connects AI agents to Telegram via the official TDLib library, enabling tools like getting user info, listing dialogs, and searching messages. | |
| cesm-runner-mcp crocodile-cesm/mcp_cesm_runner MCP server for driving CESM case lifecycle: setup, build, submit, and monitor. Complements CrocoDash MCP for grid creation and forcing. | |
| regional-ocean-debugger-mcp crocodile-cesm/mcp_regional_ocean_debugger MCP server for debugging regional ocean (MOM6 + CESM) model runs, combining log analysis tools with a searchable knowledge base of expert interview transcripts. | |
| whatsapp crodriguez83407/whatsapp-claude-plugin A stdio MCP server that lets Claude Code sessions be driven directly from WhatsApp chats, with bidirectional messaging and media, voice-note transcription, pairing-code access control, per-group personalities, and emoji-reaction approval of | |
| ctx crodris/ctx MCP server for context switching across git worktrees and Claude Code agent sessions, providing a board of worktree status and distilled task summaries. | |
| gribs_mcp croesnick/gribs_mcp MCP server for gribs.net, the Grünen-intern platform, providing read-only access to search and browse Antragsbörse posts and fetch recent public posts, with source URLs and timestamps for traceability. | |
| npm-mcp crogers2287/npm-mcp Enables AI assistants to manage Nginx Proxy Manager, including proxy hosts, SSL certificates, streams, and more. | |
| Hippycampus MCP Server cromwellian/hippycampus A LangChain-based server that supports dynamic loading of OpenAPI specifications and enables natural language interaction with web services through Server-Sent Events (SSE) transport. | |
| be-amsa-reporter-te cromwelmaunahan/be-amsa-reporter-te Automates BE AMSA review by validating EFF folders, driving AMSA 5.1 to generate reports and graphs, and producing a PowerPoint summary. Designed to not hang with worker threads and timeouts. | |
| context-guard crona16/devin-resource-guard-mcp Enables autonomous coding agents to check memory, CPU, and disk headroom before heavy work, emitting cgroup-aware NEAR_OOM_THRESHOLD alerts that let them back off before an OOM kill or context blowup. It also scans a workspace for token-hea | |
| Cronlytic MCP Server cronlytic/cronlytic-mcp-server A comprehensive Model Context Protocol (MCP) server that integrates with the Cronlytic API to provide seamless cron job management through LLM applications like Claude Desktop. | |
| cronozen-proof cronozen/proof Tamper-proof audit trail for AI decisions. 6 tools to record, verify, and export cryptographic proof chains via MCP. | |
| @crontinel/mcp-server crontinel/mcp-server Connects AI assistants to Crontinel, enabling natural language queries about cron jobs, queues, Horizon status, and alerts without opening a browser. | |
| Cronty MCP cronty-com/cronty-mcp A FastMCP server that enables AI agents to schedule notifications and reminders via Upstash QStash and NTFY. | |
| Home Assistant MCP Server cronus42/homeassistant-mcp A comprehensive Model Context Protocol server providing 60 tools across 9 categories to interact with and manage Home Assistant smart home systems via the REST API. | |
| Transmission MCP Server cronus42/transmission-mcp Provides tools for interacting with the Transmission BitTorrent client via natural language, enabling users to manage torrents, configure download settings, and monitor download activity. | |
| Proxmox MCP Server cronus87/proxmoxmcp-production An enterprise-grade management tool that enables Claude Code to securely interact with Proxmox VE for full VM and LXC container management. It provides single-command installation and comprehensive security controls for production-ready dep | |
| AI Team OS cronusl-1141/ai-company Turns Claude Code into a self-driving AI company with autonomous CEO, agent teams, and self-improvement capabilities. | |
| CARLA_MCP croquembouche/carla_mcp Enables scenario control, parking, sensor configuration and visualization, recording/playback, weather and traffic-light management for the customized CARLA UE5 simulator, with ROS 2 bag integration, through MCP tools and resources. | |
| FORGE croresnos/forge Enables exposing any REST or GraphQL API as MCP tools from a single JSON spec, with writes requiring explicit confirmation before being sent. | |
| amp-supervision crosby33/amp-supervision Enables local, stdio-based MCP bridging to supervise Amp coding agents, with tools to spawn, read, send to, and list Amp threads so a supervisor agent can manage turn-based workflows while humans retain approval. | |
| linkding-mcp crosbyh/linkding-mcp An MCP server for Linkding bookmarks and web archival, enabling Claude to search, add, tag, archive, and delete bookmarks including archival snapshots. | |
| nextcloud-tasks-mcp crosbyh/nextcloud-tasks-mcp MCP server for managing Nextcloud Tasks (todos) via CalDAV, allowing Claude to view, add, complete, edit, and delete tasks with GitHub OAuth authentication. | |
| obsidian-vault-mcp crosbyh/obsidian-vault-mcp Enables reading, searching, and modifying Obsidian vault notes directly, including saving conversation summaries and appending to daily notes, with GitHub OAuth authentication. | |
| vikunja-mcp crosbyh/vikunja-mcp Enables AI assistants like Claude to manage Vikunja tasks – view, add, complete, edit, and delete tasks through natural language commands via Vikunja's REST API. | |
| aristotle-mcp crosedev/aristotle-mcp Enables MCP clients such as Claude Code to submit Lean projects and plain-English math problems to an automated theorem prover, check job status, download or extract results, and manage proving jobs. | |
| Crosmos MCP Server crosmos-labs/crosmos-mcp MCP server for the Crosmos memory layer, enabling semantic, keyword, and graph retrieval of memories, as well as storing content with automatic entity and relation extraction. | |
| velora-mcp-demo crossi-dev/velora-mcp-demo A free public demo of Velora's agentic-commerce MCP toolkit, hosting ~49 real tool schemas with three honesty levels: pure validations, read-only sample data, and refused side-effect tools. | |
| CrossingKey MCP server crossingkey-holdings/crossingkey-mcp-origin Enables agent commerce with prepaid credits, authenticated bounded paid execution, and machine-readable fulfillment. | |
| @crossly/buyer-mcp crossly-dev/crossly-buyer-mcp Enables an AI agent to act on a shopper's Crossly account, managing cart, orders, wishlists, offers, and cashback while quoting carts without completing purchases. | |
| @crossly/mcp crossly-dev/crossly-mcp Enables AI agents to fully manage a Crossly reselling account, including listing and crossposting items across major marketplaces, handling orders, tracking, refunds, buyer messages, offers, analytics, and automation rules. | |
| Crossmint Checkout MCP Server crossmint/mcp-crossmint-checkout Enables AI agents to programmatically purchase physical and virtual goods from platforms like Amazon and Shopify using stablecoins, without the need for virtual debit cards or browser automation. |
40,801–40,850 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.