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 |
|---|---|
| HomeBoxMCP businessnone/homeboxmcp Enables natural-language read and write access to a Homebox inventory, including searching and managing items, locations, tags, and attaching files such as receipts and warranties. | |
| WhatsApp MCP Stream businessnone/whatsappmcp Enables programmatic WhatsApp automation through MCP, including sending messages, managing chats and contacts, searching conversation history, and exchanging media files. | |
| Portals MCP busportals/portals-mcp Enables Claude to design and build interactive 3D games within the Portals virtual platform through direct API integration. It facilitates automated asset placement, interaction logic configuration, and quest management using natural langua | |
| Agent Harness Kit busra530/agent-harness-kit Provides a provider-agnostic MCP server that runs structured multi-agent workflows by owning task claims, action logs, handoffs, and server-side health gates over a shared filesystem and database. It enables coordinated Explorer, Consultant | |
| read-website-fast busra822/mcp-read-website-fast Enables MCP clients and AI agents to fetch webpages, remove boilerplate, and convert content into clean Markdown with low token usage, optionally crawling multiple pages and preserving links. | |
| Social Media Scraper busra8477/custom-mcp-server Enables AI assistants to retrieve public profile data from LinkedIn, Facebook, and Instagram and to perform Google web searches through RapidAPI and Serper. | |
| Sub-Agents MCP Server busrabarbosa/sub-agents-mcp Enables users to define reusable Markdown-based coding agents and run them through any MCP-compatible client with a chosen coding CLI, returning results to the same conversation. It also supports shared backend and model configuration, perm | |
| JMComic AI MCP Server busraf483/jmcomic-ai Enables AI agents to search, browse, download, and post-process JMComic albums and chapters through MCP tools and resources, with favorites, comments, rankings, task control, account login, and runtime configuration. Supports asynchronous d | |
| uisight busrag99/uisight Runs live, URL-synced mobile and desktop browser sessions and returns measured UI findings — contrast ratios, sub-44px touch targets, overflow, theme drift, clipped or covered controls — as precise text tied to selectors, so an agent can fi | |
| jev-browser-mcp busrakilic42/jev-browser Enables MCP clients to drive Playwright browser automation through natural-language goals, with Jev/TypeSafe System One deciding targets, actions, values, completion, errors, and irreversible steps. It also exposes tools for checks, page re | |
| Codexless busralaurent173/codexless Enables ChatGPT to inspect and edit local projects, run bounded commands, use Git, automate Chrome or Edge, and control connected Excel workbooks, while invoking the Codex model only when explicitly needed. | |
| MCP Python Interpreter busraprice/mcp-python-interpreter Enables LLMs to interact with Python environments, execute code or scripts, manage packages, and read/write files within an isolated working directory. | |
| Sonicmatch busraprice/sonic-match-mcp Enables agents to ingest local video files or URLs, analyze footage for mood, energy, speech, and scene cuts, and receive license-labeled royalty-free or Creative Commons BGM shortlists with a 12–20s hook window, beat-snapped cut suggestion | |
| MCP-PostgreSQL-Ops busraz5104/mcp-postgresql-ops Enables AI assistants to perform PostgreSQL database operations, monitoring, and management via natural language, covering performance analysis, bloat detection, lock/deadlock monitoring, autovacuum and schema inspection with read-only prod | |
| Flipper Zero MCP Server busse/flipperzero-mcp Modular MCP server for interacting with a Flipper Zero from MCP-capable clients (including Claude Desktop). Supports system info, BadUSB scripts, and music playback over USB or WiFi. | |
| tripstudio bustakar/tripstudio MCP server for travel-planning agents to create and manage concise Markdown briefs and validated structured trip documents, without booking or altering travel. | |
| kev-mcp busy-office/kev-agent-kit Enables coding agents to query a locally running Kev decision model through MCP tools, returning calibrated probabilities for typed questions such as yes/no, choice, and score. | |
| BambooHR MCP Server busybee3333/bamboohr-mcp-2026-complete A comprehensive MCP server for BambooHR with 47 tools covering employee management, time off, reports, benefits, payroll, goals, training, files, and webhooks, plus 18 React-based UI apps. | |
| Calendly MCP Server busybee3333/calendly-mcp-2026-complete Complete MCP server for Calendly API v2 with 40+ tools and 12 interactive React apps, enabling calendar management, scheduling, and user operations. | |
| ClickUp MCP Server busybee3333/clickup-mcp-2026-complete Complete Model Context Protocol server for ClickUp, enabling interaction with tasks, spaces, lists, docs, goals, time tracking, and more through 93 tools and 18 React MCP apps. | |
| Constant Contact MCP Server busybee3333/constant-contact-mcp-2026-complete Provides comprehensive access to the Constant Contact API v3 for email marketing, campaign management, contact management, analytics, and automation through MCP tools. | |
| mcp-server-deel busybee3333/deel-mcp-2026-complete A production-quality MCP server for the Deel API that enables managing global HR, payroll, contractors, invoices, payments, and compliance through 48 tools. | |
| @mcpengine/etsy busybee3333/etsy-mcp-2026-complete Comprehensive MCP server for the Etsy API v3, providing 50+ tools to manage listings, shops, orders, payments, and more through natural language. | |
| FieldEdge MCP Server busybee3333/fieldedge-mcp-2026-complete Provides comprehensive access to the FieldEdge field service management platform through over 87 tools and 16 React applications. It enables users to manage customers, jobs, scheduling, and invoicing through natural language or integrated U | |
| GoHighLevel (GHL) MCP Server busybee3333/go-high-level-mcp-2026-complete Provides access to over 460 tools within the GoHighLevel CRM, allowing AI assistants to manage contacts, opportunities, messaging, and business workflows through natural language. | |
| Keap MCP Server busybee3333/keap-mcp-2026-complete Complete Model Context Protocol server for Keap (formerly Infusionsoft) with 111 tools and 22 React apps. | |
| Mailchimp MCP Server busybee3333/mailchimp-mcp-2026-complete Comprehensive MCP server for Mailchimp Marketing API v3.0 with over 104 tools and 15+ React UI apps, enabling management of campaigns, audiences, ecommerce, automations, reports, and more via natural language. | |
| Pipedrive MCP Server busybee3333/pipedrive-mcp-2026-complete Comprehensive MCP server for Pipedrive CRM with 118 tools and 27 UI apps, enabling full CRM operations via natural language. | |
| Rippling MCP Server busybee3333/rippling-mcp-2026-complete Provides 50+ tools for interacting with Rippling's HR platform, including employee management, payroll, time tracking, benefits, recruiting, learning, devices, groups, and custom objects, all through natural language. | |
| ServiceTitan MCP Server busybee3333/servicetitan-mcp-2026-complete Provides 108 tools and 15 React apps to manage ServiceTitan field service operations, including jobs, customers, estimates, invoices, dispatching, technicians, equipment, memberships, inventory, locations, marketing, reporting, tags, and pa | |
| Toast MCP Server busybee3333/toast-mcp-2026-complete Enables AI assistants to manage restaurant operations by integrating with Toast POS, including orders, menus, employees, payments, inventory, and reporting through 50+ tools and 18 React apps. | |
| TouchBistro MCP Server busybee3333/touchbistro-mcp-2026-complete A comprehensive MCP server for TouchBistro restaurant management, offering 190 tools across 12 domains and 15 React apps for visual management. | |
| Trello MCP Server busybee3333/trello-mcp-2026-complete A comprehensive integration providing 96 tools and 18 interactive React apps for full Trello API coverage, including board management, card operations, and workflow analytics. It enables users to perform complex project management tasks and | |
| Wave MCP Server busybee3333/wave-mcp-2026-complete Comprehensive MCP server for Wave Accounting, providing 45+ tools across invoicing, customers, products, transactions, bills, estimates, taxes, and financial reporting, plus 17 pre-built UI workflows. | |
| Wrike MCP Server busybee3333/wrike-mcp-2026-complete Complete MCP server for Wrike project management with 70+ tools and 20 interactive React apps, enabling task, project, and workflow management via natural language. | |
| Zendesk MCP Server busybee3333/zendesk-mcp-2026-complete Comprehensive MCP server providing 89 tools and 13 React UI apps for complete Zendesk Support API integration, enabling ticket, user, organization, and automation management. | |
| context-index-mcp butler-kasagi/context-index-mcp A lightweight MCP server that maps keywords to file paths instantly using a JSON index, enabling fast context retrieval for AI agents without embeddings or vector databases. | |
| applemusic-mcp butler38235/applemusic-mcp Enables MCP clients to search the catalog, manage playlists, folders, and library items, and control playback, ratings, and the Up Next queue across macOS, Windows, and Linux. It selects among native Music.app, Safari, Chrome, and web API e | |
| jevmem butler48171/jevmem Saves decisions, rules, bugs, to-dos, and failed approaches from Claude Code, Cursor, and Codex chats into a repository file, then brings relevant entries back in later sessions and checks tool calls against saved rules before commands or e | |
| Medical MCP Server butler699/medical-mcp Enables AI assistants to query authoritative medical sources such as FDA, WHO, PubMed, RxNorm, and ClinicalTrials.gov for drug information, safety data, health statistics, clinical guidelines, pediatric resources, and evidence-graded litera | |
| Claude Telegram Supercharged butt621/claude-telegram-supercharged Runs coding sessions around the clock from Telegram chat, with two-way voice notes, persistent memory across restarts, scheduled reminders, calendar access, and inline-button prompts. Streams live progress for every tool call so users can w | |
| flameox butt91/flameox Enables coding agents to coordinate profilers, benchmark tools, trace processors, and direct local targets so that explicit artifacts or commands become bounded runtime evidence with recorded provenance, coverage, and limitations. Its analy | |
| swissdevjobs butt91387/swissdevjobs-cli Enables AI agents to search, filter, and apply across nine job boards in eight countries — including ~4,700 salary-transparent tech jobs plus Swiss and Singapore listings — with results returned as JSON data and applied jobs tracked so dupl | |
| butterbase butterbase-ai/butterbase AI-native open-source backend-as-a-service. Manage Postgres with RLS, auth, file storage, serverless TypeScript functions, durable objects, realtime, KV, AI gateway, and RAG via MCP, either HTTP at /mcp on a self-hosted instance or stdio wi | |
| elgato-keylight butterflyskies/elgato-control-home-automation MCP server for controlling Elgato Key Lights. Enables turning lights on/off, adjusting brightness and color temperature, applying presets, and triggering effects via Claude. | |
| butterstack butterstack/butterstack-mcp Grants AI assistants read/write access to your ButterStack game dev pipeline, including tasks, builds, asset approvals, and project status through MCP. | |
| Buu AI MCP Server buu-ai/buu-mcp-server MCP Server for Buu AI | |
| Tushare_MCP buuzzy/tushare_mcp A Model Context Protocol server that provides intelligent stock data assistance through Tushare's financial data API, enabling users to query comprehensive stock information, financial data, and market indices through natural language. | |
| MCP Database Bridge buvaneswaraneb/mcp-database-bridge A secure, read-only MCP server that empowers Claude Desktop and AI agents to safely query and inspect local SQLite databases. | |
| nbdpsy-mcp buxiulei/nbdpsy-server MCP server for managing Xiaohongshu (Little Red Book) account matrix operations, including account management, cookie sharing, and note publishing via MCP tools. |
36,151–36,200 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.