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 |
|---|---|
| spotify-mcp chienchuanw/spotify-mcp Enables Claude to control Spotify playback, search tracks/albums/artists/playlists, and manage the queue via the Spotify API. | |
| Popup MCP chietears/popup-mcp A cross-platform MCP server that provides native popup windows for AI agents to gather user feedback, input, and safety confirmations. It enables agents to present interactive questionnaires and secure confirmation prompts for sensitive ope | |
| Yandex-mail-Dot-Connector chiginskiy/yandex-mail-dot-connector Enables users to browse folders, list and search messages, read emails, and retrieve selected attachments through a private read-only MCP bridge with OAuth and safe HTML extraction. | |
| MCP Tool Agent chigurupatiakhil5/mcp-tool-agent A custom MCP server exposing database, ticketing, and external-API tools to both Claude Desktop and a self-built autonomous agent powered by Groq's free-tier LLaMA 3.3. | |
| PyAutoGUI-MCP chigwell/pyautogui-mcp Exposes PyAutoGUI desktop automation functions as MCP tools, enabling mouse control, keyboard input, and screenshot capture. | |
| OpenClaw MCP Server chiharrison/openclaw-mcp Enables Claude clients to securely bridge to self-hosted OpenClaw assistants with OAuth 2.1, offering chat, status, async task management, and routing across multiple gateway instances. | |
| Page Design Guide MCP chihebnabil/page-design-guide-mcp Provides comprehensive design principles and best practices to help LLMs generate modern, accessible web pages through guidance on layouts, colors, and typography. It enables users to review design approaches and access expert recommendatio | |
| google-calendar-mcp chihi913/google-calendar-mcp Enables natural language interaction with Google Calendar, including creating, updating, deleting events and managing recurring events through MCP. | |
| google-spreadsheet-mcp chihi913/google-spreadsheet-mcp MCP server enabling AI agents to read, write, and manage Google Sheets, including sheet manipulation, row/column operations, dropdowns, checkboxes, and conditional formatting. | |
| ezmcd-mcp chiiz0/ezmcdonalds A local-first stdio MCP server that lets personal agents use user-authorized McDonald's China accounts to browse stores and menus, verify discounts, place pickup orders, and pay with McWallet under local spending policies. It provides accou | |
| Alberta Tax Agent chikeka/alberta-tax-agent An MCP server delivering Alberta tax accounting and law expertise, with 47 tools across 10 domains including corporate tax, GST/HST, payroll, and a self-learning layer for dynamic rate and rule updates. | |
| Bricolage chikeka/bricolage An agentic system that turns free-tier cloud resources into working outcomes. It orchestrates six specialist agents to plan, acquire, and assemble free services into deployable applications. | |
| Qdrant RAG MCP Server chikhio123/rag-mcp Provides RAG search and ask capabilities over markdown and text files using Qdrant vector database, with tools for ingestion, retrieval, and source management. | |
| safari-bookmarks-mcp chikingsley/safari-bookmarks-mcp Manage Safari bookmarks through an MCP server, providing tools to list, search, add, remove, and organize bookmarks and folders. | |
| local-recall-mcp chikoku-neko/local-recall-mcp Provides fully local long-term memory for AI agents by enabling semantic search over notes and session logs using Ollama embeddings, with no external APIs or databases. | |
| snipeit-mcp chiku-wa/snipeit-mcp Read-only MCP server for Snipe-IT v7 REST API, providing search and retrieval of assets, users, models, categories, and locations without modification. | |
| cove chiku524/cove Enables AI assistants and agents to ask support questions, search knowledge articles, and list available articles from a configured support bot through MCP tools. | |
| JMComic AI MCP Server chikumar967/jmcomic-ai Enables AI agents to search, browse, favorite, download, and post-process JMComic albums and photos, retrieve comments and rankings, manage login/configuration, and access MCP knowledge resources. | |
| Universal Docs MCP Server chikumbu-kudakwashe/universal-docs-mcp-server Provides AI assistants with live, searchable documentation for any programming library, eliminating hallucinated APIs by returning current, structured API references. | |
| Raspberry Pi MCP Audio Control System chilindrinobot/raspberry-pi-mcp Enables remote control of audio playback and system volume on a Raspberry Pi via the Model Context Protocol (MCP). | |
| meetergo-mcp chill-lichen/meetergo-mcp MCP server that exposes meetergo's scheduling and CRM API as tools for AI assistants, enabling Proton Calendar-backed booking management and contact operations without Google Workspace. | |
| oh-my-cassette chill1381/oh-my-cassette A local MCP server that lets an AI coding agent turn a folder of raw clips into a finished, beat-synced montage from a plain-language brief. It handles clip analysis, shot selection, timeline planning, music matching, subtitles, transitions | |
| Crawl4AI RAG MCP Server chillbruhhh/crawl4ai-mcp Provides AI agents and coding assistants with advanced web crawling and RAG capabilities, allowing them to scrape websites and leverage that knowledge through various retrieval strategies. | |
| telegram-claude-mcp chilldude/telegram-claude-mcp This server enables Claude Code to send notifications and ask questions via Telegram, allowing user interaction during coding tasks. | |
| Zintlr MCP Server chillitray/zintlr-mcp-server Integrates LLMs with the Zintlr sales intelligence platform to search for prospects, companies, and contact information. It provides tools for profile retrieval, lead generation, and technology stack analysis via a remote MCP interface with | |
| NodeSeek MCP Server chillpoints/nodeseek-mcp An MCP server enabling LLMs to interact with the NodeSeek forum, supporting account status retrieval, daily check-in, post browsing, reading, replying, and posting. | |
| linux-ssh-mcp-server chillwind132/linux-ssh-mcp-server Remote Linux operations via SSH, exposed as an MCP server, with tools for filesystem, systemd, Docker, network, and more, using per-user AD authentication and optional sudo elevation. | |
| mssql-mcp-server chillwind132/mssql-mcp-server A Microsoft SQL Server MCP server that enables querying, inspecting, and troubleshooting SQL Server instances via ODBC with per-caller credential elicitation. | |
| win-mcp-server chillwind132/win-mcp-server A Windows MCP server for remote administration over WinRM/NTLM, enabling management of files, services, registry, events, certificates, processes, network, and more on AD-joined Windows hosts from MCP clients. | |
| promptforge chillzone2025/prompt-forge Generate deployment-ready AI agent system prompts for professionals in one click. 251 curated archetypes across 41 industries — from FX risk management to clinical documentation to OSINT intelligence. | |
| Nigerian Reference Data chimaobikanu/nigerian-reference-data-mcp Pay-per-call Nigerian phone, bank-account, NIN/BVN and state reference data for AI agents over x402 (USDC), no API key. | |
| figma-mcp chimbuezedavid/figma-mcp Enables AI-driven UI/UX design and prototyping in Figma by letting agents generate AutoLayout screens, modify canvas elements, and wire interactive prototype flows through natural language. | |
| Universal LinkedIn MCP Server chimbuezedavid/linkedin-mcp Universal LinkedIn MCP server for profile editing, rich posting (media, polls), messaging threads, network growth, and analytics with stealth browser automation and strict account guardrails. | |
| TrustLens chimdalu-ofoegbu/trustlens A pay-per-call MCP server that evaluates AI agents on the OKX.AI marketplace, providing a hiring-trust score, grade, and breakdown based on review authenticity, sales velocity, and price fairness. | |
| MCP GitHub Project Manager chimitsotakis8030/mcp-github-project-manager Enables AI agents to use GitHub Projects v2 as a persistent task backbone: registering, atomically claiming tasks, coordinating via heartbeats, submitting work for review, and enforcing token budgets. It also supports AI-powered PRD generat | |
| ga4-mcp chimpmatic/ga4-mcp An MCP server integrating Google Analytics 4, Search Console, and Indexing API, enabling AI agents to run reports, inspect URLs, manage properties, and request indexing. | |
| skillfinder-mcp chin-mae/skillfinder-mcp An MCP server that provides on-demand skill discovery for AI coding agents by querying GitHub repositories, using BM25 search to return relevant SKILL.md content. | |
| coding-memory-mcp chinacarlos/coding-memory-mcp Provides a local long-term memory layer for AI coding tools like Cursor and Claude Code, enabling cross-session, cross-tool sharing of project facts, user preferences, decisions, and workflows. | |
| figma-agent-mcp chinacarlos/figma-agent-kit Connects AI agents to Figma through a local WebSocket bridge, enabling read/write access to open Figma files, node manipulation, and AI-assisted rename/group features. | |
| op-product-design-mcp chinacarlos/op-product-design-mcp Enables AI hosts to validate, write to disk, hot-reload, preview, and export single-file HTML prototypes built to the Spark OP design spec, serving them locally at 127.0.0.1:5179 by slug. Also bundles the triggering skill, spec references, | |
| japan-healthcare-mcp chinahamu/japan-healthcare-mcp A local-first MCP server and toolkit for Japanese healthcare reference data, enabling lookup and search without bundling official datasets. | |
| Delphi Compiler MCP Server chinawsb/daofy Enables AI assistants to compile Delphi projects and single units directly through the Model Context Protocol. It features automatic compiler detection via the Windows registry and supports MSBuild with full build event integration. | |
| tldraw MCP Server chindris-mihai-alexandru/tldraw-mcp-server An MCP server that gives AI agents programmatic control over a live tldraw canvas, enabling diagram creation through natural language. | |
| mcp_for_agents chineidu/mcp_for_agents Enables building local, offline MCP servers that expose open-source package documentation to AI agents, with tools to list doc sources, search docs, and retrieve doc content over stdio. | |
| mnelo chinesewebman/mnelo Local-first, single-file, knowledge-graph memory layer for AI agents. | |
| comsol-mcp ching-chiang/comsol-mcp MCP server for visible COMSOL automation that attaches to a running COMSOL Multiphysics Server, enabling shared model state with the Desktop GUI for collaborative modeling. | |
| SQMCPaL chingenlin/sqmcpal An MCP server that enables MCP-compatible AI tools to read-only query Azure Database for PostgreSQL Flexible Server using your existing Azure CLI login, with auto-discovery, schema inspection, and arbitrary read-only SQL. No passwords or co | |
| FastMCP Style Enforcer chinggu88/flutter_mcp A server that automatically reviews code style and suggests improvements, with special focus on Flutter/Dart projects and general programming styles. | |
| demo-mcp-server chingyangtseng-houzz/demo-mcp-server Enables end-to-end testing of OAuth authorization for an MCP server, exposing scoped tools like whoami and echo over streamable HTTP. | |
| xT MCP Server chinhanxt/xt-mcp Enables AI agents such as ChatGPT, Claude, and local LLMs to operate an enterprise digital-operations platform through MCP, exposing 19 model tools and 3 app-only tools for identity, data, workflow, files, and PII-controlled operations with |
38,401–38,450 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.