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 |
|---|---|
| mikrotik-mcp denver6000/mikrotik-mcp Enables MCP agents to run RouterOS commands on MikroTik routers over SSH, with configurable profiles, secure authentication, and a read-only safety guard. | |
| mcp-weather-ukraine denverzp/mcp-weather-ukraine Enables getting weather forecasts for Ukraine using coordinates via the get_forecast tool. | |
| todoist-api-mcp denwakeup/todoist-api-mcp MCP server for Todoist API integration, allowing management of tasks, projects, sections, labels, and comments through natural language. | |
| ametller-origen-skill denya/ametller-origen-skill Open Claude integration for Ametller Origen's live catalog, online orders, real cart, and optional offline Gmail tickets. | |
| Glovo Claude Skill denya/glovo-skill MCP server for browsing Glovo stores, menus, products, and managing a basket via API calls without checkout or payment. | |
| Hippocampus denyanna7-design/hippocampus-memory Enables Alexa+ and other MCP clients to store memories as files and recall them via spreading activation over an association graph shaped by Hebbian learning, the spacing effect, and salience. Sleep consolidation plus graded compression tie | |
| TestRail MCP Server denys-ispaniuk/testrail-mcp Enables AI assistants to interact with TestRail test management system, supporting full CRUD operations on projects, suites, sections, test cases, runs, results, plans, and milestones. | |
| Hotline Finance FAQ MCP Server denysmilimonko/hf_faqs_mcp_server MCP server for retrieving FAQ and glossary from the hotline.finance insurance service, supporting both stdio and HTTP modes for integration with clients like Cursor, Claude Desktop, and ChatGPT. | |
| codegraph-mcp denzharkov/codegraph-mcp Provides Claude Code with a repository symbol graph via tree-sitter, enabling instant symbol lookup, file skeletons, call-site analysis, and persistent notes, reducing token usage by reading signatures instead of whole files. | |
| machine-maintenance-agent deodatta1234/machine-maintenance-mcp Enables agents to inspect machine status and sensor anomalies, search maintenance guidance, and create maintenance tickets through controlled MCP tools. | |
| Task Master deokgoo/task-manager-mcp Simplified Trello-style task management via MCP with 11 essential tools for efficient CRUD operations and a real-time web dashboard. | |
| Weather & Web Search Agent deon62/mcp Provides weather information and web search capabilities with special support for Hugging Face inference providers. Integrates seamlessly with tiny-agents framework for conversational AI interactions. | |
| Moon-Link Discord MCP Server deonetwo/moon-link-discord-mcp Enables AI clients to securely manage and automate Discord servers through natural language, covering channel and role administration, messaging, moderation, invites, and audit log inspection via 27 tools and 3 resources. | |
| Vista API MCP Server department-of-veterans-affairs/octo-vista-api-x-mcp-server-example Provides secure access to VA's VistA electronic health record system, enabling AI applications to retrieve and summarize patient medical records for clinical staff. | |
| Cloudflare Playwright MCP dependify/playwright-mcp Enables AI assistants to control a browser through Playwright running on Cloudflare Workers, allowing web automation tasks like navigation, typing, clicking, and taking screenshots through natural language. | |
| Cloudflare Playwright MCP dependify/playwright-mcp2 Enables AI assistants to control a browser through Playwright and Cloudflare Workers, allowing web automation tasks like navigation, typing, clicking, and taking screenshots through natural language commands. | |
| MCP Express Server Example depeshmandalia/mcp-1 A basic example demonstrating how to develop and run a serverless Model Context Protocol (MCP) implementation using Netlify Functions and Express. | |
| Express MCP Server depeshmandalia/mcp-1-fd3bb A basic example of a serverless Model Context Protocol (MCP) implementation using Netlify Functions, allowing developers to run MCP services without managing traditional server infrastructure. | |
| Depfender MCP Server depfenderdev/mcp Enables users to scan software packages for data exfiltration and security threats directly within their IDE across npm, PyPI, Cargo, and Maven ecosystems. This tool helps ensure the safety of project dependencies by identifying potential r | |
| CCI Black Book MCP dephekt/grow-book-mcp Enables semantic search over the CCI Black Book, a scanned grow manual, retrieving both text and visual content with cited evidence packs for AI assistants. | |
| Catalog dephrat/catalog-mcp Exposes a read-only tag index over a synced personal email archive, letting MCP-compatible agents run fast local searches, browse generated tags, check indexing health, and fetch full thread content for the most promising matches. Built for | |
| convoy deploy-forward/convoy Enables isolated bring-up of Windows Terminal windows with split panes per named thread, and supports native harness hops through the hop CLI. | |
| AfterHours Gmail MCP deploy103/afterhours-gmail-mcp-public Enables a single owner to connect an MCP client to their own Gmail account over authenticated Streamable HTTP and read status, recent inbox messages, and full message content using their own Google OAuth app and grant. | |
| Afterhours Kakao MCP deploy103/afterhours-kakao-mcp-public Enables a single owner to securely list, read, and reply in configured KakaoTalk open rooms via a self-hosted, token-authenticated Streamable HTTP MCP with send controls disabled by default. | |
| After-hours Vooy MCP deploy103/afterhours-mcp-public Enables a single owner to run a self-hosted authenticated MCP server that adds Slack reading and replying, Outlook inbox and calendar lookup, signed Slack event capture, restricted KakaoTalk Windows-agent tasks, appointment tracking, and mo | |
| AfterHours Outlook MCP deploy103/afterhours-outlook-mcp-public Enables a single owner to connect an authenticated Streamable HTTP client to read-only Microsoft Graph inbox previews and basic calendar data using their own Entra application and delegated consent, without sending, deleting, or modifying m | |
| After-hours Slack MCP deploy103/afterhours-slack-mcp-public Enables a single owner to use private Slack app credentials with a self-hosted Streamable HTTP MCP server to read allowlisted public channel messages, inspect thread context, send event-scoped replies, and notify the owner. | |
| After-hours Telegram MCP deploy103/afterhours-telegram-mcp-public Enables a single owner to run an authenticated Streamable HTTP MCP endpoint backed by their own BotFather token, with tools to check bot status, poll allowlisted updates, inspect and acknowledge pending messages, and optionally send replies | |
| browser-use MCP server deploya-labs/mcp-browser-use AI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction. | |
| Email sending MCP deploya-labs/mcp-resend An MCP server that allows Claude Desktop or Cursor to send emails directly using Resend's API, eliminating the need to copy-paste email content. | |
| Supabase MCP Server deploya-labs/mcp-supabase Enables Cursor and Windsurf to safely interact with Supabase databases by providing tools for database management, SQL query execution, and Supabase Management API access with built-in safety controls. | |
| Hermes_WorldKit_MCP deployfaith/hermes_worldkit_mcp Controls a Godot editor adapter via MCP, reporting bridge status, scene summaries, and selected nodes, with secure WebSocket authentication and scene-safe node selection. | |
| hermes-gpt deployfaith/hermes-gpt-bridge MCP sidecar for Hermes Agent exposing operator tools (cron, skills, config, workspace) with tiered read-only/operator/owner modes and dry-run by default for safe local development. | |
| NetBox Read/Write MCP Server deployment-team/netbox-mcp A Model Context Protocol server that provides safe, intelligent read/write access to NetBox instances, designed with safety-first principles for Large Language Model automation. | |
| Unimus MCP Server deployment-team/unimus-mcp A read-only Model Context Protocol server that enables interaction with Unimus network configuration management system directly via LLMs, providing access to device data, backups, and configuration analysis. | |
| MCP Server deploypilotorg/mcp-server A modular Model Control Protocol server that provides tools for GitHub repository analysis, calculations, weather, time, and command execution via HTTP or stdio. | |
| mcp-gempa-bmkg depripramana/mcp-server Enables users to retrieve the latest BMKG earthquake event and recent felt-earthquake reports, including tsunami-potential details, and supports generating calm earthquake summaries for family groups. | |
| Spotify MCP deprised/spotify-mcp Enables connecting a Spotify account to remote MCP clients to search music, manage libraries and playlists, and control playback with per-user OAuth authorization. | |
| depthy-mcp depthy-io/depthy-mcp Gives AI assistants access to real-time crypto market structure data from Depthy, including order book depth, liquidity walls, liquidation clusters, and Polymarket signals. | |
| Railway Sandbox MCP deputy-proxy/cr8or-sandbox Enables AI clients to manage and execute development commands within isolated Railway sandboxes, providing a remote shell, file read/write, and sandbox lifecycle management for running tests, builds, and repository operations. | |
| mozaia-laws-mcp dequive/mozaia-laws-mcp MCP server for real-time access to Mozambican legislation, enabling search, status checks, article retrieval, historical versions, and citation resolution via the Mozaia platform. | |
| zadig-mcp deraiven/zadig-mcp Enables management of Zadig CI/CD workflows, builds, services, environments, and webhooks through the Zadig OpenAPI. | |
| EasyPeasyMCP derberg/easy-peasy-mcp A lightweight, zero-config MCP server that makes documentation and API specifications instantly accessible to AI models using the llms.txt standard. It enables searching and retrieving full documentation, OpenAPI, and AsyncAPI specs without | |
| LightBurn MCP derchris2011/lightburn_mcp Enables AI assistants to read an open laser project through LightBurn's local REST API, explain and sanity-check cut settings, change them by natural-language sentence, apply material-library entries, and drop generated SVGs onto the worksp | |
| crypto-knowledge derdophil/crypto-knowledge Enables AI agents to perform complex crypto operations like cross-chain routing, contract decoding, portfolio management, and anti-rug security checks, returning unsigned transactions for safe signing by the agent. | |
| centralita-vpbx-mcp derechovirtual/centralita-vpbx-mcp MCP server for vpbx.me virtual PBX, enabling assistants to access telephony features like call history, recordings, live calls, click-to-call, and configuration management. | |
| claude-notebooklm derechovirtual/claude-notebooklm Enables users to create notebooks, upload documents and court rulings, query their contents, and generate audio, video, presentation, or flashcard outputs. | |
| correo-despacho-mcp derechovirtual/correo-despacho-juridico Enables Claude to read, search, organize, and optionally send email via IMAP/SMTP for a law firm, with multi-account support and safety locks. | |
| gmail-mcp derechovirtual/gmail-mcp Gives an agent (like Claude) complete control over a Gmail or Google Workspace account via IMAP/SMTP using an app password, without needing OAuth. | |
| CENDOJ Sentencias MCP Server derechovirtual/mcp-cendoj-sentencias Enables searching and downloading Spanish court rulings from the CENDOJ database, with automatic captcha resolution via Claude's vision, returning PDFs, full text, ECLI, and metadata. |
43,701–43,750 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.