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 |
|---|---|
| notes-mcp apj72/notes_mcp A comprehensive system for creating and managing notes in Apple Notes on macOS. | |
| MCP Fantastical Server aplaceforallmystuff/mcp-fantastical Enables natural language calendar management through Fantastical on macOS, allowing users to create events, view schedules, search appointments, and navigate their calendar without leaving their AI conversation. | |
| MCP Homescan Server aplaceforallmystuff/mcp-homescan Enables local network discovery and security scanning to identify connected devices, manufacturers, and potential risks. It allows users to track network changes and export inventories into Markdown or Obsidian-compatible formats. | |
| mcp-local-llm aplaceforallmystuff/mcp-local-llm MCP server that lets Claude Code delegate mechanical tasks to a local LLM for summarization, classification, extraction, and drafting. | |
| mcp-tailscale aplaceforallmystuff/mcp-tailscale An MCP server for managing and monitoring Tailscale networks through natural language. It enables users to list devices, check connection status, monitor for client updates, and retrieve detailed tailnet summaries. | |
| mcp-wisdom aplaceforallmystuff/mcp-wisdom Provides philosophical thinking frameworks and tools based on Stoic, cognitive, mindfulness, and strategic traditions to assist with decision-making and perspective. It enables AI models to apply structured wisdom from 2,500 years of tested | |
| WordPress Abilities MCP Server aplaceforallmystuff/mcp-wp-abilities Dynamically discovers and exposes WordPress 6.9+ Abilities API capabilities as AI-accessible tools, enabling interaction with WordPress sites and any registered plugin abilities through natural language with automatic schema validation. | |
| Spain AI Kit aplaceforallmystuff/spain-ai-kit A collection of MCP servers that connect AI assistants to Spanish open government data, including statistics, legislation, land registry, and weather forecasts. | |
| iserv-mcp aplanatic/iserv-mcp Enables accessing IServ school platform features such as timetable, exercises, messenger, and more via natural language, without exposing credentials to agents. | |
| boxoban-mcp aplassard/boxoban-mcp Enables users to load and solve Boxoban puzzles by providing tools to get game state, list valid moves, and take actions. | |
| julia-mcp aplavin/julia-mcp Enables AI assistants to execute Julia code efficiently with persistent sessions, avoiding startup costs and maintaining state across calls. | |
| Ollama MCP Proxy apn-ra/ollama-mcp-proxy A comprehensive MCP proxy server that bridges MCP clients with Ollama local language models, providing advanced features like RAG integration, context management, caching, and production-ready security. | |
| Kontur.Elba MCP apo100l/elba-kontur-mcp Enables managing Kontur.Elba data through the official Public API, including organizations, bank accounts, counterparties, products, documents, invoices, and public links via MCP tools. | |
| mcp-conf-server apo100l/mcp-conf-server Enables users to search, read, create, update, and trash pages; manage spaces, child pages, comments, and labels; and authenticate via PAT, cookie, or browser SSO. It exposes these self-hosted Confluence Server / Data Center operations as M | |
| MCP Jira Server apo100l/mcp-jira-server Enables natural-language interaction with self-hosted Jira through the Jira REST API, supporting PAT or browser-cookie/SSO authentication. It allows viewing and managing issues, projects, comments, assignments, and statuses, as well as JQL | |
| F4 Crash Doctor apocalypse-meow/f4-crash-doctor Fallout 4 crash log diagnosis tool for MCP clients. Analyzes crash logs, load order, and game environment to explain crashes and suggest fixes. | |
| ES Archive MCP apocryphx/es-archive Persistent, searchable archive and memory for Claude and ChatGPT. Native macOS MCP server, install from the App Store, no setup. Private, local and open source. | |
| OpenAPI Contracts MCP Server apodi/openapi-contracts-mcp-server Enables AI assistants to browse, read, compare, and validate OpenAPI contracts for providers and consumers. | |
| Global MCP Server apofenic/mcp-prompt-router A modular MCP server that extends GitHub Copilot's capabilities through intelligent context compression and dynamic model routing for long-lived coding sessions. | |
| Apogee MCP apogeemcp/- Enables agents to perform on-chain intel and operations on Robinhood Chain, including search, charting, wallet tracking, analytics, and preparing pons launches signed in Phantom. | |
| mcp-notes-server-app apok9934/mcp-notes-server-app Enables Claude Desktop to add, retrieve, update, delete, and list notes persisted in a JSON file whose path is set via MCP_NOTES_FILE or --notes-file, with atomic, lock-protected saves. | |
| vmware-aria-logs apollion69/vmware-aria-logs MCP server for querying and analyzing logs from VMware Aria Operations for Logs, enabling log search, incident detection, and vROps correlation. | |
| Design Patterns MCP Server apolosan/design_patterns_mcp Provides intelligent design pattern recommendations using semantic search through a comprehensive catalog of 200+ patterns across 20 categories. Users can describe programming problems in natural language to discover appropriate design patt | |
| FastMCP Demo Server apoojary94/mcp_hackathon A production-ready MCP server that provides hackathon resources and reusable starter prompts. Built with FastMCP framework and includes comprehensive deployment options for development and production environments. | |
| SQL MCP Server apoorva183/mcp_for_sql Exposes a SQLite database to AI assistants with structured, read-safe access. Includes five tools for schema exploration, querying, and sampling data. | |
| Developer Toolbox MCP apoorva5544/mcp A production-ready MCP server providing file, system, math, and text utilities through a simple CLI client. | |
| PM Counter Monitoring MCP Server apoorvbrooklyn/networking-mcp Enables monitoring and querying of telecom performance management (PM) counters from remote SFTP locations, providing access to interface statistics, CPU/memory utilization, BGP peer data, and system metrics through a conversational interfa | |
| Telos Model Context Protocol aporialabs/telos-mcp An MCP server providing access to Telos, a philosophical AI mentor that combines rationalist thinking with stoic philosophy to offer personalized guidance and smart contract accountability on Solana. | |
| ssh-mcp aposadm/ssh-mcp Enables remote server management via SSH, including command execution, file transfer (SFTP), and interactive shell sessions, with support for multiple hosts. | |
| MCP Fast Server apossebon/mcp_server MCP server that enables web search via DuckDuckGo and readable content extraction from HTML pages using FastMCP. | |
| @graphty/babylonjs-inspector-mcp apowers313/babylonjs-inspector-mcp Enables LLMs to inspect a live BabylonJS scene through structured scene data, WebGL frame captures, screenshots, and arbitrary scene evaluation, with optional Gemini vision analysis. | |
| Proms MCP Server app-sre/proms-mcp A lean MCP server that provides LLM agents with transparent access to multiple Prometheus instances for metrics analysis and SRE operations. | |
| MarTech MCP Server appalchapa/martech-mcp-server Exposes marketing catalogs (offers, assets, campaigns, and computed metrics) to MCP clients, enabling natural language queries and AI-driven marketing analysis. | |
| github-token-mcp appare45/gh-token-server Enables secure retrieval of GitHub App installation tokens using 1Password authentication, providing temporary access tokens for GitHub API operations. | |
| mcp-bridge appare45/mcp-bridge YAML-configured MCP server that exposes host commands as tools via HTTP, enabling safe execution from containers with sandboxing. | |
| appium-mcp-auth appclawhq/appium-mcp-auth Authentication and authorization plugin for appium-mcp, adding bearer API keys, OAuth JWT, session tokens, scope-based authorization, rate limiting, and per-session ownership when running over SSE/HTTP Stream. | |
| AppControl Windows System History & Performance MCP appcontrollabs/appcontrol-mcp-go Connect AI agents like Claude, Cursor, and Gemini to historical Windows performance and privacy data gathered by the AppControl Windows app. This server enables natural language queries into CPU, GPU, and temperature history alongside syste | |
| AppDataLayer MCP Server appdatalayer/mcp An app intelligence query engine that enables analysis of over 1 billion reviews from Google Play and the Apple App Store. It provides tools for sentiment analysis, keyword rankings, competitive comparisons, and time-series forecasting acro | |
| siyuan-ai-mcp-bridge appdev/siyuan-ai-mcp-bridge Provides a local MCP stdio server that enables AI clients to read, search, create, update, and delete notes in SiYuan through its Kernel HTTP API, with configurable notebook and tool permissions. | |
| Universal MCP Server Framework appdevlpr/universal-mcp-server Enables Large Language Models to connect to various real-world applications through a modular framework with pluggable service connectors. Supports messaging platforms like WhatsApp and Telegram with secure authentication and includes a Rea | |
| @appdropper/mcp appdropper-io/mcp Enables coding agents to upload local .apk or .ipa builds and receive tester install links without leaving the editor. | |
| Google Play Store MCP Server appeeky/google-play-console-cli Enables AI agents to automate Android release workflows via the Google Play Android Publisher API, including deploying builds, managing listings, and replying to reviews. | |
| SalesSuite MCP Server appetizers-io/salessuite-mcp Enables MCP clients to read and manage CRM data through the SalesSuite API — contacts and contact persons, deals and pipelines, notes, calls, emails, forms, action button executions and webhook subscriptions — with toolset filtering, a read | |
| FreeTicket MCP Server appfreeticket/freeticket-mcp Exposes FreeTicket's B2B domain (events, sales, tickets, etc.) as tools for MCP clients like Claude Code, using the same authentication as the CLI. | |
| Claude Code Slack Channel appgambitstudio/claude-code-slack-channel MCP server that connects Claude Code to Slack, allowing two-way communication via Slack Socket Mode without tunnels. | |
| Design System MCP Server appian-design/aurora-mcp Provides access to Appian's Aurora design system documentation via GitHub, enabling LLMs to query components, layouts, and patterns. It supports both public and internal repositories with features for keyword searching and detailed componen | |
| Jokes MCP Server appieschot/mcplab An MCP server that delivers jokes on request, allowing Microsoft Copilot Studio and GitHub Copilot to serve different categories of jokes including Chuck Norris and Dad jokes through natural language queries. | |
| MCP Appium appium/appium-mcp Enables AI assistants to automate mobile app testing and development for iOS and Android through natural language interactions. Supports intelligent element identification, session management, automated test generation, and comprehensive de | |
| mcp-appium-gestures appiumtestdistribution/mcp-appium-gestures Provides resources and tools for generating Appium mobile gesture code (tap, swipe, scroll, etc.) in JavaScript and Java. | |
| mcp-webdriveragent appiumtestdistribution/mcp-webdriveragent Provides tools to build, package, and sign WebDriverAgent for iOS, enabling natural language automation of Appium WebDriverAgent preparation via MCP. |
29,901–29,950 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.