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 |
|---|---|
| RepoPilot MCP Server azen-jc/repopilot Enables MCP-compatible clients to audit public GitHub repositories and receive structured launch-readiness reports with evidence-backed findings, reproducible scoring, and ready-to-paste launch copy. | |
| Recordly MCP Server azenyes/recordly-mcp-server Enables editing copies of Recordly projects by cutting approved source-time ranges, modifying or deleting existing zoom effects, and saving projects to a desktop-readable Projects directory. | |
| agent-wars azerax/agent-wars Enables autonomous agents to compete in an arena over MCP, where their available tools change based on items they equip, loot, and lose, allowing agents to fight, survive, and interact using dynamic tool lists. | |
| ue-angelscript-mcp azereki/ue-angelscript-mcp MCP server for Unreal Engine Angelscript development, providing documentation lookup, script file management, test running, and editor interaction through MCP-compatible clients like Claude Code. | |
| thimiko azerv1/thimiko Enables searching and retrieving local chat history from Codex and Claude CLI sessions via BM25 full-text search and MCP tools. | |
| LLMconcil azeur365/llmconcil Enables Claude Code to send a prompt to multiple LLMs simultaneously and get a judge model's structured comparison of their responses. This surfaces consensus, contradictions, and blind spots, letting Claude write a more informed final answ | |
| obsidian-excalidraw-universal-mcp azgem102-max/obsidian-excalidraw-universal-mcp MCP server enabling AI assistants to read and write Obsidian notes, create and edit Excalidraw drawings, and run Excalidraw scripts via natural language commands. | |
| qdrant-llamaindex-mcp-server azhang/qdrant-llamaindex-mcp-server An MCP server for querying and managing LlamaIndex documents stored in Qdrant vector databases, with automatic embedding model detection and extensive tools for search, retrieval, and collection management. | |
| xlsx-drive-mcp azhang4216/xlsx-drive-mcp An MCP server that lets AI agents read and write .xlsx files stored on Google Drive. | |
| Obenan MCP Server azhar-obenan/review-analyzer-mcp-server A simple note storage and management system that allows users to add, access, and summarize notes through a custom URI scheme. Supports creating summaries with configurable detail levels and provides real-time resource change notifications. | |
| MCP Jupyter Server azharlabs/mcp-jupyter-server Enables inspection and editing of Jupyter notebook files (.ipynb) through tools for reading, adding, updating, deleting, moving, and converting cells while preserving metadata. | |
| Taobao MCP Bridge azhi-xinxin/taobao-mcp-bridge Enables AI assistants to search Taobao products, read details, and view product images through a local relay, with limited browsing and no ordering or cart actions. | |
| OH2P Speaker MCP azhi-xinxin/xiaomi-oh2p-mcp-tutorial Enables AI clients to play custom TTS announcements and control the speaker’s native music library, including song requests, pause, and resume over Wi-Fi SSH. | |
| Safe Google Ads FastMCP Server azhy34/safe-google-ads-mcp Enables autonomous AI agents to safely inspect, optimize, and manage live search campaigns through 38 purpose-built tools covering bids, budgets, keywords, RSAs, assets, and negative keyword harvesting. Bundles two-layer Pydantic execution | |
| todo-mcp azibagirramani/mcp-todo Enables users to manage a todo list with add, list, complete, delete, and clear completed operations, persisting todos to a JSON file. | |
| Repliz MCP Server azickri/repliz-mcp Enables AI assistants to manage Repliz workspaces via natural language, including listing and replying to comments, scheduling posts, handling DMs, and browsing content and stats. | |
| 4DMap azieleliab/4dmap Enables AI clients to pin, span, join, list, and verify temporal/pattern inspection cards with fail-closed SHA-256 hashing and self-check diagnostics. | |
| Langfuse Prompt Management MCP Server azielinski994/mcp-server-langfuse Enables users to access and manage Langfuse prompts through the Model Context Protocol, including listing available prompts and retrieving/compiling specific prompts with variables for MCP clients. | |
| Azion MCP Server Template azionlearn-cloud/mcphttpeventsandnetworklists A Model Context Protocol server template deployed on Azion Edge Computing Network that provides a simple calculator tool for basic arithmetic operations. | |
| Hydra azixxxxx/hydra Enables Codex to delegate bounded engineering jobs to Claude Code CLI in isolated Git worktrees with strict security and allowance pacing. | |
| NitroStack Calculator MCP Server aziyakk974-bit/researchmate A starter template for building a calculator-focused MCP server with tools, resources, and prompts using TypeScript and Zod validation. | |
| DB MCP Demo azizdevfull/db-mcp-demo Provides read-only database access for AI agents, enabling table listing, schema inspection, and filtered row queries through MCP tools. | |
| pm4py-mcp azizketata/pm4py-mcp An MCP server that wraps PM4Py to bring research-grade process mining (event log analysis, discovery, conformance, OCEL 2.0) to Claude and other MCP agents, fully locally. | |
| DC Hub Intelligence (Claude Desktop Extension) azmartone67/dchub-desktop-extension DC Hub is the live data layer for data-center siting that agents can query and cite. Its Data Center Power Index (DCPI) scores where data centers can get grid power across 300+ markets daily. Also 330,000+ mapped power, grid, gas and fiber | |
| RAGBuddy azmirizkifar20/ragbuddy MCP server that enables coding agents to retrieve project context, semantically search indexed documentation, and read specific documents from registered repositories. | |
| PrismSec azmisyahrul/prismsec A secure, modular MCP server that wraps seven industry-standard security tools (nmap, nuclei, gobuster, subfinder, httpx, nikto, sqlmap) into thirteen MCP tools, enabling AI agents to perform port scanning, vulnerability scanning, directory | |
| postgres-mcp azmym/postgres-mcp Enables AI assistants to run SQL queries against PostgreSQL databases through the psql CLI, with support for multiple configured databases and enforced read-only guarantees. | |
| mcp-for-Azgaar aznan-triks/mcp-for-azgaar Connects MCP-compatible AI assistants to Azgaar's Fantasy Map Generator so they can view, inspect, edit, and export fantasy maps in a live local browser, including borders, states, terrain, layers, and files. It runs locally and offline aft | |
| CodeRAG azraf122312/reposage Enables natural-language Q&A over codebases via MCP, using AST-aware chunking, hybrid retrieval, reranking, and call-graph expansion to answer with file:line citations and impact analysis. | |
| Aztec MCP Server aztecprotocol/mcp-server Provides local access to Aztec documentation, examples, and source code via cloned repositories, with optional semantic search for enhanced querying. | |
| answer-check-mcp azterizm/answer-check-mcp Enables an AI agent to verify its draft answer against supplied sources sentence by sentence, flagging unsupported figures, dates, citations, and must/may wording and offering source-backed corrections. An optional judge mode can additional | |
| codesona-mcp-server azteron/codesona-mcp-server Provides team coding standards to AI assistants via the MCP protocol, with tools to fetch rules and suggest new ones. | |
| textlint MCP Server azu/textlint-mcp-example A server that enables real-time checking and automated correction suggestions for Japanese technical documents using textlint's linting capabilities. | |
| ClickUp MCP Server azukhrufy/clickup-mcp-server An MCP server providing comprehensive access to the ClickUp API, enabling AI assistants to manage docs, tasks, spaces, lists, and more. | |
| AzkiDeck-mcp-server azumachiaki/azkideck-mcp-server Enables MCP clients to remotely control a user's AzkiDeck mobile app over the internet, allowing notification delivery to watches, watch face/quick app installation, and notification icon management without requiring same-LAN connectivity. | |
| Shogi MCP Server azumausu/shogi-mcp Enables AI agents to analyze shogi (Japanese chess) positions and moves by integrating with USI protocol engines. Provides position analysis, move evaluation, and game state assessment through HTTP API bridge and MCP tools. | |
| MCP Marketing Analytics azuostech/mcpmarketing A minimal MCP server for marketing analytics data discovery and querying, supporting Google Ads integration with mock fallback and real API access. | |
| Feishu Connect azurboy/feishu-connect Enables cloud AI agents to search and read an organization's Feishu Docs and Wiki through an OAuth-protected, read-only remote MCP connection that uses the signed-in user's own permissions. It exposes four read-only tools for keyword search | |
| Azure AI Vision Face API MCP Server azure-samples/azure-ai-vision-face-api-mcp-server Enables face detection and recognition in Agentic AI workflows using Azure Face API, supporting attribute detection, image comparison, and face recognition. | |
| MCP Container TS azure-samples/mcp-container-ts A remote MCP server (Node.js/TypeScript) deployed on Azure Container Apps that provides todo list management tools with JWT authentication and role-based access control. | |
| Pizza MCP Server azure-samples/pizza-mcp-agents Enables AI agents to browse pizza menus, place orders, and track order status via the Model Context Protocol. | |
| Secure Remote MCP Server azure-samples/remote-mcp-apim-functions-python Acts as an AI Gateway for MCP servers using Azure API Management, implementing the latest MCP Authorization specification. | |
| Remote MCP Server azure-samples/remote-mcp-functions-typescript A cloud-based custom MCP server using Azure Functions that enables saving and retrieving code snippets with secure communication through keys, HTTPS, OAuth, and network isolation options. | |
| Node.js MCP Weather Server azure-samples/remote-mcp-webapp-node An MCP server that provides weather information like forecasts and alerts for US locations using the National Weather Service API. | |
| Python MCP Weather Server with OAuth 2.1 Authentication azure-samples/remote-mcp-webapp-python-auth-oauth Provides weather information from the National Weather Service API with full MCP OAuth 2.1 compliance, including weather alerts and forecasts for US locations through secure Azure AD authentication. | |
| Azure MCP Server azure/azure-mcp The Azure MCP Server, bringing the power of Azure to your agents. | |
| App Service Builder HTTP MCP server azureappservice/app-service-builder-mcp-server Enables authenticated HTTP MCP clients to call a bounded, read-only tool that counts Unicode code points in supplied text without accessing files, networks, or application state. | |
| plant-mcp azureiraraavis-png/plant-mcp MCP server for managing houseplants by recording waterings and observations, providing care reminders and diagnosis through natural language. | |
| rpgvxace-mcp azureknight63/rpgvxace-mcp Enables AI assistants to read and edit RPG Maker VX Ace and VX project data files directly, including databases, maps, events, scripts, and validation, without requiring Ruby. | |
| cocos-mcp-pro azusasubaru/cocos-mcp-pro Enables AI clients to directly control the Cocos Creator 3.8+ editor, including scene and node manipulation, UI building, script attachment, validation, preview runtime logs, and screenshots. |
32,351–32,400 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.