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 |
|---|---|
| Trading 212 Demo Execution MCP ethan-sun01/trading-212-demo-execution-mcp_public Enables safe interaction with a Trading 212 practice/demo account through MCP, providing read-only account and market tools plus guarded order placement and management, strictly limited to the demo API. | |
| Thread Analyzer MCP Server ethan-tsai-tsai/thread-analyzer Scrape and analyze replies from any public Threads post right from your AI coding agent. | |
| qq-local ethan-wang-dev/qq-local-interface Enables agents to inspect and synchronize local macOS QQ data snapshots, with read-only access to contacts, conversations, messages, search, changes, exports, full tables/datasets, media assets, and favorites via MCP tools. | |
| voxai-mcp ethan-ys/voxai-mcp Gives your AI a live, speaker-labeled transcript of the meeting or call happening right now, plus the ability to push advice into the meeting window and speak out loud on the Mac. Requires the VoxAI macOS app — the server reads and writes t | |
| java-class-analyzer-mcp ethan0430/java-class-analyzer-mcp MCP server that scans Maven project dependencies, decompiles Java class files, and provides class structure analysis to LLMs for accurate code generation. | |
| Presales Research Agent MCP Server ethan071711/presales-research-agent Exposes search_knowledge and create_quote over Streamable HTTP with JWT validation, enabling permission-scoped knowledge retrieval and deterministic simulated quote creation while keeping pricing and approvals outside model control. | |
| 1Forge Finance MCP Server ethan2000liu/1forge-finance-apis An MCP (Multi-Agent Conversation Protocol) Server that provides an interface to the 1Forge financial APIs, allowing access to forex data and currency conversion services through natural language interactions. | |
| NASA APOD MCP Server ethan2000liu/apod Multi-Agent Conversation Protocol server for accessing NASA's Astronomy Picture of the Day (APOD) API, allowing users to retrieve space imagery and related information through natural language interactions. | |
| bambu-printer ethan2298/bambu-printer-agent-plugin Enables local Mac agents to monitor and control Bambu Lab 3D printers via MCP tools, including status checks, camera snapshots, and print job management. | |
| DataBook ethan2298/databook Enables AI assistants to manage and query SQLite databases through MCP tools, supporting CRUD operations, schema management, and saved views. | |
| Personal Semantic Search MCP ethan2298/personal-semantic-search-mcp Enables semantic search over local notes and documents using natural language queries. Supports multiple file types (Markdown, Python, HTML, JSON, CSV, text) with fast local embeddings and persistent ChromaDB vector storage. | |
| mcp-citation-checker ethanchand/mcp_citation_checker An MCP server that verifies whether a claim is actually supported by the source text at a given citation — independent of what the calling LLM asserts. | |
| PDF Inspector MCP ethancheung-gh/pdf-inspector-mcp Enables MCP clients to inspect PDF structure and extract object-level data such as characters, words, tables, images, fonts, and metadata, with JSON/CSV export and image retrieval. | |
| textura-mcp ethancheung-gh/textura-mcp Enables hosts to expose a workspace of typed items and relationships through seven MCP tools for listing, searching, creating, updating, and status-setting items, linking items, and retrieving statistics, while leaving transport and persist | |
| Binance MCP Server ethancod1ng/binance-mcp-server A Model Context Protocol server that provides Claude Code with seamless access to Binance exchange API functionality for market data retrieval, account management, and trading operations. | |
| Bybit MCP Server ethancod1ng/bybit-mcp-server A Model Context Protocol server that enables AI coding tools like Claude Code and Cursor to interact with Bybit's trading platform for market data retrieval, account management, and trading operations. | |
| RedNote MCP Server ethancod1ng/rednote-mcp-server A Model Context Protocol (MCP) server that enables AI assistants to search, retrieve, and analyze content from Xiaohongshu (Little Red Book), providing access to notes, user information, and trending topics. | |
| pdf-to-pptx ethandev/pdf-to-pptx Enables converting a direct HTTPS document link into an editable slide deck while keeping charts, images, and shapes as background visuals, with job tracking and file download. | |
| strava-mcp ethandm/strava-mcp A read-only local MCP server for querying your own Strava data from Codex, providing tools for activities, athlete profile, stats, gear, and more. | |
| tmdb-mcp ethandm/tmdb-mcp A local, read-only MCP server for discovering movies and TV series from The Movie Database (TMDB). It provides tools for search, details, trending, discovery, and related content. | |
| youtube-mcp ethandm/youtube-mcp Local YouTube MCP server for turning public video, channel, and playlist URLs into structured context, with bounded comment retrieval, timestamped captions, and owned-playlist management using your own Google Cloud credentials. | |
| tradingview-mcp ethandodds120-lang/tradingview-mcp Connects Claude Code to your locally running TradingView Desktop app via Chrome DevTools Protocol for AI-assisted chart analysis, Pine Script development, and workflow automation. | |
| ComfyUI-Agent-Bridge ethanfel/comfyui-agent-bridge Enables an external coding agent to exchange text and images with ComfyUI workflows and trigger runs via MCP tools. | |
| Anki MCP Server ethangillani/anki-mcp-server A Model Context Protocol server that allows LLMs to interact with Anki flashcard software, enabling functions like creating decks, adding notes, searching cards, and managing flashcard content through natural language. | |
| ragic-mcp ethanh9977/ragic-mcp Enables AI agents to interact with Ragic databases via MCP protocol, supporting form exploration, data CRUD, approval, and locking operations. | |
| io.github.ethanhamilthon/yenflow ethanhamilthon/yenflow Enables AI agents to orchestrate Google Flow video and image generation, including multi-scene planning, silent background generation, credit tracking, and video stitching via MCP. | |
| SAP ADT MCP Server ethanhan2014/sap-adt-mcp An MCP server that enables AI assistants to interact with SAP systems via the ABAP Development Tools (ADT) REST API. It allows users to read ABAP source code, inspect DDIC objects, and execute SQL queries directly. | |
| sap-help-mcp ethanhan2014/sap-help-mcp An MCP server for searching SAP Help Portal documentation, enabling AI assistants to search, browse, and retrieve SAP documentation programmatically. | |
| sap-s4hana-odata-mcp ethanhan2014/sap-s4hana-odata-mcp Enables querying SAP S/4HANA Business Partner data via OData V2 API, supporting filtering, sorting, pagination, and field selection. | |
| Math-MCP ethanhenrickson/math-mcp A Model Context Protocol server that provides basic mathematical and statistical functions to LLMs, enabling them to perform accurate numerical calculations through a simple API. | |
| tuya-local-mcp ethanj2k/tuya-local-mcp Enables local network control of Tuya and Smart Life smart home devices without cloud round-trips, including power, brightness, color, and raw datapoint operations. | |
| yellow-pages ethank64/yellow-pages Exposes two MCP tools (discover and execute) that enable agents to query an OpenAPI schema via natural language and execute matched API operations. | |
| ynab-mcp ethankang1/ynab-mcp A Model Context Protocol (MCP) server for interacting with YNAB (You Need A Budget). Provides tools for accessing budget data through MCP-enabled clients like Claude Desktop. | |
| tossinvest-openapi-mcp ethanklocked/tossinvest-openapi-mcp Safe-by-default MCP server for the official Toss Securities Open API, providing read-only market and account data with optional order operations protected by multiple safety gates. | |
| Gatehouse ethanl05/gatehouse Enables AI coding agents to request and perform registered deployment and login actions without exposing credentials, using local human approval and redacted verification receipts. | |
| computer-use-plus ethanout/computer-use-plus MCP server for Windows computer use, providing low-token, low-latency automation through UIA/Win32, OCR, and vision. It enables batch actions, shortcuts, isolated desktop execution, and browser control via MCP tools. | |
| MCFunction Debug Toolkit MCP Server ethanout/mcfunction-debug-toolkit Enables AI clients to validate and run Minecraft commands, read chat and tellraw messages, control player movement and GUI, and capture screenshots from within the game, aiding datapack debugging. | |
| Astro-LLM ethanpany/astro-llm An MCP server that enables agents to evaluate LLMs daily through capability benchmarks and value alignment tests, providing tools to list models, get almanac, judge dilemmas, match user values, and score models. | |
| thermal-mcp ethanpany/thermal-mcp Print beautiful HTML & Markdown on a $30 thermal receipt printer, straight from your AI agent. | |
| BrandSweets ethanplusai/brandsweets-studio A local, stdio-based MCP server that lets AI agents create and maintain a brand project through typed tools covering identity, palette, typography, voice, assets and guide chapters, then validate it and export a self-contained, client-facin | |
| google-sheets-mcp ethanratnofsky/google-sheets-mcp Enables AI agents to read, write, format, and manage Google Sheets spreadsheets using their own Google account via OAuth 2.0, including tabs, formatting, data validation, and batch updates. | |
| model-deploy ethanrise/dsh-model-deploy Enables inspecting ONNX models, probing the deployment environment, and benchmarking inference latency and FPS either locally or on remote SSH targets such as Linux workstations and Jetson devices. Benchmark results are validated against FP | |
| dsh-nx ethanrise/dsh-nx Enables safe, local Siemens NX automation through MCP, providing tools for part creation, sketching, extrusion, feature manipulation, measurement, save-as, and STEP export within a confined workspace. | |
| Remote MCP Server Template ethanrosswomack/everlight-mcp A template for deploying MCP servers on Cloudflare Workers without authentication. Enables users to create and customize their own remote MCP tools that can be accessed from Claude Desktop or AI playgrounds. | |
| Metasploit-MCP ethanroubal/metasploit-mcp Enables AI agents to interact with a local Metasploit Framework instance through the Model Context Protocol for AI-driven red teaming, exposing RPC calls, persistent consoles, native process execution, interactive terminals, and local file | |
| AI HueBot ethansk/ai-huebot-mcp Enables users to control Philips Hue lights through natural language, set moods, save favorites, and learn preferences over time. | |
| mcp-telegram-claudecode ethansky2986/mcp-telegram-claudecode Enables Claude Code to send and receive messages via Telegram for remote interaction and approval of sensitive operations. | |
| craftsman-map ethanxue666/craftsman-map Compiles codebases into a layered knowledge graph, providing an MCP server with 16 tools for AI to navigate, understand, and analyze code before making changes. | |
| discord-mcp ethdreamer/discord-mcp Enables Claude to read Discord message threads using a personal user token, so it can fetch thread content from any server you're a member of. | |
| codex-mcp-server etheaven/codex-mcp-server An open-source MCP server that connects your IDE or AI assistant to the Codex CLI, enabling non-interactive automation with codex exec, safe sandboxed edits with approvals, and large-scale code analysis via @ file references. |
48,751–48,800 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.