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 |
|---|---|
| WHOIS MCP Server ahooop/whois_mcp_server A Python-based server that provides tools for querying domain WHOIS information through the Chinaz API. It enables Claude and other MCP clients to retrieve domain registration details using standardized tools. | |
| json-promptor-mcp ahopo/json-promptor-mcp An MCP server that converts raw text prompts into structured JSON prompts using heuristic keyword extraction — no API keys required. | |
| mcp-0ne ahostbr/mcp-0ne A standalone MCP gateway that multiplexes multiple backend MCP servers behind a single endpoint, supporting both HTTP and stdio transports. It allows users to dynamically manage backends at runtime and organizes tools using a configurable n | |
| WooCommerce MCP Server ahoward9334/woocommerce-mcp-server Enables interaction with WordPress-based online stores through the WordPress and WooCommerce REST APIs, exposing tools to manage products, orders, customers, shipping, taxes, coupons, reports, and store settings. It also supports WordPress | |
| Domain Checker ahramadan44/remote-mcp-server-template Enables checking domain name availability using WHOIS lookups and DNS resolution. Supports both single and batch domain checking with detailed availability analysis. | |
| Ahrefs MCP Server ahrefs/ahrefs-mcp-server A Model Context Protocol server that connects Claude desktop and other compatible AI assistants to Ahrefs, allowing them to access Ahrefs functionality. | |
| Apple Deep Docs MCP ahrentlov/appledeepdoc-mcp Provides comprehensive access to Apple's development documentation ecosystem including hidden Xcode docs, Swift Evolution proposals, GitHub repositories, and WWDC session notes. Enables developers to search and retrieve advanced Apple devel | |
| ahromlabs-search ahrom-labs/ahromlabs-mcp Read-only search over Ahrom Labs' published guides on Indian ERP requirements, IBR 2026 boiler forms, interior BOQs, TallyPrime integration and AI assistants for business data. Returns passages with the URL of the page each came from; no si | |
| browser-agent ahsaanfarooq/browser-agent An MCP server that gives Claude a real, persistent Chrome browser with logged-in sessions, enabling automation of sites that block headless browsers. It supports 50+ tools, cross-session knowledge, and recipe replay for complex workflows. | |
| CustomerIQ-Agent ahsankamal22/project-04-mcp-agent Exposes a churn risk model, a support ticket classifier, and a retrieval-augmented policy Q&A pipeline as callable MCP tools. Enables any MCP-aware AI client to orchestrate all three capabilities within a single conversation. | |
| pubmed-mcp ahsanmandhar-ui/pubmed-mcp Enables auditable PubMed literature searches, abstract retrieval, open-access checks, and legal PDF downloads via NCBI E-utilities, while flagging missing fields rather than inferring them. | |
| Mental Models MCP ahsanmassgazal-cmd/mental-models-mcp Enables users to choose among seven decision-making frameworks and work through them step by step with their own situation, ending with one clear decision and a next action. It also chains multiple frameworks for larger decisions and provid | |
| Model Advisor MCP ahsanmassgazal-cmd/model-advisor-mcp Recommends the right Claude model for a task — Haiku, Sonnet, Opus or Fable — at the start of work and reviews the choice afterward to suggest a lighter or stronger option, running locally with no API calls or token cost. | |
| Lead Gen Playbook MCP ahsanmassgazal-cmd/sigmamax-leadgen-playbook-mcp Enables MCP clients to recommend and search 100 sales-agent prompts, retrieve ready-made workflows, and build copy-ready prompts across the lead-generation funnel. | |
| trading-platform-mcp-server ahsansabir143/mcp-web-app Enables Claude to monitor and execute Binance trading strategies through a bounded MCP tool interface, with risk controls and audit logging. | |
| FAST-NUCES Flex Student Portal MCP Server ahtishamdilawar/nuces-flex-mcp Connects AI assistants to the FAST-NUCES Flex Student Portal, enabling students to query their academic data including attendance, marks, transcript, and fee reports through natural language conversations. | |
| Z-Image Studio MCP Server ahuang71/z-image-studio Enables AI agents to generate images, list available models, and view generation history over stdio, SSE, and Streamable HTTP transports. | |
| Motion MCP Server ahuculak88/motion-mcp-server Enables LLMs to manage tasks, projects, workspaces, comments, custom fields, and recurring tasks, and to check schedules through Motion's API via natural-language conversation. | |
| SiLA MCP Server ahueber/sila-mcp Enables AI assistants to interact with laboratory devices via a SiLA server, allowing querying device info, listing commands, executing commands, and monitoring status. | |
| AbletonMCP ahujasid/ableton-mcp Connects Ableton Live to Claude AI through the Model Context Protocol, enabling AI-assisted music production by allowing Claude to directly interact with and control Ableton Live sessions. | |
| BlenderMCP ahujasid/mcp-for-blender Connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender for AI-assisted 3D modeling, scene manipulation, and rendering. | |
| Remote MCP Server Authless ahump20/remote-mcp-server-authless Enables deployment of a remote MCP server on Cloudflare Workers without authentication, supporting custom tools and integration with Claude Desktop and Cloudflare AI Playground. | |
| Excalidraw Architect MCP ahunt852/excalidraw-architect-mcp Enables AI coding tools to turn architecture and other structured descriptions into auto-laid-out, hand-drawn Excalidraw diagrams across 25 diagram types, including architecture, flowcharts, sequence, ER, swimlanes, timelines, Gantt, and ch | |
| Bitbucket MCP ahussein00/bitbucket-mcp Enables AI assistants to interact with Bitbucket Cloud and Server APIs for repository and pull request operations, including listing repositories, retrieving details, and creating or fetching pull requests. | |
| Feature Engineering MCP Server ahutosh173/automated-feature-engineering-mcp Exposes the automated feature engineering LangGraph agent as MCP tools, enabling dataset profiling, feature planning, and feature code execution through MCP-compatible hosts. | |
| Israeli Weather MCP ahuva-git/mcp-project MCP server that lets users obtain current Israeli city weather forecasts. It uses Playwright to browse Weather2day, extract the forecast page, and feed the cleaned data back to the LLM for natural language responses. | |
| ZimAgent ahx47/zim-agent-gui Enables offline CRUD and semantic search on Wikipedia ZIM archives via MCP tools for reading, writing, editing, deleting, and searching articles. | |
| Chrome Tab Remote ai-4-you/chrome-tab-remote MCP server that gives AI agents secure, consent-based access to a single browser tab, supporting read-only snapshots, element interaction with per-action approval, and frozen multi-step plans, all audited. | |
| jira-attachment-mcp ai-accelchamp/jira-attachment-mcp Fetches Jira attachments and returns them inline (for small images) or as local paths for larger files and other types, enabling AI models to access Jira attachments directly. | |
| hermes-tabs ai-ag2026/hermes-tabs Enables AI agents and other MCP clients to operate individual tabs in a user's real signed-in Chromium browser—reading pages, clicking, typing, scrolling, uploading files, and taking screenshots—visibly with per-site permissions and a stop | |
| ip-free-mcp ai-alexbaum/ip-mcp Enables trademark clearance and research across EU and Benelux registers, plus company, group-structure, and EU VAT lookups, all through free public sources without API keys. | |
| Ask Samin ai-answer/ask-samin Enables users to search Samin Yasar's video library and receive full-video recommendations grounded in transcript evidence with links to exact matched caption cues. | |
| ICP Rosetta MCP Server ai-api-booster/mcp-rosetta-icp Enables interaction with blockchain networks through the Rosetta API standard for Internet Computer Protocol (ICP). Supports operations like account balance queries, transaction construction and submission, block retrieval, and network stat | |
| AI-Archive MCP Server ai-archive-io/mcp-server Enables AI agents to interact with the AI-Archive platform for research paper discovery through semantic search, paper submission and management, peer review with structured scoring, and citation generation in multiple formats. | |
| shopify-mcp-server ai-assistant-kira/shopify-discord-agent Exposes Shopify Admin API as typed MCP tools for inventory, orders, revenue, and more, enabling Discord-based store management via AI agents. | |
| Avatar Studio MCP Server ai-calypse/avatar-studio Enables people and AI agents to generate personalized animated robot avatars with accessories, colors, expressions, fluid bodies, and badges, then export them as SVG, PNG, or GIF through local MCP tools. | |
| WhatsApp MCP Server ai-caseylai/whatsapp-mcp Enables seamless integration with WhatsApp through the Model Context Protocol, featuring multi-user support and Supabase cloud storage for persistent message history and media. Users can send messages, search chat records, and manage contac | |
| Utility MCP Server ai-chinmay/mcps An MCP server that provides AI-powered document processing and search capabilities, including PDF summarization, text extraction, metadata retrieval, and web search via Google Custom Search. | |
| Lumenco Catalog MCP Server ai-code-co/claude_mcp_lumenco Provides read-only access to the Lumenco product catalog, enabling retrieval of products, specifications, listings, and recommendation candidates without browsing the site. | |
| Magento MCP Server ai-coffeencode/magento-mcp Enables to interact with Magento stores through the Magento REST API. Supports product, order, customer, and category management via natural language. | |
| Business Card MCP ai-cooperation/business-card-mcp AI-native, self-hostable private business card database for ChatGPT using Remote MCP with Firebase authentication and Cloudflare storage. | |
| TapCard MCP ai-cooperation/tapcard-mcp Allows AI assistants to preview, confirm, import, search, and manage NFC/QR digital business cards through a private Cloudflare-deployed contact library. | |
| ai-cortex ai-creed/ai-cortex Provides durable project context for coding agents, including project maps, session history, and explicit memories, all stored locally. | |
| AI Debugger ai-debugger-inc/aidb Bringing the debugging we know and love as human programmers to our AI agents – debug any supported language with breakpoints, variable/state inspection, and stepping, to supercharge agents' capabilities to reason about runtime code. | |
| Stream MCP ai-engineer-devansh-singh/stream_mcp Enables deployment of MCP servers over HTTP, providing ready-to-use tools for text processing, math calculations, and social media content generation, accessible to AI assistants like GitHub Copilot and Claude. | |
| Apartment Hunter MCP Server ai-engineers-guild/apartment-hunter An MCP server for rental apartment aggregation, enabling geographic polygon search, semantic vector search, and LLM-powered analysis. Integrates with AI agents like Claude Desktop to manage apartment hunting workflows. | |
| eds-mcp-server ai-enthusiast-eds/eds-mcp-server An MCP server that supercharges AEM Edge Delivery Services development in IDEs by providing tools for scaffolding blocks, validating code, and generating configurations directly through natural language. | |
| Crawl4AI+SearXNG MCP Server ai-enthusiasts/crawl4ai-rag-mcp Provides AI agents with a comprehensive web intelligence stack including crawling, private search via SearXNG, and intelligent RAG capabilities for focused content extraction. It supports advanced features like semantic vector search and kn | |
| RobotArm MCP P340 ai-fange/robotarm-mcp-p340 Enables natural language control of ElephantRobotics MyCobot series robotic arms (especially ultraArmP340) through MCP protocol, with simulation mode and safety features. | |
| Dify MCP Server ai-fe/dify-mcp-server Integrates Dify AI API to provide code generation for Ant Design components, supporting both text and image inputs with stream processing capabilities. |
24,851–24,900 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.