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 |
|---|---|
| FlexSim MCP Server fateedit/flexsim-mcp Enables AI clients to control simulation models through a WebServer interface by creating and connecting objects, reading and writing model tree nodes, controlling runs, and hot-deploying custom handlers. | |
| guanling fateliang/guanling A task-management MCP server that enforces strict gates on task states, WIP limits, and closing reasons, refusing operations that would leave the list ambiguous or rotting. | |
| Odoo 17 Project Management MCP fatemeh-mohseni-ai/odoo17-project_management-mcp Enables AI agents to securely plan and manage projects, tasks, stages, planning, subtasks, milestones, tags, chatter comments, statuses, and timesheets in an Odoo 17 Project application via XML-RPC, with project-scoped access control. | |
| n8n-mcp fatemehmollaeimdepended-cloud/mcp A Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. | |
| mcp-pagure fatherlinux/mcp-pagure Enables AI assistants to manage issues, pull requests, and projects on Pagure instances (pagure.io and self-hosted). | |
| mcp-pcloud fatherlinux/mcp-pcloud A Model Context Protocol (MCP) server for pCloud cloud storage. Enables AI assistants like Claude to interact with your pCloud - listing files, creating folders, searching, sharing, and more. | |
| fonio MCP (community) fathyshalaby/fonio-mcp-community Enables AI assistants to connect to fonio.ai's public API for help-center search, API reference lookups, and verified outbound calling after user confirmation. | |
| Keyset MCP fatih-developer/keyset Enables compatible coding agents to inspect a Next.js project, plan and set up Google or GitHub OAuth providers, import credentials, and verify the resulting redirect through typed tools instead of unrestricted shell commands. It keeps secr | |
| webx-mcp fatih0234/web-searxng Local on-demand web search and page reading for coding agents via SearXNG, with SSRF-protected fetching and Markdown extraction. | |
| ulvane-mcp fatihaura/ulvane-mcp Provides onchain intelligence tools for Base, including token risk checks, wallet PnL, and leaderboard data, with paid calls settled per-request in USDC via x402. | |
| agentic-vision fatihberkanteren/agentic-vision-server Enables LLMs to autonomously analyze camera images for occupational safety violations, generate risk reports per ISG regulations, and log violations to a database. | |
| FatihAI MCP Server fatihdagustu20-hub/fatihai-mcp-server A free MCP server providing 13 tools for email verification, domain intelligence, and website analysis with no API keys required. | |
| IMAP MCP Server fatima19101/imap-mcp-server Enables AI assistants to search, read, send, reply to, forward, organize, and bulk-delete email across multiple IMAP/SMTP accounts from a single pooled connection. Supports encrypted AES-256 credential storage, folder and unread-count manag | |
| Niblet fatima90887/niblet-skill-mcp Enables coding agents building UI to ground their work in real product screens, returning one to three reference screenshots for an unresolved layout, state, or interaction question, plus licensed fonts and icons and the recorded colors, ty | |
| LunchMoney MCP Server fatimaioannidis564/lunchmoney-mcp Enables AI assistants and other MCP clients to interact with LunchMoney data for automated financial insights, transaction management, budgeting, and more. Provides comprehensive tools for categories, tags, transactions, recurring items, bu | |
| AI-CV-Builder-MCP fatimaiqbal34/ai-cv-builder-mcp MCP server for AI-powered CV building, offering tools to create professional CVs, improve sections, match skills to jobs, and recommend skills. | |
| medical-mcp fatimas7789/medical-mcp Enables AI tools to locally query authoritative medical sources like FDA, WHO, PubMed, RxNorm, and related APIs for drug information, health statistics, clinical guidelines, trials, and medical literature without API keys. | |
| engram fatinnihal532-hub/engram Enables MCP clients such as Claude Code to give LLM agents long-term memory by exposing remember, recall and forget tools over stdio, backed by a hybrid BM25 and vector store that reinforces frequently used memories. | |
| Vibe-Coder-MCP fatma03281/vibe-coder-mcp Enables AI assistants to perform software-development tasks such as deep research, codebase mapping, context curation, requirements and user-story generation, full-stack starter project scaffolding, and multi-step workflow execution. | |
| SerpApi MCP Server fatmab3964/serpapi-mcp Enables AI assistants to run real-time searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and other engines, returning results such as answer boxes, news, images, shopping, weather and stock data. Responses are automatically det | |
| Image Context Runtime fatmak93/codex-image-context-runtime Enables Codex to run image generation and inspection as durable local jobs while returning only bounded text handoffs, hashes, relative references, and Job IDs instead of media bytes. | |
| AgentQL MCP Server fatmal5473/agentql-mcp Enables users to extract structured data from a specified URL by providing a natural-language prompt that describes the desired fields and data. | |
| zotero-mcp fatmao9170/zotero-mcp Enables AI assistants to search a Zotero library, retrieve complete item metadata, and access full text from stored PDFs through the Model Context Protocol. | |
| Claude Telegram Supercharged fatmav070/claude-telegram-supercharged Enables users to run and control Claude Code from Telegram with voice-note transcription and replies, persistent memory across restarts, scheduled reminders, calendar access, and live progress for every tool call via a self-healing daemon. | |
| KDP Studio MCP fatoh2/kdp-mcp Enables reading KDP paperback drafts and making a single guarded cover-finish change through a user-authorized, already signed-in Chrome session while keeping credentials and tokens in the browser. | |
| JalinWP fatomate/jalinwp An MCP gateway that enables AI clients to securely connect to WordPress and WooCommerce sites via OAuth, retrieve permitted content and data, and apply changes under configurable approval modes. | |
| Homelab MCP Server faton5/homelab-mcp-server Extensible MCP server for managing a homelab from Claude AI, enabling control of VMs, snapshots, services, and files via natural language. | |
| dimension-mcp fatoomdes-lang/dimension-mcp An MCP server that lets AI agents drive Adobe Dimension to build product mockups and 3D scenes: adding models, setting materials, colors, decals and logos, matching background photos, framing cameras, rendering, and saving documents. It rea | |
| mcp-sqlserv fattan-malva/mcp-sqlserver Enables AI agents to safely read SQL Server databases via MCP with structured queries, default-deny table permissions, OAuth authentication, and full audit logging. | |
| CHS-DRG MCP Server fattank/chs-drg-mcp Enables AI agents and compatible MCP clients to submit inpatient medical-record front-page codes and receive deterministic MDC/ADRG/DRG grouping for CHS-DRG 2.0 and 3.0, including severity, status, and trace. Also supports diagnostic/proced | |
| Apple Notes MCP fattoliu/apple-notes-mcp Enables AI assistants to save well-organized technical articles to Apple Notes and local Markdown files simultaneously. | |
| x-api-mcp fatwang2/x-api-mcp Enables multi-account posting, replying, threading, deletes and image/GIF/video uploads through the official X API v2, plus likes, reposts, bookmarks, follows, timelines, search, DMs, Lists and trends. It runs locally over stdio so OAuth to | |
| Super Windows CLI MCP Server faucet94/super-win-cli-mcp-server A command-line interface server that provides unrestricted system access to Windows environments with SYSTEM-level privileges, allowing complete control over files, processes, and configuration settings. | |
| ireland-stats faulknco/archaic-stats-mcp Enables read-only access to Ireland's CSO PxStat statistics, including table search, catalog browsing, metadata retrieval, and filtered data queries with cell limits. | |
| Sentry MCP Server faurealexis/sentry-mcp-server A TypeScript server that allows AI agents to access, retrieve, and analyze Sentry error data through the Modern Context Protocol. | |
| ChatGPT MCP Server Template faust-donf/chatgpt-mcp-server-template A boilerplate for building local Node.js MCP servers that integrate with ChatGPT Web UI, featuring mock OAuth and secure tunneling for instant connection. | |
| Fusion360 MCP Server faust-machines/fusion360-mcp-server Connects AI coding agents to Autodesk Fusion 360 for CAD automation, enabling natural language control over sketching, 3D modeling, and CAM operations. It uses a Python-based bridge and a custom add-in to execute over 80 tools ranging from | |
| keycloak-mcp faust-systems/keycloak-mcp An MCP server that lets an AI assistant inspect and modify Keycloak realm, client, and protocol-mapper configuration across multiple Keycloak hosts. | |
| Hunch faustasri/hunch MCP server that exposes Kalshi prediction markets as tools for AI agents, enabling conversational trading with safety features like demo mode, preview-before-place, and hard caps. | |
| tokopedia-mcp fauzanmhr/tokopedia-mcp MCP server for searching Tokopedia products, retrieving product details and reviews, designed for use from LLM clients like Claude Desktop. | |
| blur-studio fauzulkc/blur-studio MCP server for coordinate-based selective photo blurring, letting AI agents blur faces, plates, or regions with ellipses, rectangles, and VIP exclusion boxes. Exposes tools to scan folders, manage configs, apply blur, and export Python snip | |
| Sociona MCP Server fav-devs/sociona-mcp-server Enables AI assistants to publish, schedule, and manage social media posts across X (Twitter), Instagram, and Threads through the Sociona API. Supports immediate posting, scheduling, analytics, and account management with natural language co | |
| mcp-feedback-enhanced favtony/mcp-feedback-enhanced An MCP server that establishes feedback-oriented development workflows with a Web UI and desktop app, allowing users to provide interactive feedback to AI models through prompts, images, and session tracking. | |
| shadcn-mcp-server favurr/shadcn-mcp-server Enables AI agents to dynamically install shadcn UI components into a mounted project workspace. | |
| baozhibao-mcp-server fawaikuangtuzhangfei/baozhibao-mcp-server MCP server for managing personal items with expiration dates, enabling AI agents to add, query, and scan barcode items via API Key authentication. | |
| MCP AI Chat Server fawazbayureksa/mcp-server A Laravel-based AI-powered chat interface for business management operations, enabling users to execute tasks like creating customers and updating task statuses through natural language conversations. | |
| Excalidraw-MCP fawninmyheart/excalidraw-mcp Enables MCP clients to inspect and collaboratively edit a local Excalidraw canvas through stdio tools for incremental element updates, explicit scene replacement, SVG export, PNG screenshots, and connection/status checks. | |
| UltraCode faxenoff/ultracode MCP server for AI coding agents that builds a complete code structure graph and semantic vector index, enabling fast querying of code entities, relationships, and impact analysis. | |
| codebugs faxik/codebugs Persistent code finding, requirements, and release tracker for AI assistants. Enables durable memory for code review findings, requirements, dependency blockers, parallel-agent coordination, and release milestones with minimal token overhea | |
| notebooklm-mcp-2026 faxtom/notebooklm-mcp MCP server for querying Google NotebookLM notebooks, enabling AI assistants to list notebooks, read sources, and ask questions about them. |
49,801–49,850 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.