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 |
|---|---|
| KubeWhisper abdulhusainahk/kubewhisper An AI-DevOps MCP server that gives LLMs read-only-by-default access to Kubernetes clusters, Prometheus metrics, and GitHub Actions, enabling natural language queries about infrastructure status and safe write operations with previews. | |
| gpower-mcp abdulkadirelaldi/gpower-rea Enables MCP clients and AI agents to compute sample sizes and statistical power for the G*Power t-test family through six tools — listing and describing tests, running power analyses, computing effect sizes, generating power curves, and rep | |
| Knowledge MCP abdulkadirkilicc/knowledge-mcp Enables saving and searching local notes, with tools to list notes and search backup files. | |
| Aza MCP abdulkereem/aza-mcp Enables AI assistants to buy airtime and data, check wallet balance, list data plans, and view transactions for Nigerian mobile networks via an Azabill account. | |
| drf-mcp-docs abdulkhalek-1/drf-mcp-docs Exposes Django REST Framework API documentation via MCP for AI coding agents to read, understand, and write frontend integration code. | |
| gander abdulkhaliqfarah/gander Enables AI agents to fetch and extract clean, readable content from web pages, and search within pages for specific queries, without needing a full browser. | |
| MCP Chat abdullah-1121/mcp-2 A command-line interface application that enables interaction with LLMs through document retrieval, command-based prompts, and extensible tool integrations using the Model Control Protocol architecture. | |
| Invoice Vision MCP abdullah-alroumi/invoice-vision-mcp Enables MCP clients such as Claude Desktop, Cursor, or a LangGraph agent to turn scanned or photographed invoices into structured data using OpenCV preprocessing and Tesseract OCR, then validate them against Saudi VAT rules and store them i | |
| quickmemo-mcp abdullah-zafarr/quickmemo-mcp A minimalist and elegant Model Context Protocol (MCP) server for fast context memo capture, keyword search, dynamic resource digests, and AI prompt workflows. | |
| Excalidraw MCP Server abdullah007bajwa/mcp_excalidraw A Model Context Protocol server that enables LLMs to create, modify and manipulate Excalidraw diagrams through a structured API, supporting element creation, styling, organization, and scene management. | |
| gennemfoert abdullah13793-commits/gennemfoert Enables MCP clients to check penetration seals against tested ETA rows, search the ETA database, inspect project penetrations, and export register, BCF, IFC, and assessment documents with citations. | |
| indeklima-twin abdullah13793-commits/indeklima-twin Enables MCP clients such as Claude, Copilot and IDE agents to interrogate a building's digital twin in plain language through seven tools covering building overview, room lists, per-room design promises, diagnosed findings, room time series | |
| MCP Gateway abdullah1854/mcpgateway A universal gateway that aggregates multiple MCP servers into a single interface while providing advanced token optimization, result filtering, and automated summarization. It enables efficient management of large tool catalogs and reduces | |
| claude-swarm-mcp abdullah4ai/claude-swarm-mcp Orchestrates multiple Claude Code instances into a collaborative swarm for real-time task delegation, message exchange, and code snippet sharing. It features peer discovery, status tracking, and a centralized web dashboard to monitor coordi | |
| mcp-image abdullah71666/mcp-image Enables generating and editing images from MCP-compatible clients with automatic prompt optimization and quality presets, supporting Gemini, OpenAI, and BytePlus Seedream. | |
| SQLite-MCP abdullahasifbutt/sqlite-mcp .. | |
| MIHAD abdullahbalabel/mihad Enables coding agents to build and query a verified project memory through the MCP protocol, so skills, facts, and user preferences are captured as experience and adopted only after passing independent checks. It also briefs agents at each | |
| Infinite Backlog MCP Server abdullahhasan42/infinitebacklog-mcp Enables AI agents to drive a real Chromium session against Infinite Backlog — which lacks a public write API — to search the game catalog, manage ratings, reviews, extra platform copies, progress, acquisition details, DLC and other nested e | |
| nextcloud-mcp-server abdullahmashuk/nextcloud-mcp-server Enables AI agents to perform file operations and sharing management on NextCloud servers via the Model Context Protocol. | |
| YouTrack MCP Server abdullahtas0/youtrack-mcp-server A comprehensive Model Context Protocol server that provides AI agents with 44 tools to manage JetBrains YouTrack issues, sprints, and projects via the REST API. It supports full YouTrack query language and works with both Cloud and Server i | |
| CareLoop abdulmannaan502/careloop Enables older adults to manage their medicines by voice — adding prescriptions, hearing what is due, logging doses and symptoms, and getting refill and adherence reports — with built-in double-dose and emergency safeguards. It also keeps di | |
| memory-manager-mcp abdulqaderahmed/memory-manager-mcp A local-first persistent memory server for AI coding agents, enabling project context to be shared across different MCP clients. It stores curated memories, task states, decisions, and handoffs as plain files under ~/.agent-memory. | |
| skills-manager-mcp abdulqaderahmed/skills-manager-mcp Acts as a personal AI development environment manager, enabling workspace bootstrapping, headless skill and bundle installation, global caching, and health diagnostics. | |
| AgentZero abdulrahman-alfeqy/agentzero MCP server for real-time credential leak detection and remediation in Slack, using AI-powered semantic analysis via Google Gemini. | |
| TFS MCP Server abdulrahman-nabil99/azure-devops-tfs-mcp-server Bridges Claude Code with an on-premise Azure DevOps Server / TFS collection, enabling work item and Git operations via PAT authentication. | |
| qenex-pathfinder abdulrahman305/qenex-pathfinder Provides security scanning tools for Claude Code, enabling real-time vulnerability detection, code analysis, and rule explanations for codebases. | |
| hadith-mcp abdulrahman84/hadith-mcp An MCP server for retrieving hadith text and metadata from auditable sources, providing exact references, Arabic text, English translations, and source-attributed grading. | |
| repository-inspector abdulrahmanzrein/ai-repo-inspector MCP server that inspects Git repository changes, runs optional validation commands, and generates Markdown reports. Exposes a review_repository tool for AI clients to analyze repositories. | |
| gdocs-comments-mcp abdulreh4874/modern-software-dev-assignments Enables AI agents to add precise, range-anchored comments to Google Docs by bridging the Model Context Protocol with browser automation. | |
| MCP order tools abdulrehman-net/mcp-order-tools Enables AI assistants to check order status and prepare versioned address change proposals that require application-owned approval. | |
| Shopify Content Engine MCP Server abdulrehman0004/shopify-ai-content-engine Enables agents to validate product content drafts and trigger the Shopify AI content engine workflow to generate complete marketing kits including SEO, ads, blog posts, and images. | |
| AR LABS Admin MCP Server abdulrehmanfatehali1-ui/ar-labs-mcp-server Full-access MCP server for managing AR LABS (Viral AI Prompts & Guides), enabling post creation, editing, deletion, image uploads, push notifications, comment moderation, and site stats via AI assistants. | |
| Google Flow Online MCP Server abdulrehmanfatehali1-ui/google-flow-mcp-server Enables generating images, videos, characters, and scenes through Google Flow. Supports SSE and Vercel deployment for integration with Gemini Spark and other IDEs. | |
| LinkedIn MCP Server abdulrehmanzahid160/linkedin_mcp A production-ready MCP server for interacting with the LinkedIn API, enabling profile lookup, post creation and deletion, image posting, and organization page management through a secure tool-based interface. | |
| mcp-stateless-recon abdulsalam-create/mcp-stateless-recon Provides safe network reconnaissance through DNS resolution, TLS inspection, HTTP security header grading, and bounded port scanning over the stateless MCP protocol. | |
| Multi-agent MCP Network abdulsammad-lgtm/--multi-agent-mcp---network---ceo---cto---designer---sale---marketing---qa-agent MCP server exposing specialized AI agents (CEO, CTO, Designer, Sales, Marketing, QA) that collaborate through an intelligent orchestrator for business strategy, technology, design, sales, marketing, and quality tasks. | |
| Instagram MCP Server abdulsammad-lgtm/instamgram_mcp A production-ready MCP server for interacting with Instagram/Meta APIs, enabling AI agents to manage content, analyze performance, research competitors, and handle publishing workflows. | |
| LinkedIn Automation MCP Server abdulsammad-lgtm/linkedin-automation-mcp Enables AI assistants to manage LinkedIn workflows through a comprehensive set of tools for content generation, profile optimization, lead management, message outreach, engagement, analytics, scheduling, and industry research. | |
| postgres-mcp-server abdulsammad-lgtm/postgres-mcp-server Enables AI assistants to securely interact with PostgreSQL databases through a standardized MCP interface, supporting SQL queries, schema inspection, and database management. | |
| WordPress MCP Server abdulsammad-lgtm/wordpress-mcp- Enables AI agents to interact with WordPress websites through structured tools, supporting posts, pages, media, users, categories, tags, plugins, themes, menus, and WooCommerce with secure authentication. | |
| coolify-mcp-server abdulwadudh/coolify-mcp-server Enables LLMs to manage a self-hosted Coolify instance, including applications, databases, services, servers, projects, deployments, environment variables, tags, teams, private keys, and S3 backup storages via the Coolify REST API. | |
| Cross-Claude MCP abdulwaqas17/cross-claude-mcp Enables AI assistants to communicate with each other through a shared message bus, supporting MCP and REST transports for cross-model collaboration. | |
| youtube-content abdulwithai/youtube-mcp Enables AI-powered YouTube content management using Claude Code to orchestrate research, scripting, and scheduling via Google Sheets, Docs, and Drive. | |
| mycop abdumajidrashidov/mycop Agentic security scanning in Claude Code, Cursor, Windsurf | |
| mcp-sqlite-chat abdunnasir/mcp-sqlite-chat Enables querying and managing a SQLite database using natural language, with an MCP server and Groq LLM. | |
| mcpcraft abdunur-dev/mcpcraft A lightweight SDK for building Model Context Protocol (MCP) servers with zero-config setup, automatic TypeScript type inference, and Zod runtime validation. | |
| ai-developer-assistant-mcp abdur-rahman-palash/ai-developer-assistant-mcp Access a 24/7 AI senior developer with 26 specialized tools for the full software development lifecycle. Use tools like explain_code, debug_code, and refactor_code to analyze, debug, and optimize your codebase instantly. Deploy github_fix_i | |
| trend-mcp abdur-rahman-palash/trend-mcp Enables multi-agent trend analysis for digital marketing, web design, and graphics design, routing requests through specialized agents to produce actionable recommendations and implementation plans. | |
| MCP Terminal & Git Server abdurraahimm/mcp-git-terminal-server Enables execution of terminal commands, git operations, and automated setup of React, Vue, and Next.js projects with VSCode integration. | |
| mcp-server-ai-bot abdurxcode/mcp-server-ai-bot An MCP server integrating Google Gemini LLM for intelligent customer service, providing chat, analytics, and tools for customer data interaction. |
22,951–23,000 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.