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 |
|---|---|
| mobile-mcp-opengl antonpinchuk/mobile-mcp-opengl Enables AI coding agents to test and automate Android apps rendering UI in OpenGL/Vulkan/Metal surfaces via screenshot-based vision tools for tapping, swiping, long-pressing, and recording, without accessibility tree dependency. | |
| Tiny Cryptography MCP Server antonpk1/gibber-mcp A Model Context Protocol server built with Express.js that provides cryptographic tools including key pair generation, shared secret derivation, and message encryption/decryption. | |
| Spreadsheet MCP App antonpk1/spreadsheet-mcp-app Enables Claude to render interactive, real-time spreadsheets with streaming cell updates, custom styling, and resizable columns. This server allows users to visualize complex data sets through a dynamic grid interface directly within the mo | |
| Auralis Commander antonpme/auralis-commander A lightweight Windows-native MCP server providing a consolidated suite of 14 tools for shell execution, file operations, and interactive process management. It optimizes efficiency through batch file operations and smart process handling to | |
| auralis-google antonpme/auralis-google MCP server for integrating Claude AI with Google Workspace, enabling access to Gmail, Calendar, Drive, Docs, and Sheets through natural language. | |
| odoo-mcp antons2042/odoo-mcp Enables LLM agents to interact with Odoo 17 ERP via external API, providing tools for inventory management, sales order processing, and customer management through natural language. | |
| MCP Server Sample antonscap/mcp-server-sample An educational implementation of a Model Context Protocol server that demonstrates how to build a functional MCP server integrating with various LLM clients. | |
| finpilot antonshkelll/finpilot-mcp Enables AI assistants to analyze a local bank statement CSV through seven tools covering spending by category, top merchants, recurring subscriptions, unusual or duplicate charges, end-of-month forecasts, and transaction search, plus a mont | |
| gravityui-reference-mcp antonskiter/gravityui-reference-mcp Provides AI-optimized offline access to the Gravity UI design system, enabling natural language search and retrieval of components, hooks, utilities, and recipes. | |
| SSMCP antonsokolskyy/ssmcp Provides web search with content extraction, YouTube subtitles, and optional LLM summarization for AI assistants. | |
| d365fo-drill-engine antontjiptadi/d365fo-drill-engine MCP server for Dynamics 365 Finance & Operations certification prep, enabling interactive drills with accuracy tracking and review. | |
| Remote MCP Server (Authless) antonydp/remote-mcp-server-authless Enables deployment of a remote MCP server on Cloudflare Workers without authentication, allowing connection from AI Playground or Claude Desktop. | |
| PostgreSQL MCP antonygold59/postgresql-mcp Provides AI-driven PostgreSQL database management with secure OAuth 2.1 authentication, enabling users to administer, monitor, and query databases with support for extensions like pgvector, PostGIS, and pg_cron. | |
| sub-pi-agent antonylang/sub-pi-agent Enables a main agent to delegate tasks to reusable Pi agents with persistent sessions, question handoffs, bounded waiting, and in-run correction, while continuing other work. It supports named agents, context retention across MCP restarts, | |
| git-repo-analyzer-mcp antonywhatsup/git-repo-analyzer-mcp Enables analysis of local Git repositories via standard git commands, providing insights like line authorship, commit frequency, code churn, and co-changed files. | |
| Web Inspector MCP antonzherdev/mcp-web-inspector Enables AI assistants to inspect, debug, and test web pages using Playwright. Provides comprehensive DOM inspection, visibility debugging, layout validation, and element finding capabilities in real browser environments. | |
| rosetta-mcp antorfr/rosetta-mcp Modular MCP hub hosting multiple read-only addons behind a single OIDC authentication layer, enabling agents to use services like Google Maps and transit APIs with server-side API key management. | |
| swipe-mcp antoshia2n/swipe-mcp MCP server for managing swipe files (sample/reference data) with tools to add, search, and update entries via Claude. | |
| MCP Dockerized Server antpavlenko/mcp_dockerized A minimal, containerized MCP server that exposes a Streamable HTTP transport with API key authentication, allowing secure access to MCP endpoints. | |
| Terminal Sessions MCP antra-tess/terminal-sessions-mcp Interactive, persistent terminal sessions for AI assistants via Model Context Protocol. | |
| heimdall antreasantoniou/heimdall Enables agents to author, validate, and execute browser/API test plans with parallel drivers, assertions, and captured evidence such as screenshots and network logs. | |
| NotiCode antropov31/noticode-mcp Runs as an MCP server providing file system operations, shell execution, and system information tools, allowing Claude or any MCP client to edit files and control the machine. | |
| mcp-task-server antropovanikolitf/mcp-task-server A security-focused Model Context Protocol server for task management over stdio, backed by SQLite. It exposes tools to create, list, complete, delete, and search tasks with strict validation, parameterized SQL, confirmation for deletes, and | |
| uvp antruly/uvp Enables agents to scaffold, build, run, and verify libuvcpp-powered C++ web services end to end, driving real HTTP/1.1, HTTP/2, WebSocket, SOAP, and load requests over live sockets. Returns verification bundles that clearly separate what wa | |
| appwrite-console-mcp antsincgame/appwrite-console-mcp Provides root access to all Appwrite projects, enabling management of projects, organizations, and direct API calls to the console or any project via a single MCP tool. | |
| clockify-mcp antuking/clockify-mcp MCP server for Clockify time tracking, enabling CRUD operations on workspaces, projects, tasks, clients, tags, users, and time entries. | |
| Hermes Terminal Dashboard antunesls/matrixui-hermes-mcp MCP server that enables an AI agent to display rich Markdown content on a physical monitor connected to a headless Linux device via a Textual/Rich TUI. | |
| MCP Server AntV antvis/mcp-server-antv A Model Context Protocol server that provides AntV visualization library documentation and code examples to AI assistants, supporting G2, G6, and F2 libraries for data visualization workflows. | |
| youtube-summary-skill antwang0604/youtube-summary-skill A local MCP server that generates bilingual (English + Traditional Chinese) study-oriented HTML summaries from YouTube URLs, including key points, quiz, and timestamped transcript. | |
| PanOS MCP Server antxine/panorama-mcp Enables AI assistants to manage Palo Alto Networks firewalls and Panorama through natural language, including policy inspection, configuration changes, monitoring, and log queries via the PAN-OS XML API. | |
| Effort MCP Server antylab/effort-project Provides local, read-only recommendations for reasoning effort, retry or escalation guidance, and integration boundaries, enabling compatible desktop apps to suggest effort levels without modifying the active conversation. | |
| Confluence MCP Server anu-june/confluence-mcp-server Enables AI assistants to interact with Atlassian Confluence Cloud by providing tools to create, update, search, and delete pages. It facilitates seamless content management within Confluence spaces using Markdown and the Confluence REST API | |
| Healthcare Research MCP Server anubhab36/healthcare-research-mcp Provides a standardized interface for AI assistants to search biomedical literature and clinical trials, combining evidence from multiple sources and offering a prompt for structured research briefs. | |
| telegram-mcp anubhavchaturvedi-github/telegram-mcp Gives an AI assistant full control of a real Telegram user account over MTProto, enabling it to read chats, search history, send and manage messages, and dynamically create new tools as needed. | |
| anubhavmalhotra.com MCP server anubhavmalhotra/anubhavmalhotra.com Enables read-only access to the site's profile and README content through MCP tools and resources over Streamable HTTP. | |
| MidPay MCP Server anubhob435/midpay-mcp Enables AI models to manage escrow payments, account monitoring, and blockchain-verified transactions through the Model Context Protocol. | |
| LinkedIn MCP Server anubisalpha/linkedin-mcp A ToS-compliant Model Context Protocol server for LinkedIn that uses the official API for OAuth 2.0 authentication, profile reading, and content posting. | |
| Educhain MCP Server anudeep-codespace/educhain_mcp_server An MCP server that utilizes Google Gemini and the educhain library to generate educational content such as MCQs, flashcards, and lesson plans. It provides specialized tools and resources for building structured learning materials directly w | |
| After Effects MCP Server anugroho-av/after-effects-mcp Enables AI assistants and applications to control Adobe After Effects through the Model Context Protocol, including creating compositions, managing layers, and animating properties via keyframes and expressions. | |
| arXiv MCP Server anuj0456/arxiv-mcp-server Enables AI assistants to search, retrieve, analyze, and export academic papers from arXiv.org using the Model Context Protocol. | |
| Google Workspace MCP Server anuj2001/mcp-server Enables AI agents to send emails via Gmail and append content to Google Docs. | |
| instagram-mcp anuj754/instagram-mcp-main MCP server providing seamless integration with Instagram's Graph API for business account management, content publishing, and analytics. | |
| Google Workspace MCP Server anuj76913/mcp-server Enables AI agents to securely interact with Google Workspace services, including sending emails via Gmail and appending content to Google Docs. | |
| win-capture-mcp anujf1005/win-capture A Windows MCP server that enables AI agents to capture screenshots of open windows or the full desktop via stdio or HTTP. | |
| skill-router-mcp anujkumar8076/skill-router-mcp Routes SKILL.md libraries to any MCP client, enabling task matching and skill loading with embedding-based scoring, keyword fallback, and context-window discipline. | |
| mcp-doc-search anujmv/mcp-doc-search Enables searching and retrieving documents from a local folder to ground LLM answers in your files. | |
| MCPDataAnalytics anujpandey2/mcpdataanalytics A teaching repository that instructs non-technical users how to create Model Completion Protocol (MCP) servers for data analysis tasks, requiring only basic technical setup and understanding. | |
| github-mcp anujsingla/github-mcp A read-only MCP server that exposes GitHub user profiles, repository info, and search via tools for AI assistants like Claude. | |
| Milkbasket MCP Server anujsup/milkbasket-mcp Enables AI assistants to interact with Milkbasket for grocery shopping, including OTP authentication, product search, cart management, wallet balance checks, and order summaries through natural language. | |
| grantguard-mcp anunanuuu-wq/grantguard Enables auditing PostgreSQL role write privileges against a policy file, using read-only tools to explain, describe, and check permissions. |
29,651–29,700 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.