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 |
|---|---|
| Limitless MCP Server 199-mcp/mcp-limitless Provides advanced analysis of conversations from Limitless Pendant recordings, including intelligent meeting detection, action item extraction, natural language time queries, and comprehensive conversation analytics with smart pagination su | |
| MedGemma Vertex 199-mcp/mcp-medical-imaging MCP server that routes medical questions and images to MedGemma models hosted on Vertex AI, enabling interaction with text-only and multimodal medical AI systems. | |
| openai-gpt-image-mcp 199-mcp/mcp-openai-image An MCP server that enables image generation and editing using OpenAI's DALL-E models with support for text prompts, inpainting, and outpainting. It includes advanced features like automatic aspect ratio mapping and intelligent file manageme | |
| MCP Uber Server 199-mcp/mcp-uber An MCP server that enables AI assistants to book and manage Uber rides, including getting price estimates, requesting rides, checking ride status, and canceling rides. | |
| MCP Wait Timer Server 199-mcp/mcp-wait-timer Provides a simple 'wait' tool that introduces deliberate pauses into workflows executed by MCP clients, allowing time for asynchronous operations to complete before proceeding to the next step. | |
| Zen MCP Enhanced 199-mcp/mcp-zen An enhanced Model Context Protocol server that enables Claude to seamlessly collaborate with multiple AI models (Gemini, OpenAI, local models) for code analysis and development tasks, maintaining context across conversations. | |
| mcp101 1995parham-learning/mcp101 A sample MCP server built with FastMCP that demonstrates basic tools and a Google OAuth integration for accessing Google APIs like Calendar. | |
| chaining-mcp-server 1999azzar/chaining-mcp A unified MCP server for enterprise tool chaining, route optimization, sequential thinking, time management, monitoring, analytics, security, and compliance. | |
| Google Search MCP Server 1999azzar/google-search-mcp Provides advanced Google Custom Search functionality, web content extraction, and specialized research tools such as search analytics, multi-site search, and fact checking. Works as an MCP server compatible with any MCP client. | |
| scrcpy-mcp 1999azzar/scrcpy-mcp MCP server for Android device control via ADB and scrcpy, enabling AI agents to see and interact with Android devices. | |
| IMApy 19chris19/imapy Enables agents to use verified IMA web capabilities through 11 STDIO MCP tools, covering QR login, knowledge-base streaming Q&A, model and mode selection, web citations, continuous follow-up, task recovery, and result export. | |
| Desktop Commander MCP Server 19miha99/system-monitor-mcp A comprehensive MCP server that gives AI assistants full control over your desktop — monitor system resources, manage windows, capture screenshots, control the clipboard, launch applications, and more. | |
| Pine Assistant MCP Server 19pine-ai/pine-mcp-server A local MCP server that lets any LLM agent manage Pine AI tasks — negotiate bills, cancel subscriptions, resolve disputes, and make phone calls on your behalf. | |
| scrape-mcp 1abhishekpandey/scrape-mcp Enables web scraping and conversion of any page to clean markdown, with crawling, mapping, and multiple output formats, deployable to Cloudflare Workers for use in Claude and Codex sessions. | |
| hansatic-mcp 1aleksa/hansatic-mcp Enables AI agents to pack trucks and shipping containers by generating validated 3D load plans with metrics like LDM, linear feet, and pallet positions through the Hansatic packing API. | |
| moodle-mcp 1alexandrer/moodle-mcp Provides Claude with full access to Moodle learning management systems, enabling interaction with courses, files, assignments, grades, and calendar events. It also supports building Obsidian study vaults from course materials through automa | |
| WebSee MCP Server 1aquantum/websee-mcp-server Provides AI assistants with advanced frontend debugging capabilities through 36 specialized tools for inspecting React/Vue/Angular/Svelte applications. Uses Playwright browser automation and source map intelligence to analyze components, ne | |
| Combo Engine MCP Server 1artik1/combopizzasushimcp MCP server for calculating profitable food combos from delivery chains in Voronezh. Provides menu parsing, best combo selection, price comparison, and health checks across multiple restaurant networks. | |
| SolHunt-Solana-Wallet-Intelligence 1arxai/solhunt-recovery Real-time Solana wallet health analysis platform and top-notch dev tool. Helps people and agents to recover their SOLs from burner and old wallets super securely. Features a complete trustless recovery flow natively via MCP - https://solhun | |
| React Patterns MCP Server 1beyza/react-patterns-mcp Provides React design and rendering patterns from patterns.dev as MCP tools and resources for Claude Code. | |
| redmine-mcp 1blacksmith/redmine-mcp MCP server that provides access to the Redmine REST API, enabling issue tracking, project management, and more through natural language. | |
| mcp-jira-server 1broseidon/mcp-jira-server Provides integration with Jira's REST API, allowing AI assistants to manage Jira issues programmatically. | |
| MCP Weather Server 1broseidon/test-mcp-weather-server Provides real-time weather information and multi-day forecasts for global locations using city names, coordinates, or ZIP codes. It includes tools for current conditions, forecasting, and weather summaries designed for activity planning. | |
| liepin-workbuddy-mcp 1bruce-eng/liepin-workbuddy-mcp A local stdio MCP adapter that surfaces the official Liepin CLI to WorkBuddy, letting users search jobs, read their resume, update job expectations, and apply to positions. Write operations require explicit confirmation text, and all action | |
| MyChatArchive MCP Server 1ch1n/mychatarchive Enables semantic search across your local AI conversation history (ChatGPT, Claude, etc.) and provides tools to retrieve context, capture thoughts, and get profile summaries. | |
| agnes-mcp 1cyberlangke1/agnes_mcp 基于Agnes AI的MCP服务器，支持图像描述、图像生成和视频生成，全部通过OpenAI兼容接口。 | |
| EggTart 1cyberlangke1/eggtart MCP server for Minecraft Bedrock Edition providing 7 tools for zone management, building, scanning, and command execution via LLM. | |
| manim-web 1cyrvox/manim-mcpweb MCP server for creating math animations with manim, enabling AI-driven real-time interactive creation and browser preview. | |
| discord-sovereign-mcp 1cz1/discord-sovereign-mcp Enables full-lifecycle Discord server management from any LLM, including creation, administration, and scaffolding, with a sovereignty guard ensuring mutations only occur when the client has the highest role. | |
| arXiv MCP Server 1dark134/arxiv-mcp-server Enables AI-powered academic paper discovery, search, and analysis from arXiv with advanced features like semantic search, citation network analysis, and multi-format exports (BibTeX, RIS, JSON, CSV). Provides intelligent research assistance | |
| genesis-mcp-robotics 1douya1/genesis-mcp-robotics Enables LLM agents to control robot simulations (grasping, pouring) in the Genesis physics simulator through persistent sessions, allowing multi-turn interaction with the same scene. | |
| Context Sync MCP 1echa/context-sync-mcp Enables AI coding agents to persist structured long-term memory (gotchas, architecture, API notes) in a .context folder and sync across devices and agents via Git. | |
| KBÜ MCP 1ffatihgur/kbu-mcp Enables AI clients to search and read university web pages and PDF/Office documents, query live phone directory, food menu, academic calendar, announcements, and AKTS course plans, and return sourced answers with URLs and dates. | |
| Data Platform MCP 1franky/data-analits-mcp Bootstrap MCP server for future data exploration and querying across multiple databases, currently only provides a hello_world tool with no actual data connectivity. | |
| 1GP Publisher MCP 1gp-studio/publisher-mcp Enables Codex users to inspect and publish local Vite games to the 1GP platform with automatic build detection, per-user browser authorization, and build status tracking. | |
| databrief-ai 1hilal7/databrief-ai Enables AI-assisted CSV data quality profiling through MCP tools, offering analysis reports and quality scores while preserving privacy by processing only aggregated data. | |
| tutorloop 1hsanullah/tutorloop Enables chat assistants to insert graded coding exercises (Python, JavaScript, TypeScript, SQL) with hidden tests, and returns failed attempts to the conversation so the tutor can explain the learner's specific mistake. | |
| Narrator MCP 1j6k21/minecraftnarratormcp Captures screenshots, analyzes changes with Gemini, generates humorous narrations with sound effects, and plays them as speech via ElevenLabs, optionally integrating with a Minecraft mod for in-game events. | |
| MCP Enterprise Architecture Project 1jelly7/mcp_enterprise_architecture_project Provides a set of MCP tools (file, database, GitHub, Slack, browser, calendar, email, vector search, Python execution) with safety constraints and OpenAI integration for enterprise architecture automation. | |
| MCP RAG Assistant 1jelly7/mcp_rag_project Enables RAG (Retrieval-Augmented Generation) with tools for vector search, document access, and OpenAI integration, plus MySQL storage and file system operations via MCP. | |
| Simple MCP Server 1jelly7/simple_mcp_server_project A learning-focused MCP server demonstrating tool, resource, and prompt functionalities including greeting, arithmetic, time retrieval, file reading, dynamic profiles, and document summarization. | |
| MCP TensorBoard 1kraks/mcp-tensorboard Exposes TensorBoard experiment data through a standardized MCP API, enabling AI coding agents to query and analyze scalars, tensors, histograms, distributions, and images from ML experiment logs. | |
| PostgreSQL MCP Server 1levick3/postgresql-mcp-server A Model Context Protocol server that enables interaction with PostgreSQL databases for analyzing setups, debugging issues, managing schemas, migrating data, and monitoring performance. | |
| Inkrelay MCP 1llum1n4t1s/inkrelay-mcp Generates images from English scene descriptions using OpenAI's gpt-image-2 (with optional xAI fallback), including automatic safe retry on content rejection, monochrome border trimming, and prompt-writing guidance. | |
| proton-pass-mcp-local 1llum1n4t1s/protonpassmcp Enables MCP clients to search Proton Pass vaults, shares, items, and notes, and read specific fields using an existing pass-cli session. | |
| Retroweb MCP 1llum1n4t1s/retroweb-mcp Enables discovery of 1990s-early 2000s Japanese personal websites from web archives by replaying old discovery routes like directories and web rings, with tools for fetching archived pages and extracting links. | |
| mimo-web-search 1lurgee/mimo-web-search-mcp Wraps Xiaomi MiMo's web_search API into an MCP tool for Claude Code, enabling real-time web searches with location awareness, automatic retry, and timeout control. | |
| flecs-mcp 1mamute/flecs-mcp Enables MCP clients and AI agents to inspect a running FLECS application through its built-in REST API, including querying entities, reading components, explaining queries, and inspecting systems and performance statistics. With explicit op | |
| Power BI Desktop Local MCP Server 1mestre/desktop-ssas-mcp Enables AI assistants to discover and interact with local Power BI Desktop instances, including inspecting table/column schema and executing DAX queries. | |
| CapabilityHub MCP Server 1milkdeliver/capsift Provides deterministic search, load, and execution operations for progressively disclosing agent capabilities (skills, MCP, CLI, HTTP/API, RAG). Enables scope-bound reference access with budgets and audit. |
21,851–21,900 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.