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 |
|---|---|
| mt4ctl ak40u/mt4ctl An MCP server for operating headless MetaTrader 4 terminals remotely over SSH, enabling status checks, logs, screenshots, systemd control, and automated first-login. | |
| ATLAS MCP Server ak47dev-biz/atlas-career-coach-life-strategist-business-consultant-plugin An integrated advisory system that transforms Claude into a personal career coach, life strategist, and business consultant with persistent memory, accountability tracking, and multi-lens analysis. | |
| ack-mcp ak68a/ack-mcp Enables AI agents to manage DIDs, verifiable credentials, JWTs, and payment requests/receipts through ACK-ID and ACK-Pay operations via the Model Context Protocol. | |
| TalentBridge Lebanon ak8x6/talent-bridge-lebanon MCP server for the TalentBridge Lebanon career-matching platform, offering job search, job retrieval, skill gap assessment, and job index statistics. | |
| hig-mcp aka-kika/hig-mcp Provides Apple Human Interface Guidelines design tokens (colors, typography, Liquid Glass constraints, SwiftUI mappings) as structured data for AI coding agents. | |
| obsidian-codex-mcp aka-kika/kika-obsidian-mcp Local-first MCP server for working with an Obsidian vault.
No API key required | |
| the-librarian aka-kika/the-librarian Skill librarian for coding agents: describe a task and get the few matching skills from a large local skill collection, then report whether they worked. Runs locally with Ollama and SQLite. | |
| unity-super-mcp aka-kika/unity-super-mcp An MCP server providing 15 tools for Unity projects, including Unity Gaming Services LiveOps (Economy, Cloud Save, Cloud Code), build-size and bloat analysis, and store-compliance checks. | |
| Azure SQL MCP akaalholdings/azure-sql-mcp Enables Azure SQL Database performance and administration through typed execution, query benchmarking, and managed DBA operations. | |
| goalplanner-share-mcp akaddons/goalplanner-share-mcp An MCP server that generates RuneLite Goal Planner import strings from natural language goal descriptions, enabling assistants to create paste-ready share codes for Old School RuneScape goal planning. | |
| mia akadorkin/mia-assist Enables an agent to oversee and operate a fleet of Linux servers over the system ssh and Tailscale — inspecting host status, auditing configuration, tracking drift and reading history across many machines. Every mutating operation runs as a | |
| hl-read akagifreeez/hl-read A read-only MCP server for Hyperliquid that provides public market data (prices, order books, funding) and any wallet's positions, orders, and fills via MCP tools, without requiring a private key. | |
| iOS Simulator MCP Server akaich00/ios-simulator-mcp-server Enables AI agents to control iOS Simulators for UI/UX debugging, app management, and accessibility auditing via simctl, IDB, and ClaudeDebugKit. | |
| MCP Memory Tracker akaiserg/mcp-memory-tracker A Model Context Protocol (MCP) server that provides persistent memory capabilities using OpenAI's vector stores, allowing AI assistants to save and search through memories across conversations. | |
| visual-browser-agent akakaui/visual-browser-agent Enables AI coding agents to see and interact with real Chrome pages through structured DOM inspection, targeted screenshots, recordings, and human-in-the-loop approvals across major coding-agent hosts. | |
| feishu-wiki-mcp akakenle/feishu-wiki-mcp An MCP server that exposes Feishu (Lark) APIs as standardized tools, enabling knowledge base, document, spreadsheet, and IM operations through any MCP client. | |
| GraphRAG TypeScript MCP Tools akakinad/genai-mcp-build-custom-tools-typescript An MCP server that connects AI assistants to a Neo4j graph database, enabling querying of movie data through tools like graph statistics, genre-based search, and movie details, along with advanced features such as LLM sampling and completio | |
| MCP_WolframAlpha akalaric/mcp-wolframalpha MCP\_WolframAlpha | |
| RemoteDev akalavol/mcp-claude-ssh-powershell Enables Claude to securely work on remote projects via SSH or WinRM, providing a restricted set of tools (read, patch, git, tests, build, docker, logs) limited to whitelisted directories. | |
| Akamai Cloud MCP Server akamai-developers/akamai-cloud-mcp A read-only MCP server for Akamai Cloud (Linode) that lets users ask plain-language questions about their account, including inventory, pricing, GPU availability, and account limits. | |
| Brand Context MCP Server akamf/medovia-brand-mcp Provides AI coding agents with authoritative Medovia/ApoSuite brand guidelines, including colors, typography, and component specs, via tools and resources. | |
| Smart Coding MCP akane036/smart-coding-mcp Enables AI assistants to search codebases by meaning using local AI embeddings, and also provides package version lookup, indexing, cache management, workspace switching, and server status tools. | |
| Basecamp MCP Server akane10893/basecamp-mcp-server Enables MCP-capable clients to browse and manage Basecamp 3 projects and resources, including todos, messages, card tables, documents, uploads, comments, events, webhooks, and search through OAuth-authenticated API calls. | |
| LeetCode MCP Server akaneadams562/leetcode-mcp-server Enables automated access to LeetCode problems, contests, solutions, and user data across leetcode.com and leetcode.cn, with optional authentication for private features such as notes, problem lists, progress tracking, and submission analysi | |
| Roundtable AI MCP Server akanecelik/roundtable Enables a primary AI assistant to delegate tasks in parallel to specialized local CLI-based AI sub-agents, share project context, and synthesize their responses through a single MCP interface. | |
| whoop-ai-mcp akanek69581/whoop-mcp Enables users to ask natural-language questions about their WHOOP recovery, sleep, HRV, strain, and workout history through assistants such as Claude Desktop, Claude Code, Codex, and GitHub Copilot. Provides read-only access to personal bas | |
| Bitbucket MCP akanem46063/bitbucket-mcp Enables AI assistants to browse repositories, retrieve repository details, fetch and create pull requests, and page through Bitbucket Cloud or Server resources via authenticated API tools. | |
| oh-my-cassette akanemartins/oh-my-cassette Enables users to turn raw clips into finished, beat-synced montage videos through natural-language chat with an AI coding agent, handling shot selection, music matching, subtitles, transitions, picture-in-picture, and rendering. It also let | |
| jev-browser-mcp akanenunes98800/jev-browser Enables browser automation where a calling LLM states one desired outcome per step and a separate decision model chooses the element, action, value, and completion status, with Playwright carrying out the action. Exposes tools for navigatin | |
| MiMo Desktop MCP akaradje/mimo-desktop A local MCP server that lets an assistant observe and control Windows application windows, plus interact with Xiaomi MiMo AI Desktop workflows, through 22 tools for Unicode typing, smooth dragging, cross-window drops, and bounded SSE stream | |
| Weather MCP Server akaramanapp/weather-mcp-server A Model Context Protocol server that provides AI agents with tools to retrieve weather alerts and detailed forecasts for US locations using the National Weather Service API. | |
| PageVault MCP Server akarazhev/pagevault Enables AI clients to query a local SQLite archive of saved web page snapshots read-only, listing sites, searching pages, and retrieving accumulated content or specific snapshot versions. It runs locally over stdio against an existing archi | |
| mcp-snapshot-filter akarda/mcp-snapshot-filter A proxy server that intercepts and filters content-heavy responses from chrome-devtools-mcp, reducing token consumption by 40-60% for browser automation tools like Claude Code. | |
| OfficeMCP akardasz/officemcp Remote MCP server for Microsoft Graph with delegated OAuth support, enabling interaction with Microsoft 365 services like mail, calendar, OneDrive, SharePoint, Teams, and more via natural language. | |
| Secret MCP akarenin/secret-mcp Enables AI assistants to write .env files with secrets stored locally, allowing search by name/description while keeping actual secret values private and never exposed to the AI. | |
| figma-developer-docs-mcp akari2600/figma-developer-docs-mcp Provides AI assistants with structured access to complete Figma developer documentation, including Plugin, Widget, and REST APIs. It enables users to search and read over 600 documentation pages to facilitate Figma-related development tasks | |
| FogBugz MCP Server akari2600/fogbugz-mcp A Model Context Protocol server that enables Language Learning Models to interact with FogBugz, allowing operations like creating and updating issues, assigning cases, listing open cases, and searching through natural language. | |
| magika-mcp akari2600/magika-mcp Enables AI-powered file type detection using Google Magika, identifying file types from content via tools like identify_file, identify_directory, and list_supported_types. | |
| GitHub MCP Server akarnik23/mcp-github Enables access to GitHub repositories and data through the GitHub API. Supports retrieving repositories, issues, pull requests, and searching code across GitHub with authentication via personal access tokens. | |
| Hacker News MCP Server akarnik23/mcp-hackernews Enables access to Hacker News data including top stories, new stories, specific story details, and search functionality. Integrates with Poke to provide Hacker News content through natural language interactions. | |
| Spotify MCP Server akarnik23/mcp-spotify Enables interaction with Spotify's music catalog through natural language conversations. Search for tracks and artists, get recommendations, explore playlists, and browse artist discographies using the Spotify Web API. | |
| Weather MCP Server akarnik23/mcp-weather Provides real-time weather data and forecasts for any location using the OpenWeatherMap API. Supports current weather conditions, 5-day forecasts, and weather alerts with optional demo data when no API key is configured. | |
| Akash MCP Server akash-network/mcp A TypeScript server implementing the Model Context Protocol that enables AI agents to interact with the Akash Network, allowing them to deploy applications, create leases, manage deployments, and access other Akash services through typed to | |
| repo-scout akash1070/repo-scout-mcp Enables AI assistants to scout GitHub for existing open-source projects, libraries, and frameworks before building from scratch, offering tools for stack suggestions, repository searches, and detailed repo evaluation. | |
| super-agent-skill akash1070/super-agent-skill Equips AI coding agents with 62 production-grade tools across 28 modules for persistent memory, live GitHub scouting, UI/UX design, DevOps, security, performance auditing, and SEO/AEO/GEO optimization, enabling automated, development workfl | |
| vision-mcp akash143antor/vision-mcp An MCP server that analyzes images using OpenRouter's Gemini Flash model, supporting local file paths and URLs. | |
| Commerce Ops MCP Server akash5908/diligence-mcp-ops Enables AI agents to investigate and resolve e-commerce order exceptions like damages, lost shipments, refunds, and replacements through a unified interface with built-in guardrails. | |
| FastMCP Enterprise Server akashat-02-dev/fastmcp-fastapi Enables secure, high-concurrency AI integrations through MCP, providing semantic document search, SSRF-protected external context fetching, and cached user profile retrieval. | |
| helios-mcp-server akashb98/mcp-tool-server Exposes a fictional smart-home store's REST API to agents as schema-validated MCP tools, resources, and prompts, letting them search products, check inventory, place atomic orders, look up customers and orders, and open support tickets. It | |
| RAG Query MCP Server akashbakshi99/rag-using-langchain-mcp Enables querying a hybrid-retrieval RAG pipeline (dense + BM25) over ingested PDF documents, returning answers generated by Gemini. |
25,451–25,500 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.