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 |
|---|---|
| Device MCP Server akshitsinha/mcp-device-server A Model Context Protocol (MCP) server for seamless integration with peripheral devices connected to your computer. Control, monitor, and manage hardware devices through a unified API. | |
| Canvas Academic Assistant akshsgaur/cmucanvasmcpserver Connects Claude to Canvas LMS, enabling students to query their coursework, assignments, grades, deadlines, announcements, and calendar events through natural conversation instead of navigating the Canvas interface. | |
| Ghostkeep akshu24tech/ghostkeep Enables AI agents to store, search, and resolve shared memories with full provenance, conflict detection, and an audit trail across MCP-compatible clients. | |
| vSphere MCP Server akshyaganesh/vmware-mcp Enables AI agents to manage VMware vSphere virtual infrastructure through comprehensive operations including VM power control, snapshot management, resource monitoring, performance analytics, and bulk operations with built-in safety confirm | |
| Magg aksoy19/magg A meta-MCP server that aggregates and proxies other MCP servers, letting LLMs discover, add, configure, and toggle backend servers at runtime and use their aggregated tools under unified prefixes. It persists configurations across sessions | |
| Canvas MCP Server aksoy958/mcp-canvas-lms Enables interaction with Canvas LMS through its REST API, allowing users to manage courses, assignments, submissions, grades, modules, discussions, enrollments, users, and account-level reports. Supports student, instructor, and account adm | |
| cavalry-mcp akspro9866-art/cavalry-mcp Connects any MCP client to Cavalry animation software, enabling creation of layers, attribute editing, keyframe animation with Magic Easing, PNG frame rendering, and scene save/open. Every tool returns real data read back from the running s | |
| sokrates aktapokus/sokrates-mcp Enables users to clarify vague goals through Socratic questioning and generate structured technical specifications, using a curated knowledge base and session state without external LLM APIs. | |
| superpose-mcp aktasbatuhan/superpose Enables coding agents to run multiple approaches or tasks in parallel on isolated Daytona sandboxes, returning tested diffs and benchmark rankings so the best outcome can be applied. | |
| snapdec aktonay/snapdec Gives any coding agent a shared local decision layer for classifying, checking, scoring, and ranking items with calibrated probabilities, plus deterministic project fact discovery, all through one install. Every answer is advisory and marke | |
| mcp-srapper aktraiser/mcp-srapper Enables read-only, leakage-safe access to curated market episodes with point-in-time market state and forward outcomes, including searching episodes, retrieving details, and finding past analogs with outcome distributions. | |
| Saiten MCP Server aktsmm/fy26_techconnect_saiten Automates the evaluation of GitHub hackathon submissions by providing tools to collect issue data, apply scoring rubrics, and generate ranking reports. It enables a multi-agent system to manage scoring consistency, statistical outlier detec | |
| MemoSaver akufikri/memosaver Local-first MCP server that persists AI coding agent memory and session context, enabling seamless resume across sessions with searchable memories and checkpoints. | |
| BNB Chain MCP Server akumachan-v/bnbchain-mcp-jp-setup A comprehensive Model Context Protocol server that enables AI agents to interact with BNB Chain, opBNB, and other EVM networks through natural language. It provides tools for DeFi trading, DEX swaps, smart contract deployment, token operati | |
| MarketIntel MCP Server akumar1903/ai-powered-market-research-mcp-server Enables AI assistants to perform real-time market research including competitor analysis, pricing intelligence, and company overviews via live web search through Tavily API. | |
| WordPress Content MCP akungapaul/wp-content-mcp Enables management of WordPress posts and pages including creating, updating, deleting, duplicating, scheduling, and bulk editing content through the WordPress REST API. | |
| employee-plus akunimal/employee-plus Enables Alexa+ users to manage home-care services, compare options, schedule or change visits, and keep records of completed work. | |
| cc-mvp akunone/cc-mcp A Cocos Creator 3.8 editor extension that exposes scene, node, component, prefab, preview, build, asset, and debug operations as MCP tools for AI clients like Codex and Claude Code. | |
| Ultimate Excel MCP Server akuntumbabanget-sketch/mcpexcel Enables AI agents to read, write, format, and execute VBA macros in Microsoft Excel in real-time through the Model Context Protocol, connecting directly to an open Excel window via COM integration. | |
| JSON MCP Server akuratipullaiah/json-mcp-server-main Enables LLMs to query and manipulate JSON data from URLs using JSONPath expressions with array, string, numeric, date, and aggregation operations via standardized tools. | |
| Dev Tool Config Sync MCP Server akurinnoy/config-sync-mcp Syncs and manages configurations for dev tools like Claude Code and Gemini CLI across workspaces with snapshot history and rollback capabilities. | |
| bugsnap-mcp akusaradigital/bugsnap-mcp Enables AI coding agents to inspect annotated screenshots, user action steps, console errors, and failed network requests from bug reports, with tools, resources, and prompts for diagnosis and triage. | |
| fastroute akushonkamen/fastroute FastRoute is an MCP server that recommends relevant skills from locally installed skills when an agent receives a new task. It provides tools to retrieve top-N skill recommendations and incrementally rebuild the skill index. | |
| knowyoubetter akushonkamen/knowyoubetter MCP server that asks users clarifying questions when uncertain, remembers their choices using local embeddings, and automatically answers similar future queries based on learned preferences. | |
| Google Tasks MCP Server akutishevsky/google-tasks-mcp A Model Context Protocol (MCP) server that brings your Google Tasks into Claude and other MCP-compatible clients, enabling task and task list management through natural conversation. | |
| astrology-mcp akuttruff/astrology-mcp MCP server for astrological calculations including natal charts, planetary positions, aspects, transits, and progressions using Swiss Ephemeris. | |
| minimal-mcp-web-search akuttruff/minimal-mcp-web-search Provides local LLMs with web search and page fetching capabilities via MCP, with a focus on OWASP security best practices. | |
| Sub-Agents MCP Server akwon509/sub-agents-mcp Lets any MCP-compatible client run reusable, task-specific coding agents defined in Markdown files, executing them through a chosen coding CLI backend and returning the results to the same conversation. Supports shared backend/model configu | |
| MariaDB MCP Server akworob/mariadb_mcp_server Enables AI assistants to interact with MariaDB databases through schema exploration, query execution, and database statistics. Includes security features like read-only mode, parameterized queries, and connection pooling with support for bo | |
| google-seo-mcp akxan/google-seo-mcp Enables AI agents to diagnose and fix technical SEO, content, and generative engine optimization issues by providing 72 tools that integrate Google Search Console, Google Analytics 4, PageSpeed Insights, structured data, llms.txt, WordPress | |
| auth0-whoami-mcp akxentech/auth0-whoami-mcp A minimal remote MCP server for Auth0 Custom Extensions that provides a single tool, who_am_i, returning safe identity claims from the authenticated Auth0 access token without exposing sensitive credentials. | |
| cimd-reader akxentech/cimd-reader Enables testing and validation of MCP OAuth clients by observing whether they use Client ID Metadata Documents (CIMD), fall back to Dynamic Client Registration, or send static client IDs via a fake OAuth server and dashboard. | |
| LocalMCP al-mighty/localmcp Enables coding agents to share a persistent local memory store across sessions and clients, saving, searching, updating, and retrieving facts, decisions, incidents, preferences, references, and snippets with semantic and lexical search. | |
| Business Data MCP al-rowads/mcp An evidence-first Model Context Protocol server for private business documents and structured datasets, preserving original files and source lineage. | |
| graccess-mcp al1t0/gracces-mcp-server MCP server that enables natural language querying and configuration of AVEVA System Platform galaxies, supporting object query, attribute inspection, model navigation, configuration writes, instance creation, and deployment. Runs on-premise | |
| @agentbook/mcp al3al3al333/agentbook-mcp Enables MCP-capable agents to access AgentBook's pay-per-call tools for agent social feeds, funded bounties, DeFi/gas intelligence, and security reconnaissance without API keys or signup. | |
| lol al3al3al333/lol 53 security & enrichment MCP tools for AI agents. Contract scanning, threat intel, OSINT, crypto data, DNS/WAF recon. Pay-per-call via HTTP 402 + USDC on Base mainnet. No API keys. First call free. | |
| text2d al3duc/text2d-mcp Enables AI assistants to procedurally generate, edit, quantize, and export 2D retro pixel art textures and tilesets for game development, with built-in palettes, dithering, and pixel-level manipulation tools. | |
| Goxel MCP Server al3x-d3v357/goxel-mcp Enables AI agents to procedurally model and sculpt 3D voxel characters, weapons, and scenery, execute custom QuickJS generation scripts, convert/export models between voxel and 3D/image formats, and open results in the desktop GUI for inspe | |
| AL CodeGen MCP Server al426198/mcp-server Generates AL code for Business Central directly from your IDE, enhancing developer efficiency by providing tools, prompts, and resources for code generation. | |
| kiosktunes-mcp al4xdev/kiosktunes-mcp Zero-bloat YouTube Music streaming server and persistent TTY player with real-time DSP audio enhancement and agent listening history for developers and AI agents. | |
| Dev Notes MCP Server al928132/mcp-server Enables Claude Code to save, list, and read markdown notes directly from conversations, eliminating manual file management for project ideas, debugging notes, and meeting summaries. | |
| LiveMCP alaarab/livemcp Turns Ableton Live into an MCP-accessible control surface, providing tools for controlling transport, tracks, clips, and devices, as well as resources for reading live state. | |
| phren alaarab/phren A persistent memory server for AI agents that stores findings, tasks, and patterns in Markdown files within a git repository, enabling context injection across multiple AI tools. | |
| AL's Kanban MCP server alaatawalbeh/alskanban-mcp Enables MCP clients to manage boards in an AL's Kanban instance, including listing workspaces and boards, creating and editing cards, moving cards between lists, setting due dates, and attaching local files directly to cards. | |
| whoop-tracker-mcp-server alacore/whoop-tracker-mcp-server Integrates with Whoop API v2 to access user profile, sleep, recovery, cycles, and workout data via natural language, with OAuth2 authentication and automatic token refresh. | |
| md-annotate alaeddineg/md-annotate A local-first markdown review tool with MCP integration, enabling AI and humans to collaboratively annotate documents inline and generate revision prompts. | |
| ContextPro alaeddinemessadi/contextpro-mcp Enables coding agents to retrieve bounded source context and compiler-exact TypeScript/JavaScript references, with inspectable evidence and evidence-aware coding workflows. | |
| Gemini Embedding 2 MCP Server alaeddinemessadi/gemini-embedding-2-mcp-server A multimodal local memory MCP server that lets AI agents search across text, PDFs, images, audio, and video using Gemini Embedding 2 and a local ChromaDB. | |
| opencode-mcp alaeddinemessadi/opencode-mcp Bridges MCP clients to OpenCode's headless API, enabling AI to delegate autonomous coding tasks like building features, debugging, and refactoring across multiple projects. |
25,701–25,750 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.