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 |
|---|---|
| Brewfather MCP 03eltond/brewfather-mcp This remote server provides a comprehensive interface for the Brewfather platform. It enables users to manage recipes, track ingredients, and update batch statuses and hydrometer readings through an MCP client. | |
| Email Verification MCP Server 05tanish/email-verification-mcp Provides an MCP tool to verify email addresses, returning valid, invalid, risky, or error statuses via the InboxValid API. It includes a mock API and retry logic for robust, type-safe verification. | |
| zhiwei 0718lol/zhiwei Provides AI agents with a read-only, local-first depth layer into Chinese web platforms—Zhihu, Weibo, and WeChat Official Accounts—offering hot lists, Q&A, posts, clean article markdown, plus opinion aggregation and TextRank summaries. | |
| M-Team MCP Server 07freedom/mcp-server-mteam Enables AI assistants to interact with the M-Team private torrent tracker API for searching resources, retrieving torrent details, and downloading torrent files. It provides a bridge for Model Context Protocol clients to manage and access p | |
| Smallway Desktop MCP 0800happy/smallway-desktop-mcp Gives ChatGPT controlled access to local files, terminal sessions, and Windows desktop UI through a local-first policy gateway with workspace-scoped permissions and stable MCP tools. | |
| AIVA MCP Server 0800tim/aiva-mcp Connects AI coding assistants to AIVA's customer intelligence and Shopify store data for managing subscriptions, affiliate tracking, and customer analytics. It enables direct access to RFM segments, churn predictions, and product informatio | |
| ktrack 0912kth-ops/k-community-trackagent Enables AI agents to discover and explore Korean community boards, search posts, and read post content and comments through a read-only MCP interface. | |
| pvc-mcp-server 096v/pvc-mcp-server A Git-like version control system for AI agent decision tracking, enabling plan commits, diffs, branches, and history. | |
| 09orche 09kz/09orche Enables Claude Code to delegate tasks to free OpenRouter models as callable tools while keeping the Anthropic endpoint for the orchestrator, with optional sandboxed file and shell access. | |
| Jokes MCP Server 09tns/telljocke A humor-focused MCP server that delivers jokes through Microsoft Copilot Studio. Demonstrates how to deploy an MCP server on Azure and integrate it with Power Platform connectors for AI-powered agents. | |
| hypr-tools 0aaryan/hypr-tools Enables an AI assistant to control a Hyprland/Wayland Linux desktop through 178 tools across 30 categories, covering audio, window and workspace management, themes and wallpapers, screenshots and recording, Bluetooth, media playback, notifi | |
| Modular MCP Server 0brym/mcp A config-driven, zero-dependency MCP server with plugin architecture that enables filesystem operations, shell commands, HTTP requests, and utilities through simple JSON configuration. | |
| comfyui-roundabout 0c0/comfyui-roundabout Exposes ComfyUI workflows as 12 MCP tools on ComfyUI's own port, letting AI agents generate, edit, and remove backgrounds from images plus create videos by passing semantic parameters instead of whole workflow graphs. Agents can list models | |
| FOFA MCP 0day404/fofa-mcp Enables agents to query internet asset data through full FOFA DSL or structured conditions, with cursor-based pagination, field aggregation statistics, host/IP detail lookup, and account quota inspection. Adds multi-account rate-limit failo | |
| okfy 0dust/okfy Enables AI agents to search, read, and traverse documentation bundles in Open Knowledge Format via MCP tools. | |
| STU MCP 0error0warning/stu-mcp Runs locally to let agents access Shantou University campus notices, grades, courses, assignments, exams, and schedules from public sites, OA, academic systems, MySTU, and Yuketang. Public data works without login, while personal features u | |
| comfy.fun MCP 0g-axion/comfy-mcp Enables MCP clients to read 0G market data — tokens, trades, quotes, creator fees, compute and tasks — and to build unsigned launch and swap transactions for an external wallet to review and sign. It holds no keys, never signs or submits, a | |
| mcp-apps 0gis0/mcp-apps Enables interacting with YouTube Data API v3 through MCP tools (get-video, get-channel, get-latest-video) and bundled UI apps for video and channel profiles. | |
| mcp-elicitations 0gis0/mcp-elicitations A demonstration MCP server that shows how to use elicitations to ask users for preferences during a video search tool execution. | |
| mcp-low-level-server-streamable-http 0gis0/mcp-low-level-server-streamable-http A TypeScript-based MCP server that implements a simple note-taking system using low-level server components and streamable HTTP. It enables users to create, store, and summarize text notes through a set of tools, resources, and specialized | |
| MCP Sampling Demo 0gis0/mcp-sampling Demonstrates how to implement sampling in MCP servers, allowing tools to request LLM content generation from the client without requiring external API integrations or credentials. | |
| YouTube MCP Server 0gis0/miduconf-mcp Enables interaction with YouTube through the YouTube Data API, allowing users to search for videos, playlists, and channels, generate video titles using AI, and manage YouTube content through natural language commands. | |
| giants-editor-mcp 0h-marvvv/giants-editor-mcp Enables Claude to drive a live GIANTS Editor 10.x (FS25) session with 59 tools for terrain editing, field creation, asset placement, map audits, and more through natural language. | |
| Academic Research & Sci-Hub MCP Server 0jsdanny/academic-research-mcp Enables AI agents to conduct literature reviews by screening multiple academic databases, performing backward and forward citation snowballing, and resolving or downloading full-text PDFs through subscription and open-access sources. | |
| slop-cop 0ju1c3/slop-cop Detects and fixes LLM prose patterns in text, exposing tools for auditing and improving writing quality in MCP-compatible hosts. | |
| devflows-mcp 0langa/cibseven-devflows Enables AI coding agents to drive developer workflows as BPMN processes on a local CIB seven engine, including starting releases, inspecting runs, and approving human-decision gates via MCP tools. | |
| Azure AI Agent Service + Azure AI Search MCP Server 0lovesakura0/mcp-server-azure-ai-agents-main Enables Claude Desktop to search private documents using Azure AI Search and perform web searches with Bing, providing AI-enhanced results with source citations through Azure AI Agent Service or direct Azure AI Search integration. | |
| mcp-artisan 0mandrock1/mcp-artisan Provides read-only, structurally safe introspection of a Laravel codebase, letting AI agents inspect routes, models, migrations, jobs, and config without risk of mutation or secret disclosure. | |
| mcp-esp32 0mandrock1/mcp-esp32 Enables interaction with ESP32/MicroPython boards via tools for flashing firmware, running REPL code, file management, and serial capture, with support for progress notifications, cancellation, and error handling. | |
| mcp-vpsobs 0mandrock1/mcp-vpsobs Enables read-only observability of a Linux host via MCP, exposing allowlisted systemd, docker, nginx, logs, disk, and cert info without shell access. | |
| coordharness 0marm0/coord-harness Enables agents to coordinate through a shared SQLite authority, claiming and handing off work, posting notes, and reading a live board with proof-gated completion. | |
| claude-bridge-mcp 0motionguy/claude-bridge-mcp An MCP server that exposes your local Claude Code CLI over HTTP+SSE, enabling any MCP-compatible client to use your Claude Code MAX/PRO subscription remotely. | |
| SitemapKit MCP Server 0nl1n1n/sitemapkit-mcp Enables AI assistants to discover and extract sitemaps from any website, providing tools for finding sitemap files, extracting URLs, and performing full crawls. | |
| HSI MCP Server 0nri/hsi-mcp-server Retrieves real-time Hang Seng Index data and news headlines with AI-powered summaries from AAStocks, supporting stock quote lookups via symbol or company name. | |
| Sashiko MCP 0nsec/sashiko-mcp MCP server that queries the Sashiko AI kernel-patch review service to find critical/high severity vulnerabilities (LPE, UAF, OOB, etc.) in reviewed patches, including overlooked AI findings. | |
| DSW Control MCP 0ozzzii/cf-remote-mcp Enables secure remote control of an allowlisted ModelScope DSW machine through a stateless Cloudflare Workers MCP gateway, supporting shell command execution, target listing, and health checks. | |
| Remote Host MCP 0ozzzii/remote-host-mcp Enables AI-controlled administration of remote Linux hosts and containers, including bounded shell execution, persistent PTY sessions, durable jobs/tasks, hardened filesystem access, process/service control, and resumable transfers. | |
| idealista-mcp 0p3rador/ide4lista-mcp Enables reading Idealista messaging conversations and sending messages through a user-run Chrome instance via Chrome DevTools Protocol. Includes draft and confirmation safeguards before sending. | |
| scrapingdog-mcp 0pen1/scrapingdog-mcp MCP server that exposes Scrapingdog APIs for web scraping, search engine queries, social media profiles/posts, screenshots, and datacenter proxy usage via nine tools. | |
| jev-browser-mcp 0pilatos0/jev-browser-mcp Enables an LLM to drive a real browser efficiently by using a lightweight decision model for each step, providing tools for navigation, clicking, typing, and extracting page data without sending full page snapshots to the model. | |
| Codex MCP Sidecar 0pinky0/codex-mcp-sidecar A local MCP server that lets Claude Code start, resume, and wait for Codex app-server sessions while humans inspect live sessions from a terminal. | |
| @0pvalencia/academic-linter-mcp 0pvalencia/academic-linter-mcp MCP server that lints academic documents (APA/structure) from Google Docs JSON, offering tools to check structure, compact headings, and find placeholders like TODO or lorem. Complements the Google Documents MCP server. | |
| app-screenshot-mcp 0pvalencia/app-screenshot-mcp MCP server for capturing real UI screenshots using Playwright. Provides tools to capture a URL or capture with login and selectors. | |
| @0pvalencia/chart-from-data-mcp 0pvalencia/chart-from-data-mcp MCP server that renders bar, line, and pie charts from data using QuickChart, returning PNG file paths. | |
| db-introspector-mcp 0pvalencia/db-introspector-mcp MCP server for introspecting PostgreSQL databases, providing tools to list tables, describe schemas, foreign keys, and generate DOT ER diagrams. | |
| diagram-studio-mcp 0pvalencia/diagram-studio-mcp MCP server for rendering diagrams (Mermaid, Graphviz, PlantUML, D2) via Kroki. Provides tools to render diagrams and list available engines. | |
| Google Documents MCP 0pvalencia/google-workspace-mcp An MCP server that enables AI assistants to manage Google Docs through natural language, including listing, reading, creating documents, and appending text. It features a simple browser-based OAuth login and persistent sessions. | |
| image-lab-mcp 0pvalencia/image-lab-mcp MCP server for searching and attributing images from Openverse and Wikimedia Commons, enabling insertion via insertUrl and attribution formatting. | |
| 0rca Dojo MCP Server 0rcanetworkalgorand/dojo_mcp Enables AI agents to browse, match, and hire agents from the 0rca Swarm Dojo marketplace, including task creation and result retrieval. | |
| dis-claude 0rnot/dis-claude Connects Discord to Claude Code, turning forum threads into interactive sessions. Supports approvals, live progress, slash commands, and terminal access. |
21,451–21,500 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.