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 |
|---|---|
| today-work-log bottlesun/today-work-log-mcp Extracts today's Git commit history and code changes from a local repository, filtering by the current user and excluding merge commits, for integration with MCP clients like Claude Desktop. | |
| Defense MCP bottobot/defense-mcp-server This is a Linux OS hardening tool. Take a fresh install and immediately harden the heck out of it using just your favourite LLM agent and natural language prompts. "Make my system secure" or "Do a full security audit of my system." | |
| TouchDesigner MCP Server bottobot/touchdesigner-mcp-server Enables AI coding assistants to access comprehensive TouchDesigner operator documentation, Python API references, and tutorials for building TouchDesigner networks. | |
| botverse-mcp botverselive/botverse-mcp MCP server + JS SDK for BotVerse, a bots-only social network where AI bots post, reply, like and follow while humans watch. | |
| xiaozhi-mcp botwith/xiaozhi-mcp A versatile MCP server framework that enables AI capabilities like remote control, calculations, and email operations via multiple transport types. It supports stdio, SSE, and HTTP protocols for seamless integration between language models | |
| Timers Studio MCP Server bouamargemini-droid/timers-studio-mcp-server Enables LLM clients to answer prospect questions about Timers Studio, a professional broadcast timer platform, with first-party data on competitive positioning, use cases, personas, and recommended plans. | |
| Logitech Sync MCP bouchecousue/logitech-sync-mcp A read-only MCP server for the Logitech Sync Cloud API, providing tools to inspect rooms, desks, devices, health, occupancy, coverage, environmental readings, and network information. | |
| godot-mcp bouelon/godot-mcp Bridges AI assistants with the Godot 4 editor, exposing tools to inspect scenes, create nodes, modify properties, capture screenshots, debug scripts, and manage project files via the Model Context Protocol. | |
| Jira MCP Server boukeversteegh/mcp-server-jira Enables to interact with JIRA issues and sprints through MCP tools, including fetching tickets, adding comments, linking issues, and more. | |
| agy-mcp boulea7/agy-mcp Wraps Google Antigravity CLI into 11 typed MCP tools, enabling any MCP client to invoke agy for code review, prototyping, execution, and long-running tasks. | |
| authority-webhook-mcp boundarycraftlab/authority-webhook-mcp Publishes normalized release notices to a configured webhook via MCP, with built-in validation, deterministic dry-run mode, and a clear boundary for authority gates. | |
| @bounded-systems/verbspec-mcp bounded-systems/verbspec-mcp Turns any verb Registry into a real MCP server, where each verb becomes an MCP tool with its own Zod input/output schemas (zero drift). | |
| @bountylens/mcp bountylens/mcp Connects Claude Code to BountyLens Hunter Tracker for managing bug bounty hunt sessions, findings, leads, and programs. | |
| bounty-operator bountyoperator/bounty-operator Connects MCP clients to pre-submission review that argues against a draft bug-bounty report or smart-contract finding the way a triager would, tying every claim to a supplied file and line and returning a submit, rewrite-then-submit, prove- | |
| ProjectMemory bountyyfi/projectmemory A proof-of-concept MCP server for security research demonstrating a multi-phase parasitic attack that disguises itself as a legitimate project memory tool while profiling users and executing cross-server shadowing attacks. | |
| k8s-pilot bourbonkk/k8s-pilot A lightweight, centralized control plane server that enables management of multiple Kubernetes clusters simultaneously, supporting context switching and CRUD operations on common Kubernetes resources. | |
| ollama-cloud-mcp bouroo/ollama-cloud-mcp Enables MCP clients to search the web and fetch individual pages through two stdio tools, returning ranked results or extracted page content, titles and outbound links. It wraps a hosted, API-key-authenticated service (or a local daemon) wi | |
| Remote MCP Server Authless bousche/remote-mcp-server-authless Deploys a customizable remote MCP server on Cloudflare Workers without authentication, enabling tools to be used with clients like Claude Desktop and Cloudflare AI Playground. | |
| KiCAD MCP Server bov27/mcpkicad A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with KiCAD for PCB design automation. | |
| API Weaver bowbozaa/api-weaver A comprehensive MCP server with RESTful API that enables file operations, command execution, project management, and AI integration for remote development control with security features and real-time communication. | |
| Multi-Model Broker bowen-studying/multimodel-broker Enables MCP clients to delegate tasks to multiple local and cloud AI workers (Codex, Claude Code, DeepSeek, GLM, Gemini) with deterministic routing, concurrent batch execution, idempotent retries, and auditable traces. | |
| ExpressJS MCP bowen31337/expressjs_mcp Exposes Express.js API endpoints as MCP tools, preserving existing schemas and authentication behavior. Supports streaming responses and can be mounted directly to existing Express apps or run as a standalone gateway. | |
| MediaCrawler MCP Server bowenwin/mediacrawler_mcp_server MCP server for crawling social media platforms (e.g., Bilibili) by keywords, video IDs, or creator IDs, with support for MySQL, JSON, and CSV storage. | |
| music-library-mcp bowerharry/music-library-mcp Enables Claude to manage an Apple Music library on macOS by searching tracks, editing tags and albums, filling genres from MusicBrainz, managing playlists, resolving duplicate albums, deleting or re-adding songs, and undoing changes through | |
| Obsidian MCP Server - Enhanced boweylou/obsidian-mcp-server-enhanced A Model Context Protocol server that provides comprehensive access to Obsidian vaults with Claude.ai remote integration, Tailscale support, and advanced query capabilities. | |
| CURRENT•SEA bowieboii/current-sea Enables AI agents and software to detect ambiguous wording in text and receive location, category, explanation, and suggested clarification questions for each signal. | |
| @bowlly/mcp-server bowlly-net/bowlly-mcp-server Enables cat food product search and ingredient analysis using natural language queries. | |
| texting bowlofarugula/texting Enables Claude to send and read iMessages on macOS, with human approval required for sending and no auto-replies. | |
| whatsapp bowlofarugula/whatsapp MCP server for sending and reading WhatsApp messages through Claude, with human approval on sends and no auto-replies. | |
| IMAP MCP Connector bowlsbeyk/imap-mcp-connector Connects Claude to any IMAP/SMTP mailbox so it can list folders, read and search messages, fetch attachments, and create or send drafts, with read/draft/send permission modes and built-in OAuth. Designed for mail hosts that lack a native Cl | |
| strudel-ai bowmana/strudel-ai Enables AI agents to create and edit Strudel music code, render offline WAV audio, and obtain structured hearing reports with waveform, spectrogram, BPM, and onset analysis. | |
| gmail-mcp-plus bowtiedswan/gmail-mcp-plus MCP server that connects Gmail and Google Calendar to AI assistants, enabling email search, reading, sending, and calendar management across multiple accounts with secure OAuth. | |
| grok-oauth-mcp bowtiedswan/grok-oauth-mcp Enables local MCP clients to interact with xAI Grok through OAuth PKCE, supporting chat, X search, image/video generation, TTS, and transcription. | |
| bowtie-mcp bowtieworks/bowtie-mcp MCP server for managing Bowtie clusters, enabling natural language control of policies, devices, DNS, users, and more. | |
| GeminiMcpServer bowwowxx/geminimcpserver Enables seamless integration between MCP-compatible clients (like LM Studio) and Google Gemini API for image generation and multimodal tasks. Provides a hybrid local-cloud workflow combining local LM Studio execution with Gemini's cloud-pow | |
| Box MCP Proxy Server box-community/box-remote-mcp-proxy A proxy server that bridges MCP clients with Box's remote MCP server, handling OAuth 2.0 authentication and message forwarding over HTTP. | |
| MCP Server Box box-community/mcp-server-box A Python server that enables interaction with Box files and folders through the Box API, allowing operations like file search, text extraction, and AI-based querying and data extraction. | |
| Box Kite MCP box-kite/box-kite Use correct the Box Kite library | |
| 神岛数据统计 MCP 服务器 box3lab/statistics-mcp 提供对神岛平台用户数据、地图信息和统计数据的访问，包括公开和需要认证的API。 | |
| mcp-notify box7e7/mcp-notify Sends push notifications from AI assistants to your mobile device. Supports Claude, Cursor, Windsurf, and more. | |
| inprofile boxed-dev/inprofile Enables reading LinkedIn profiles into structured JSON using your own signed-in session, with no browser automation or API keys. | |
| threatmodel-mcp boxed-dev/threatmodelling-mcp Enables AI-powered threat modeling with tools for creating threat models, analyzing security threats, generating security controls, and validating architecture against best practices. | |
| Boxline MCP server boxline-dev/mcp Enables MCP clients such as Claude and Cursor to control an isolated cloud machine with a real browser, shell, filesystem, and web access, so agents can navigate pages, click and type, run commands, manage files, and search or fetch web con | |
| Firefly III MCP Server boxpositron/firefly-iii-mcp Enables AI tools to interact with Firefly III personal finance management instances through a cloud-deployed MCP server. Supports financial operations like account management, transactions, budgeting, and reporting with configurable tool pr | |
| Boxtalk Data MCP Server boxtalk/boxtalk-data-mcp Provides tools for interacting with SQL Server databases, enabling users to retrieve paginated table data, inspect schemas, and count records. It features enforced pagination and secure configuration options to manage database operations ef | |
| Prescription Review MCP Server boya1999/when-laboratory-evidence-is-incomplete-who-may-approve Enables MCP-integrated prescription review with incomplete laboratory evidence, using deterministic rules and language-model guardrails to enforce approval authority boundaries. | |
| FL Studio 2025 AI Bridge boyan253/fl-studio-2025-ai-bridge Enables AI assistants to read and control FL Studio 2025 projects via file-based RPC and MIDI wake, overcoming sandbox restrictions for tempo, mixer, and note recording. | |
| sharpspring-mcp-server boyddriesen/sharpspring-mcp-server An open-source MCP server for the SharpSpring API (Constant Contact Lead Gen & CRM) that enables AI clients to read and write Leads, discover custom fields, and call any documented API method. | |
| Python MCP Server Kit boyeep/python-mcp-server-kit Enables developers to build and deploy secure, typed Model Context Protocol servers with tools, resources, prompts, bearer-token authentication, per-tool scopes, rate limiting, and health probes over Streamable HTTP. | |
| hike-finder boykoneov/hike-finder-mcp Finds marked hiking routes from OpenStreetMap filtered by locally-computed elevation gain, distance, loop shape, and car/chairlift access, providing consistent and tunable metrics instead of third-party scraped data. |
35,201–35,250 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.