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 |
|---|---|
| arr-mcp dogeared/arr-mcp Enables MCP clients to interact with the arr media stack (Sonarr, Radarr, Prowlarr, Jellyseerr, Bazarr) via clean, typed tools over each app's REST API. | |
| dsm-mcp dogeared/dsm-mcp Enables MCP clients to inspect Synology NAS system, storage, and utilization, and manage Docker containers via the Synology Web API with automatic session handling. | |
| mcp-terminal dogeheng/mcp-server-controller Enables MCP clients to create and control persistent, PTY-backed terminal sessions on macOS: launch commands and interactive programs, read output incrementally via byte cursors, send keystrokes, wait on conditions, and detect running/await | |
| Dogeshit MCP dogeshitmeme/dogeshit-mcp Enables AI agents to trigger on-chain minting of $SHIT tokens via EIP-7702 delegation and MCP, with the user retaining full custody and the contract ensuring tokens go to the caller's own wallet. | |
| StashDog MCP Server dogfoodlab-io/stashdog-mcp-server Enables AI assistants to manage StashDog inventory through natural language commands, supporting item management, collections, tags, smart search, and URL imports with secure authentication. | |
| EndNote Library Reader doggy-saint/enl-reader-mcp Enables programmatic access to EndNote .enl libraries, allowing users to list, search, and extract full text from bibliographic references and their attached PDFs through MCP tools. | |
| mcp-http-api-gateway doghelwang/mcp-http-api-gateway Wraps bare-IP HTTP REST APIs as MCP tools, supporting dynamic IP switching and stdio/SSE modes for use in AI IDEs. | |
| mcp-visual-programming-pc-client doghelwang/mcp-visual-programming-pc-client Enables AI agents to programmatically create and manipulate Qt-based visual programming flows, including device model parsing and port connection, through natural language. | |
| wpa-mcp dogkeeper886/wpa-mcp Control Linux WiFi from Claude and other MCP clients — scan, connect, debug, and automate networks (WPA-PSK, WPA2-Enterprise, EAP-TLS, Hotspot 2.0, captive portals, MAC randomization) over the Model Context Protocol. | |
| Alpaca Trading MCP Server dogmaai/alpaca-mcp-server Enables natural language trading operations through Alpaca's API, supporting stocks, options, crypto, portfolio management, and real-time market data with comprehensive order execution and account management capabilities. | |
| Elrond MCP dogonthehorizon/elrond-mcp Enables enhanced decision-making through hierarchical LLM analysis, using three specialized critique agents (positive, neutral, negative) that analyze proposals in parallel and synthesize them into comprehensive, actionable insights. Helps | |
| cedulon dogrucanemek-alt/cedulon Policy-gated agent spend with signed receipts and rail-extract audit: a fail-closed gate issues a COSE receipt for every allowed payment, and the audit reconciles those receipts against a rail extract so a settlement with no receipt is name | |
| Roblox Super MCP dogtheseller/robloxsupermcp A Node.js MCP server that connects MCP clients to Roblox Studio's official MCP process, adding discovery, inspection, auditing, atomic script edits, verification, and rollback-oriented tools. | |
| dsh-plugin-subagent-bridge dogtiti/dsh-plugin-subagent-bridge Exposes a local loopback MCP endpoint that lets Codex spawn, wait on, follow up with, and close DeepSeek Harness sessions as workers and read back their final answers, while letting DSH agents dispatch work back to Codex in return. Includes | |
| netcdf-mcp dogukanteber/netcdf-mcp Enables reading and understanding NetCDF files, providing tools to inspect structure, variables, metadata, and data quality for scientific datasets. | |
| Chat2Local doguozyigit/chat2local Connects ordinary ChatGPT chats to a single user-chosen project folder so they can read, edit, and search files, run bounded development commands, drive a separate browser profile, discover relevant skills, and save per-chat recovery checkp | |
| GDotMCP dohmboy64bit/gdotmcp MCP server providing 174 tools for AI-powered Godot 4 development, enabling scene manipulation, scripting, animation, runtime analysis, and more. | |
| MCP JobSearch dohoasen/mcp_jobsearch Personal job posting management MCP server that fetches job postings from multiple Korean job sites and stores them for LLM analysis, enabling timeline tracking and cover letter draft management. | |
| InfluxDB Natural Language Query MCP Server dohoon84/influx-db-mcp Enables users to generate and execute InfluxDB queries using natural language commands in Korean. Supports querying metrics like CPU usage, memory status, and system monitoring data through conversational interface. | |
| HoneyMCP dohunkr/honeymcp Enables generating human-quality A Dance of Fire and Ice (ADOFAI) custom maps from any song by extracting note onsets with ffmpeg, then auto-placing beat-synced tiles, multi-key presses, and camera/lighting effects — validated by a quality | |
| doibio-mcp doi-dot-bio/mcp Enables MCP clients to search, read, edit, fork, and create vaults and pages on doi.bio through its public HTTP API, with token-based writes and versioned page editing. | |
| toolhive-mcp doingdog/toolhive-mcp A hosted HTTP MCP server for Cloudflare Workers that exposes a bundle of tools via a remote /mcp endpoint, enabling Claude-compatible clients to connect without a local server. | |
| Todoist AI MCP Server doist/todoist-mcp Enables AI agents to access and modify Todoist accounts to manage tasks and projects on the user's behalf. It provides a suite of tools for task operations and supports interactive UI widgets for a rich visual experience in AI chat interfac | |
| Twist AI MCP Server doist/twist-ai Enables AI agents to access and interact with a Twist workspace, managing threads, conversations, inbox, and more through natural language. | |
| google-task-ifttt-webhook-mcp doitian/google-task-ifttt-webhook-mcp MCP server running on Cloudflare Workers that exposes a create_google_task tool to send tasks to Google Tasks via IFTTT Maker webhook. | |
| DoiT MCP Server doitintl/doit-mcp-server Provides LLMs with access to the DoiT API for managing cloud resources, analyzing costs, and handling support tickets via natural language. | |
| Obsidian MCP Server dojicreates/local-obsidian-mcp-server-with-claude Connects Claude Desktop to your Obsidian vault, enabling reading, writing, searching, and organizing notes locally. | |
| hacienda-cr MCP Server dojocodinglabs/hacienda-cr MCP server that enables AI assistants to issue electronic invoices (facturas electrónicas) in Costa Rica through the Hacienda API v4.4. | |
| mcp-metricool dojocodinglabs/mcp-metricool MCP server for Metricool — schedule social media posts, get analytics, and find optimal posting times. | |
| nanobanana-mcp dojocodinglabs/nanobanana-mcp A security-hardened MCP server for generating and editing images using Google Gemini models. It provides tools for text-to-image creation and iterative image editing with strict input validation and secure file handling. | |
| remote-mcp-server-authless dojododo/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without authentication, enabling use with Cloudflare AI Playground and local clients via mcp-remote proxy. | |
| Sensei MCP dojoengine/sensei-mcp A Model Context Protocol server that provides expert guidance for Dojo and Cairo development on Starknet, offering specialized knowledge and assistance for building onchain worlds using the Dojo Entity Component System framework. | |
| no-tax-on-tips-mcp dojogenesis/no-tax-on-tips-mcp MCP server that exposes the OBBBA No Tax on Tips federal deduction logic as callable tools, enabling users to check eligibility and estimate tip deductions. | |
| Laravel MCP Server dok4everak47/cortex-agent-runtime Exposes Laravel development tools (artisan, migrations, config, schema, logs) as MCP tools for use with compatible clients. | |
| reflex-brain dokiromboide/reflex-brain MCP server that gives AI agents a continual learning brain with lessons, skills, memories, evidence-based refinement, rollback, and hybrid GraphRAG retrieval. | |
| all-agents-mcp dokkabei97/all-agents-mcp Enables orchestrating multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified MCP interface for task delegation, cross-agent comparison, and specialized tools like code review and debugging. | |
| redmine-mcp dokkiitech/redmine-mcp MCP server to operate self-hosted Redmine from Claude Code, enabling project and issue management, search, and metadata retrieval via natural language. | |
| Dokmatiq DocGen dokmatiq/docgen-sdks PDF/DOCX/Excel generation from HTML/Markdown with stationery overlay, ZUGFeRD/XRechnung e-invoicing, digital signing, form filling, and AI receipt OCR with DATEV/SKR03 export. | |
| MCP Memory doko89/mcp-memory Enables MCP clients to remember user preferences and behaviors across conversations using vector search technology. | |
| MyContext MCP Server doko89/mcp-mycontext Enables personal project documentation management through local markdown files stored in nested directories. Supports organizing context by project and layer (backend/frontend/fullstack) with search functionality across all documentation fi | |
| Godot MCP Server dokujaa/godot-mcp Enables Claude Desktop to control and interact with the Godot Engine editor through the Model Context Protocol. It supports dynamic scene generation and direct asset importation via Meshy API integration. | |
| retail-inventory-mcp-server dol7/retail-inventory-mcp-server Enables MCP clients to query synthetic retail inventory data through eight tools, covering stores, inventory levels, promotional events, sales transactions, recommendations, and sell-through metrics, with access scoped by Partner API keys. | |
| companysim dolevhayut/companysim Enables AI agents to explore and query a locally generated synthetic organization—with employees, teams, projects, documents, and relationships—through read-only MCP tools, facilitating agent testing, evaluation, and demos without external | |
| okc-mcp dolgogae/okc-mcp A local Obsidian Vault authoring MCP for building high-quality knowledge inputs for OKC, enabling note creation, search, and audit without the Obsidian app. | |
| MCP Weather Server dolgova/mcp-weather-server MCP server that provides current weather and forecasts via Open-Meteo API, with an optional ML-based next-day max temperature prediction. | |
| MCP Dev Runtime dolibali/mcp-dev-runtime Enables direct local development operations such as shell commands, interactive terminals, file patches, images, and execution history through MCP tools, accessible via HTTP/stdio or a ChatGPT tunnel. | |
| Human Taste Engine dollan9/human-taste-engine A local MCP server that gathers web captures, image crops, video frames, and copy into structured evidence artifacts, letting a vision-capable agent inspect the returned media and produce evidence-backed critique with scored findings, compa | |
| GR-MCP dollarhyde/gr-mcp An MCP server that enables natural language-driven creation and management of GNU Radio flowgraphs with validated block connections and parameter configurations. It provides tools for searching the GNU Radio block library, detecting SDR har | |
| keyless-web-search-mcp dollarser/keyless-web-search-mcp Enables keyless web search across multiple engines with fallback and relevance ranking, plus anonymous HTTP(S) page fetching, all without API keys or vendor dependencies. | |
| CargoEffe MCP Server dollob/cargoeffe-mcp Connects AI assistants to CargoEffe for automated cargo loading plan design, offering tools to manage containers, cargo items, and load plans. |
45,351–45,400 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.