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 |
|---|---|
| codex-photoshop-psd-automation bdhxhxhhxhxhxhhxjxhxhxhxhx2-del/codex-photoshop-psd-automation Enables Codex to orchestrate Adobe Photoshop via MCP to reconstruct AI-generated artwork into editable, validated layered PSDs, with automated saving, reopening, and verification. | |
| mcp-mail-bridge bdi-admin/mcp-mail-bridge Enables an LLM client to read and manage email over IMAP/SMTP with read-only mailbox operations and safe, idempotent send/reply, without mutating messages or risking duplicate sends. | |
| Lexware Office MCP Server bdiaby1/claude_lexware_mcp_2 Enables MCP-capable assistants to query and manage Lexware Office contacts, sales documents, vouchers, files, payments, webhooks, and reference data via the Lexware Office public API. Adds bank reconciliation tools for matching bank stateme | |
| Lexware Office MCP Server bdiaby1/claude_lexware_mcp_3 MCP server for Lexware Office that enables querying and managing contacts, sales documents, vouchers, files, payments, and webhooks through a sandboxed two-tool interface (search/execute) with read-only-by-default write safety. | |
| mem0-lite bdombro/mem0-lite Provides self-hosted memory management for coding agents via MCP, with local vector storage and tools for adding, searching, updating, and deleting memories. | |
| 蓝的唤醒桥 bdoublel1021-stack/blue-wake-bridge Enables ChatGPT to schedule future proactive messages and receive queued events into conversations through MCP Apps, without calling the OpenAI API. | |
| Kount Developer MCP bdrhoa/kount-developer-mcp Enables developers to integrate Kount Payments Fraud v2 from a coding assistant by inspecting API contracts, generating and validating synthetic requests, authenticating against Sandbox, troubleshooting errors, and checking integration read | |
| gma3-mcp bdstark/gma3-mcp Enables MCP clients such as Claude Code or Claude Desktop to control grandMA3 onPC by executing command-line commands, running Lua, reading show data like sequences, cues, executors, patch and pools, driving playback and faders, and looking | |
| CodebaseHQ MCP Server bdteo/codebasehq An MCP server that enables users to manage CodebaseHQ tickets and track project activity through natural language. It supports searching tickets, viewing discussions, and performing updates such as creating new tickets or changing assignmen | |
| Pinchtab MCP Wrapper bduba/pinchtab-mcp-wrapper MCP server that exposes the Pinchtab browser API for token-efficient web scraping, change detection, and automated testing workflows. | |
| Dad Joke MCP Server bdurrett/joke-poc-mcp-server A Python-based MCP server that generates creative dad joke prompts on any topic in various styles, enabling AI agents to produce dad jokes through natural language requests. | |
| LicenseGround MCP Server bdzgroup12/licenseground Enables AI agents and procurement systems to verify contractor licenses against official state boards, search contractors by trade and location, audit workers' comp, surety bonds and OSHA safety records, and check SAM.gov federal debarment | |
| Volante be-aesthetics/volante Enables AI apps to connect to any local or remote MCP server through one local endpoint, with per-server permissions, tool prefixes, and an activity log. Supports one-click connections to multiple AI clients and imports servers already conf | |
| Pulse MCP Server be-infinitum/pulse-mcp Enables interaction with the Pulse usage-based billing platform to track metering events, manage customers, and generate invoices. It also supports managing products, payment links, and AI agent usage directly through MCP-compatible assista | |
| gemini-mac-computer-use-mcp be-young/gemini-mac-computer-use-mcp Enables AI agents to control macOS by capturing screenshots and performing mouse clicks, movement, dragging, text typing, hotkeys, and scrolling, with support for Gemini's normalized coordinate protocol and Retina display scaling. | |
| urfu-mcp be1pheg0r/urfu-mcp Enables users to retrieve Modeus schedules, iStudent grade/rating data, and eLearn course listings, content, and files through local MCP tools while using their university service login. | |
| guarded-computer-use-mcp be1st6666/guarded-computer-use-mcp Enables agentic control of Windows via MCP tools for screenshots, mouse, keyboard, UI Automation, OCR, windows, and clipboard, while risky actions require real-human approval through a policy-gated dialog with audit logging. | |
| MCP Memory Server beach55607-max/mcp-memory-server Provides long-term memory for AI coding agents, enabling them to remember, search, and organize information across sessions and platforms like Claude Code, ChatGPT, and Cursor. | |
| experimental-cardano-pool beacnlabs/experimental-cardano-pool-mcp Enables safe, local simulation of guarded block producer maintenance workflows, with tools for status inspection, plan generation, and approval/execution testing across three authority modes. | |
| Firecrawl MCP Server beaconchain-horizon/firecrawl-mcp-server Enables MCP-compatible AI agents to search, scrape, crawl, map, and interact with live web pages, returning clean, structured, agent-ready content. It also supports recurring page monitoring, autonomous deep research, and credit-usage check | |
| Beaconed MCP Server beaconed/beaconed-mcp Connect AI assistants to Beaconed so they can inspect product catalogs, generate SEO optimizations, manage settings, and safely publish or revert product content. | |
| mcp-oauth-test beaconfire-projects/mcp-oauth-test An MCP server that provides OIDC-protected access to QA MGT OpenAPI data, enabling tools for trainees, orders, products, customers, and recruitment operations. | |
| beakr beakrhub/beakr-cli Enables Claude Code and Codex assistants to research and read/write a team's knowledge base, manage projects and files, and use integrations through MCP tools. | |
| Pybricks RAG Assistant beallac/pybricks_mcp Enables beginner-friendly Python and Pybricks development support through RAG-powered tools that search official documentation, suggest code snippets, and provide version-aware guidance for LEGO robotics programming. | |
| sleeper-mcp bealmot/sleeper-mcp Enables reading Sleeper fantasy football rosters, matchups, standings, news, chat, and pick'em entries, with optional write actions for setting lineups, claiming waivers, and proposing trades. | |
| ffmpeg-mcp-server beambuilder/ffmpeg-mcp-server Enables video processing operations (speed adjustment, keyframe optimization, concatenation, and file management) using FFmpeg via Claude Desktop. | |
| mmd-mcp beammanp/mmd-mcp Enables Windows MCP clients to author MikuMikuDance scenes by controlling characters, cameras, lighting, physics, timeline editing, MME effect assignments, and AVI video output through natural language or scripted tool calls. | |
| QMT MCP Server beamof/qmt-mcp-server Wraps the miniQMT interface to enable AI assistants to query A-share market data, account information, and place/cancel orders. | |
| Beamswap MCP beamswap/beamswap-mcp Enables AI assistants to access Base wallet balances, token data, swap quotes and routes, price/balance alerts, and token distribution contracts through the Beamswap API. | |
| MCP Blogger Posting Server beanspapa/mcp-blogspot-posting Enables LLMs to automate Google Blogger content management by providing tools for single and batch post creation via the Blogger API. It supports secure OAuth2 authentication and allows for seamless blog integration through the Model Contex | |
| RAGJur MCP Server beanstechhub/ragjur-mcp Enables semantic search, outcome prediction, and legal document drafting across 67M+ Brazilian court decisions from 55 tribunals, with tools for jurimetric analysis and citation verification. | |
| Recharge Storefront API MCP Server bearded-giant/recharge-storefront-api-mcp A comprehensive Model Context Protocol (MCP) server that provides complete access to the Recharge Storefront API endpoints. Enables AI assistants to manage subscriptions, customers, orders, and billing through a standardized interface. | |
| spaceship-mcp bearded-giant/spaceship-mcp Enables natural-language management of Spaceship domains, DNS records, contacts, and marketplace listings through any MCP-compatible AI client. It adds TXT records without clobbering existing ones, restores records when a save fails, and ca | |
| Picus Security MCP Server beardedinfosec/picus-security-mcp Enables interaction with Picus Security's Breach & Attack Simulation API, allowing natural language queries for simulations, threat library searches, and agent management through MCP-compatible clients. | |
| codeJung-mcp beardfaceguy/codejung-mcp MCP server that exposes the self-hosted codeJung code-review service as tools, enabling PR and local directory reviews through any MCP client. | |
| opennews-mcp beare/opennews-mcp Crypto news aggregation MCP server with AI ratings, trading signals, and real-time updates. Enables searching, filtering, and subscribing to news from various sources. | |
| SketchupMCP bearnetwork-brnkc/sketchup-mcp Integration that connects Sketchup to Claude AI through the Model Context Protocol, allowing Claude to directly interact with and control Sketchup for prompt-assisted 3D modeling, scene creation, and manipulation. | |
| TradingView MCP Server bearspeed77/claude-tradingview Pulls Binance spot candle data, computes technical indicators (RSI, MACD, EMAs), and evaluates user-defined bias and risk rules without needing a TradingView session. | |
| @bearst/lucky-mcp-server bearstozawa/lucky-mcp-server Enables management of Lucky 3.0 via MCP, providing tools for reverse proxy, certificates, port forwarding, DDNS, and related modules using OpenToken authentication. | |
| Imagen bearthreat/nano-banana-openrouter-mcp Image generation | |
| FreeCAD Robust MCP Server beastknight933/freecad-mcp Enables AI assistants to interact with FreeCAD for 3D modeling, macros, and debugging via MCP. | |
| spec-assistant beastkp/spec-mcp Enables natural language queries on technical specifications and automated code compliance checks using local RAG with vector search, integrated via MCP. | |
| claude-todo beat-yt/claude-todo Enables Claude Code to maintain a persistent todo list stored in SQLite, with tools to list, search, add, update, complete, and delete todos across sessions. | |
| omnivox-mcp beat-yt/omnivox-mcp MCP server for the Omnivox platform used by Quebec CEGEPs. Enables AI agents to access course schedules, grades, MIO messages, evaluations, and documents from Omnivox-based institutions. | |
| BeatAPI Codex Plugin beatapi/beatapi-agent-plugin Enables creating and managing BeatAPI AI Music Video and Ecommerce Video workflows. Supports inspecting workflows, credits, usage, uploading files, creating tasks, polling tasks, and managing webhooks. | |
| tmux-bridge-mcp beatriceh4206/tmux-bridge-mcp A standalone MCP server that lets AI coding agents running in separate tmux panes read each other's output, send messages and keystrokes, and coordinate multi-agent workflows through standard MCP tool calls. It shells out directly to tmux, | |
| dev.augments/mcp beatricen1965/augments-mcp-server Enables MCP clients to fetch context-aware API signatures, prose documentation, and code examples for any npm package, along with version diffs, migration guides, error diagnosis, package comparison, and dependency scanning. | |
| Stock Trade MCP Server beatriz22092/stock-trade-finance-api Enables programmatic access to stock prices, financial news, forex data, fundamentals, dividends, and splits through MCP tools. | |
| msw-mcp beatriz4020/msw-mcp Enables AI assistants to dynamically add, update, and remove Mock Service Worker network mocks through MCP tools, without restarting or reloading the application. | |
| scrcpy-mcp beatriz4020/scrcpy-mcp Enables AI agents to visually perceive and directly control Android devices via ADB and screen-control tooling, including screenshots, taps, swipes, typing, app management, UI inspection, file transfer, shell commands, and audio/video strea |
33,351–33,400 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.