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 |
|---|---|
| Brave Search MCP Server arben-adm/brave-mcp-search Facilitates integration of Brave Search functionalities with AI assistants through the Model Context Protocol, enabling web and local searches using the Brave Search API. | |
| Tavily Search MCP Agent arben-adm/tavily-mcp-search This MCP server performs multi-topic searches in business, news, finance, and politics using the Tavily API, providing high-quality sources and intelligent summaries. | |
| nofomo-mcp-server arbendemajxai/nofomo-mcp-server MCP server and SDK for AI agents to interact with NoFOMO News, enabling reading articles, chatting, rating, and commenting. | |
| MCP Hub arberrexhepi/mcpburst An Express server implementation of Model Context Protocol that allows websites to connect to LLMs through streamable HTTP and stdio transports, with a built-in chat UI for testing responses. | |
| strava-openapi-mcp arbodgad/strava-openapi-mcp Enables MCP clients to interact with the Strava REST API through tools generated from Strava's official Swagger spec, supporting OAuth, activity and athlete data retrieval, and configurable write/delete operations. | |
| ClaudeHopper arborist-ai/claudehopper AI-powered MCP server that enables Claude and other LLMs to interact directly with construction documents, drawings, and specifications through advanced RAG and hybrid search capabilities. | |
| Daimon arborithm/daimon A local daemon for macOS that gives any MCP-capable AI client eyes, hands, and a face — screen capture, accessibility tree, mouse/keyboard actions, and an overlay — with a built-in security ceiling. | |
| ComfyUI MCP Hub arborithmdev/comfyui-arbo-mcp-hub Give AI agents full control over your local ComfyUI by exposing 77 tools for workflow management, image generation, model handling, and real-time canvas control. | |
| PayPal MCP Server arbuthnot-eth/paypal-mcp A Model Context Protocol server that provides comprehensive integration with PayPal's APIs, enabling seamless interaction with payment processing, invoicing, subscription management, and business operations through a standardized interface. | |
| PayPal MCP Server arbuthnot-eth/paypal-mcp-defunct A server that provides integration with PayPal's APIs, enabling seamless interaction with payment processing, invoicing, subscription management, and business operations through a standardized interface. | |
| auto-news MCP server arbyazra123/auto-news Enables AI assistants to access and manage an Indonesian stock market news pipeline, including checking news status, running scraping, and reading reports. | |
| brain-mcp arc-labs-ai/brain-mcp Gives MCP clients a small remote Streamable HTTP tool surface for a Brain memory database, letting agents store facts, retrieve current-truth answers with evidence, delete memories, and check their effective identity. Each call is scoped by | |
| arc-mcp-hub arc-mcp/mcp-hub A thin, deterministic MCP hub for SAP BTP that routes connections to multiple SAP systems behind one login, preserving per-user identity. | |
| SAP WebGUI MCP arc-mcp/sap-webgui-mcp Enables MCP clients to perform administrator-approved, read-only SAP WebGUI lookups of DDIC table fields, data elements, domains, and displayed source over BTP principal propagation. Live reads are disabled by default and require each exact | |
| mcp-tools arc119226/mcp-tools A collection of simple, practical MCP servers that require zero configuration, enabling web search via DuckDuckGo (no API key needed) and management of Hexo blogs through AI. | |
| claude-room arc585/claude-room Enables multiple Claude Code sessions to join the same named room and exchange messages so they can sync context without manual copy-pasting. Supports same-machine file storage or remote HTTP relay transport, with a watcher that pushes new | |
| Librarian arcadeai-labs/agent-library Provides AI agents with persistent knowledge storage, enabling them to store, search, and retrieve text, documents, and files using semantic and keyword search via MCP tools. | |
| mcp-grad-party arcadeai-labs/mcp-grad-party A celebratory MCP server that provides information about the MCP spec graduation, including tools for trivia, toasts, and migration checklists. No authentication required. | |
| Safe Hands arcadeai-labs/safe-hands An MCP server that governs AI agent commands to physical robot arms, enforcing Asimov's Three Laws through Cedar authorization policies to prevent unsafe actions. | |
| Blueprint MCP arcadeai/blueprint-mcp Generates architecture diagrams, flowcharts, and sequence diagrams to visualize codebases, system architectures, and technical workflows using Nano Banana Pro. Integrates with Arcade's ecosystem to pull data from various sources and transfo | |
| utm-helper-mcp arcadeai/utm-helper-mcp MCP server for generating consistent UTM-tagged links based on an authoritative, version-controlled UTM specification. | |
| Arcaelas MCP arcaelas/mcp Provides AI-powered tools for image generation, text-to-speech conversion, background removal, and image upscaling through OpenAI and image processing APIs. | |
| ledger arcaeon-io/ledger Provides tamper-evident, hash-chained logging for MCP agents, enabling append, verification, and artefact-binding of action records. | |
| Samantha arcaman07/samantha_mcp MCP server that dynamically extracts and manages user memory from LLM conversations, enabling consistent personalization across different models. | |
| Wiki Arcana arcanada-one/wiki-arcana An open-source knowledge-space registry and API/MCP orchestration service for agents, providing relational space classification, hierarchical authorization, and engine-independent graph/vector ports. | |
| anycubic-slicer-next-control arcane-d7/anycubic-bridge-pluggin Enables secure local control of Anycubic Slicer Next and compatible printers, supporting slicing, 3MF/CAD operations, printer control, spool registry, and camera access through MCP tools. | |
| Freshdesk MCP Server arcanesk/freshdesk-mcp-server Provides a standard MCP interface for Freshdesk helpdesk operations, including ticket lifecycle management, draft/send replies and notes, contact lookup, and agent/group discovery. | |
| Local Eyes arcanum703/local-eyes Enables text-only and offline AI agents to see images through three MCP tools that read UI screenshots, extract verbatim text, and describe images or URLs, returning schema-validated JSON from Gemma 4 running locally via Ollama or through t | |
| MCP Server Whisper arcaputo3/mcp-server-whisper Enables advanced audio transcription, text-to-speech generation, and audio processing using OpenAI's Whisper and GPT-4o models with support for multiple audio formats, file management, and parallel processing. | |
| Arcate MCP Connect arcatehq/arcate-mcp Gives AI agents direct access to your Arcate product discovery workspace to read signals, browse roadmaps, and ingest new customer feedback. It enables users to search existing data and link signals to initiatives through natural language c | |
| remote-ssh-mcp arcdent/remote-ssh-mcp Enables AI agents to run commands, read and write files, inspect containers and services, and check system health on remote Linux hosts configured in ~/.ssh/config, while blocking dangerous operations by default. | |
| MaaMCP_CC arcelibs/maamcp_cc Enables Claude Code to directly control Android emulators or Windows windows for MaaFramework pipeline development, with features like screenshot with grid, template cropping, and real-time recognition testing. | |
| Todoist MCP Server arcforgelabs-archive/todoist-mcp Enables AI assistants to manage Todoist tasks, projects, and labels through natural language, with support for filters, priorities, and natural language dates. | |
| arcframe-mcp arcframe-ai/arcframe-mcp Generate videos, images, audio, and 3D models from any MCP-compatible AI agent — Claude, Cursor, ChatGPT, and more. | |
| MCP-PST-Server arch3rpro/mcp-pst-server Enables AI-assisted penetration testing by connecting MCP clients to a Windows API server for executing penetration testing tools like nmap, ffuf, nuclei, and other security tools. Allows AI agents to perform automated security assessments, | |
| YourHand archahmedzaki/yourhand-community Enables permission-aware control of authorized Windows devices via MCP tools, including device pairing, sharing, and guarded UI interaction. | |
| Archaic MCP Server archaic-ai/archaic-mcp Integrates Archaic's AI-powered architecture analysis with Claude Code, enabling interactive exploration of component connections, data flows, and system structure through natural language. | |
| financial-fraud-detection-mcp archana-gurimitkala/financial-fraud-detection-mcp An MCP server that enables AI-powered fraud detection on financial transactions using rule-based and statistical analysis tools, with sample data and Gradio dashboard. | |
| MCP_Based_AI_Assistant archana-m-11/mcp_based_ai_assistant Enables an AI assistant to dynamically discover and invoke MCP tools for document search, employee information lookup, and mathematical calculations, with human-in-the-loop approval for sensitive operations. | |
| Intern MCP archastro/intern-mcp Local stdio MCP server for working on Intern-hosted sites through guarded Git checkouts. It enables authentication, site preparation, testing, validation, and publishing via coding harnesses like Codex and Claude Code. | |
| @archawat/mcp-cloudflare archawat/mcp-cloudflare MCP server for managing Cloudflare DNS across multiple zones from a single API token, enabling bulk operations like toggling proxy, listing records, and batch updates. | |
| yinxiang-mcp archchuan/yinxiang-mcp 非官方印象笔记MCP服务器，支持笔记本、原生超级笔记、原始ENML和资源附件操作。 | |
| Arche arche-project/arche Serves an offline knowledge base — an aggregated corpus of reference works plus a RAG index over them and the user's own documents — to any local AI model over MCP. Enables offline assistants such as Open WebUI, OpenCode, or Jan to ground a | |
| cpp-coro-graph archerlin13/cpp-coro-graph Enables exploring a C++17 coroutine and device-domain call graph through MCP tools, providing symbol search, caller/callee queries, and neighborhood exploration of coroutine-aware codebases. | |
| Beijing Time MCP Server archerlliu/time-mcp Enables users to query and retrieve the current Beijing time in multiple formats including standard, ISO 8601, and Chinese formats. Provides timezone information and Unix timestamps for time-related operations. | |
| Liquipedia MCP archers007/liqmcp Provides MCP tools to query Liquipedia esports data (matches, teams, players, tournaments, placements, standings) via the Liquipedia v3 API and MediaWiki action API. | |
| Playwright Browser MCP App archestra-ai/browser-mcp-app Drives a real Chromium browser with Playwright, providing a live, clickable view of the page for the model to browse and the user to interact with. | |
| Telegram MCP Server archetyx/telegram-mcp-server Enables remote control of AI coding assistants (Claude Code/Codex) via Telegram, allowing you to manage long-running tasks, send commands, and receive notifications from anywhere. Supports unattended mode with smart polling for up to 7 days | |
| Tsumugi archfill/tsumugi An MCP-based memory layer for autonomous agents that provides observation, memory recall, and dreaming capabilities. It enables AI clients like Claude Code and Codex to store and search structured memories via a unified interface. | |
| civ6-mcp archi-max/jev-civ6 Enables LLM agents to play full games of Civilization VI by connecting to running game instances via the FireTuner debug interface, with 76 tools for units, cities, diplomacy, research, and turn management, plus narration of game state thro |
30,151–30,200 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.