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 |
|---|---|
| Cicall basionwang-bot/cicall A terminal-independent MCP runtime for CLI agents, enabling orchestration of CLI processes via a background daemon and any MCP client. | |
| Grok CLI MCP Server basissetventures/grok-cli-mcp Provides seamless access to Grok AI models through the Model Context Protocol by wrapping the official Grok CLI, offering tools for general queries, multi-turn conversations, and code generation. | |
| local-env-mcp basit-devbe/local-mcp Exposes your local machine's filesystem, git, shell, network, databases, and system to any MCP-compatible LLM client over HTTP. | |
| vehicle-safety basit-khan-abdul/vehicle-safety-mcp Connects Claude to NHTSA vehicle safety data, enabling VIN decoding, recall checks, crash-test ratings, and consumer complaints via natural language. | |
| Figma Console MCP Server baskaran03528/figma_mcp Enables Claude to interact directly with Figma Desktop for creating UI components, managing design tokens, and auditing files through natural language. It establishes a live connection between the AI and the Figma API via a local server and | |
| Todoist for VoiceOS baskovicp/ultimate-todoist-mcp-for-voiceos Enables voice-driven task management by letting users view, select, complete, and reschedule tasks through natural-language commands and a native confirmation card with date parsing and batch handling. | |
| Harvest MCP Server baspenny/harvest-mcp Enables AI assistants to manage Harvest time tracking by verifying credentials, listing projects and tasks, retrieving and logging time entries, and starting/stopping/restarting timers. | |
| able-mcp bassdaddydevices/able-mcp An MCP server for parsing and analyzing Ableton Live .als project files offline, enabling queries about tempo, tracks, clips, and MIDI data through tools like als_summary and als_list_tracks. | |
| Darak MCP Server basseko/darak-mcp-server Remote MCP server for Saudi real estate data, giving AI assistants access to 65,000+ rental and sale property listings across 5 Saudi cities with market analytics and price trends. | |
| MCP Excel Server bassem-elsodany/mcp_excel_server An MCP server that enables AI agents to automate Excel file operations including workbook creation, worksheet management, and data manipulation. It provides a standardized interface for reading, writing, merging, and filtering cell ranges w | |
| MCP-Claude bassicalyadev/mcp-claude Enables chatting with AI directly in Roblox Studio to read, write, and modify scripts and instances, supporting multiple free AI providers. | |
| Adyen Checkout Utility Service MCP Server bassilkhilo-ag2/adyen-checkout-utility-service An MCP (Multi-Agent Conversation Protocol) Server that enables interaction with Adyen's Checkout Utility Service API through natural language, auto-generated using AG2's MCP builder. | |
| deck bassotov/deck Enables agents to create, read, and edit slide decks as plain markdown files, with support for drawing annotations, and handles deck management through MCP tools. | |
| local-memory-mcp basst85/local-memory-mcp A local MCP server that provides semantic memory storage and retrieval for coding and AI agents, enabling durable context across chat sessions. | |
| MCP Zephyr Scale Cloud Server basterboy/mcp-zephyr-scale-cloud Enables AI assistants to interact with Zephyr Scale Cloud for test management, including test cases, cycles, plans, folders, priorities, and statuses via the MCP protocol. | |
| Delphi Build MCP Server basti-fantasti/delphi-build-mcp-server Enables AI coding agents to compile Delphi projects programmatically by parsing .dproj files, executing the Delphi compiler, and returning structured error results with multi-language support and automatic configuration generation from IDE | |
| Deep Code Reasoning MCP Server bastiaan17655/deep-code-reasoning-mcp Enables Claude Code to escalate complex coding problems to Google's Gemini AI for large-context execution tracing, cross-system impact analysis, performance diagnostics, hypothesis testing, and iterative AI-to-AI debugging conversations. | |
| mcp-it-ops bastiaan365/mcp-it-ops Exposes homelab and IT-ops tools to Claude, including system health monitoring, Grafana alert states, Docker container status, Loki logs, SMART disk health, and more. | |
| clinicaltrialsgov-mcp-server bastiaan531/clinicaltrialsgov-mcp-server Enables searching ClinicalTrials.gov studies, retrieving full study records and posted results, discovering valid API fields and values, and matching patient demographics to candidate recruiting trials. Runs over STDIO or Streamable HTTP ag | |
| Train in Silence bastiaanerdogan9458/train-in-silence It enables users to describe an LLM fine-tuning workload once and automatically estimates required VRAM/FLOPs, compares live GPU pricing across cloud providers, and returns ranked cheapest, fastest, or balanced hardware recommendations. | |
| minimax-mcp-js bastiaang06/minimax-mcp-js Enables MCP-compatible clients to generate images and videos, convert text to speech, clone voices, and design custom voices through MiniMax APIs. It supports dynamic configuration and multiple transport modes for local or cloud deployment. | |
| Blender Open MCP bastiaanmorris/blender-open-mcp Enables AI agents to control a live Blender session via MCP tools for scene and object operations, rendering, code execution, and PolyHaven asset management. It supports provider-agnostic LLM backends that can be configured at startup or sw | |
| Rohlik MCP Server bastian32733/rohlik-mcp Enables AI assistants to search grocery products, manage shopping carts, access account and order information, and get personalized shopping suggestions across multiple Rohlik Group grocery platforms. | |
| io.github.Hylouis233/bibverify bastian34698/bibverify Enables AI assistants and researchers to verify bibliographic existence and metadata consistency across multiple sources, perform identifier-first lookups, and produce explainable, non-destructive BibTeX checks. | |
| Zettelkasten MCP Server bastiankrol5493/zettelkasten-mcp It enables users to create, link, explore, and synthesize atomic notes through MCP-compatible clients such as Claude. It supports tags, semantic link types, search, and a dual Markdown/SQLite storage-and-indexing architecture. | |
| routeforge bastianmr/routeforge-core Enables MCP-compatible AI agents to discover and invoke provider skills with automatic multi-account API key rotation, encrypted key storage, and usage monitoring. | |
| Frappe MCP bastiant13752/mcp Enables applications built on the Frappe Framework to serve MCP tools over Streamable HTTP, letting LLM clients call registered Python functions through a Werkzeug-compatible endpoint. | |
| apple-mail-mcp bastianzim/apple-mail-mcp A read-only MCP server for Apple Mail on macOS that enables searching and reading emails directly from the local SQLite database, with fast SQL-level filtering and pagination. | |
| auto-suggest bastidood/auto-suggest-mcp-prototype This MCP server exposes a recommend_skills tool that a UserPromptSubmit hook calls to inject relevant context into the harness before a prompt is processed. It surfaces matching external skill listings only when a suggestion meets a confide | |
| Gmail MCP Server bastienchabal/gmail-mcp Enables intelligent integration with Gmail and Google Calendar for context-aware email analysis, advanced searching, and personalized response drafting. It supports natural language interactions for managing communication history, detecting | |
| copilot-rag bastlam/copilotrag Enables GitHub Copilot Chat to semantically search locally indexed source code, documentation, and project statistics from reference projects through a fully local vector store. This lets Copilot find existing implementations and convention | |
| Crowdin MCP Server bastlast/crowdinmcp Enables AI assistants to manage Crowdin translation projects with tools for listing projects, files, source strings, translations, and performing bulk search-and-replace operations. | |
| ai-workers-mcp basttran/ai-workers-mcp Routes commodity NLP tasks like summarization and translation to free-tier LLMs, saving Claude tokens for complex work. | |
| MCP Audio Server batchlion/mcp-audio-server Enables text-to-speech conversion with smart language detection (using Google TTS for Chinese) and audio file playback with playback controls for Claude Desktop. | |
| CodePilot MCP bathinanna/codepilot_mcp Enables automation of workflows across GitHub, Notion, and Google Calendar with AI-powered task execution, personalized agent memory, and Slack integration for seamless team coordination and project management. | |
| weather-chat-mcp bati3702/weather-chat-mcp Enables LLMs to fetch Israeli weather forecasts by controlling a real browser via Playwright, simulating human interactions like typing and clicking on a weather website. | |
| MCP NFS-e batilieri/mcp_nfs Enables searching, downloading, and querying Brazilian electronic service invoices (NFS-e) through ISSWeb/Fiorilli municipal portals, including XML and PDF retrieval, access-key and CNPJ lookups, and multi-client configuration. | |
| scandomain-mcp batman0506/scandomain-mcp MCP server that enables AI agents to search domain, IP, port, service, title, ICP, server header, and component assets via the SCANDOMAIN API using Quake-style DSL queries. | |
| tinkoff-wealth-mcp batonec/tinkoff-wealth-mcp Enables personal AI-driven portfolio analysis and management for Tinkoff Investments through natural language chat, providing risk assessment, goal tracking, and market-aware recommendations in read-only mode. | |
| @batontasks/mcp batontasks/mcp MCP server for the Baton task tracker, enabling AI agents to manage tasks, process inbox events, and collaborate with humans via natural language. Wraps the Baton REST API with 12 tools over stdio. | |
| Alexa+ MCP batoolzehra320/flashcard-coach Turns natural-language smart-home commands into real tool calls, using Agent Skills loaded on demand over MCP Streamable HTTP. | |
| morgen-mcp batoorsayed/morgen-mcp Enables AI clients to fetch and list calendar events from Morgen, supporting end-of-day diary generation by providing schedule data. | |
| @jrmc/adonis-mcp batosai/adonis-mcp Enables AI clients to interact with AdonisJS applications through tools, resources, and prompts. Integrates authentication and authorization seamlessly. | |
| Adonis MCP Documentation Server batosai/adonis-mcp-docs MCP server to access and search adonis-mcp documentation files from GitHub, with tools for listing, searching, and extracting code examples. | |
| opsagent batpepe/ai-automation-lab A read-only MCP server that exposes Kubernetes cluster telemetry tools (pods, events, logs, metrics, ArgoCD syncs) with automatic redaction for incident triage and hypothesis ranking. | |
| SET-MCP batprem/set-mcp Provides access to the Securities Exchange of Thailand (SET) to retrieve comprehensive financial statements for listed companies. It enables AI agents to query income statements, balance sheets, and cash flow statements with historical data | |
| Squidbrake batrapulkit/squidbrake Enables AI agents and MCP clients to route every tool call through configurable rules that allow, block, or hold risky actions for human approval, while recording decisions in a tamper-evident audit trail. | |
| email-mcp-pro batsama/email-mcp-pro Enables sending, listing, and reading email messages via IMAP/POP3 with support for multiple providers, including NetEase, QQ, Gmail, and Outlook. | |
| Kairos Codex MCP Server batson-j/kairos_codex_mcp_server A Model Context Protocol server providing standardized access to Bible data resources, allowing LLMs to query various Bible translations, verses, and chapters. | |
| Taproom batteryshark/taproom Discovers and manages portable agent capabilities (skills and MCP servers) from configurable collections, providing search, inspection, and local installation via CLI and MCP tools. |
33,151–33,200 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.