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 |
|---|---|
| Component Library MCP Server alex-abrams711/component-library-mcp Provides AI assistants with access to private React component library documentation, props, and code examples through type-safe TypeScript integration. | |
| Aiqaramba alex-ai-eu/aiqaramba-mcp Browser-based QA testing for AI-built software. Agents open real browsers (via Selenium), navigate pages, fill forms, click buttons, and report findings. Two modes: targeted tests (30-90s) and full-site discovery scans (3-15min). | |
| RAG MCP Server alex-chanhc/rag-mcp-app A Model Context Protocol server that exposes Retrieval-Augmented Generation capabilities and a weather tool, allowing clients to interact with document knowledge bases and retrieve weather information. | |
| Office MCP Server alex-eng-ux/office-mcp-server MCP server for Microsoft Office file operations. Read, write, and create Excel, Word, and PowerPoint files directly from your local filesystem. | |
| Fortnox MCP alex-engvall/fortnox-mcp-test Enables users to connect AI assistants to Fortnox for reviewing financial results, costs and liquidity, managing receipts and bookkeeping proposals, preparing customer invoices, tracking payments, and working across multiple companies with | |
| MCP Filesystem Server alex-furrier/mcp-filesystem A Model Context Protocol server that provides secure and intelligent interaction with files and filesystems, offering smart context management and token-efficient operations for working with large files and complex directory structures. | |
| agentic-commerce alex-hahn/agentic-commerce An MCP server for LLM-driven commerce that lets agents shop in real storefronts while enforcing a trust layer to prevent financial loss. | |
| build-quality-mcp alex-jb/build-quality-agent Enables Claude-powered pre-push code review, blocking bad commits by analyzing diffs with Anthropic's models. | |
| shadow-perception-mcp alex-jb/shadow-perception-mcp An MCP server that scans data science artifacts (Jupyter notebooks, R scripts, code) and runs a 5-voice compliance council to detect issues like leakage and fairness, outputting signed verdicts. | |
| Reality Calendar MCP Server alex-kamikaze/mcp-reality-calendar-test-task Enables interaction with tool data stored in Google Drive Excel files through cached SQLite database. Provides access to tool information and descriptions with automatic background synchronization and OpenWebUI compatibility via OpenAI prox | |
| Boostcamp MCP Server alex-keyes/boostcamp-mcp Integrates with the Boostcamp fitness platform to provide access to training history, workout programs, custom exercises, and analytics through Claude. | |
| Boxes MCP alex-keyes/boxes-mcp Enables local-first search and analysis of Boxes home inventory exports and images, with tools for inventory queries, documentation audits, and signed webhook verification. | |
| gsc-mcp-connector alex-lang272/gsc-mcp-connector Enables natural-language querying of Google Search Console data, including search analytics, site properties, URL inspection, and sitemap status, through MCP-compatible clients like ChatGPT and Claude. | |
| proton-mail alex-pradas/mcp-proton-email A safe-by-default MCP server that gives Claude access to your Proton Mail through Proton Mail Bridge's localhost IMAP/SMTP. Sending requires human approval and destructive operations are limited. | |
| bug-ledger-mcp alex-r-a/bug-ledger-mcp A shared, concurrency-safe ledger for LLM code audits. It enables multiple agents to collaboratively report, verify, and resolve bugs with deduplication and hallucination resistance. | |
| Statcast MCP Server alex-rimerman/statcast-mcp Enables users to query MLB Statcast, FanGraphs, and Baseball Reference data using natural language through an AI assistant. It provides comprehensive tools for analyzing player performance, pitch-level data, season leaderboards, and team st | |
| Grinfi MCP Server alex-rise/grinfi-mcp-server Connects Claude to your Grinfi.io account, enabling management of contacts, automations, messages, and more through natural language. | |
| AI Switch MCP Server alex-shirazi1/aiswitchmcpserver Enables session continuity across AI coding assistants by preserving context and generating handoff markdown, allowing seamless switching between tools like Cursor, Claude Code, and Claude Desktop. | |
| 讯飞智文PPT生成服务MCP Server alex-smith-1234/zwppt-mcp An MCP-compatible server that uses iFlytek's large language model to generate PowerPoint presentations, offering template selection, outline creation, and PPT generation with features like automatic image insertion. | |
| skypilot-mcp alex000kim/skypilot-mcp MCP server for SkyPilot that lets LLMs manage cloud clusters, jobs, and storage through the Model Context Protocol. | |
| RepoImmune MCP Server alex0ai/repoimmune Enables querying a repository's resolved bug history through six read-only tools, allowing agents to check patches against past failures, retrieve regression tests, and replay behavior cases to prevent regressions. | |
| TraceFact MCP Server alex0ai/tracefact Read-only MCP server for TraceFact that lets agents list trace runs, fetch run details, and retrieve reliability reports from a local store. | |
| remnawave-mcp alex0nes/remnavawemcp Enables AI clients to drive the full Remnawave panel API, exposing one tool per method+path operation (users, nodes, hosts, subscriptions, inbound, bulk actions) plus search, describe, status, audit and metrics helpers. Read-only/read-write | |
| shm-mcp alex0nes/shmmcp Enables MCP clients to drive every admin and user operation of the SHM billing panel (148 generated tools plus search, describe, status and audit-tail helpers) through a single server. Includes read-only or read-write gating, deny rules for | |
| obsidian-secondbrain-mcp alex106/obcidian_mcp_manager_locals Turns a local Obsidian vault into a second brain with 27 MCP tools for capture, search, distillation, and review, all offline with no API keys or model calls. | |
| Up Banking MCP Server alex1092/up-bank-mcp-server Enables integration with Up Banking API to query account balances, transaction history, and spending categories. Supports filtering transactions by date, category, tags, and account type for comprehensive banking insights. | |
| capcut-mcp alex28042/capcut-mcp Creates and edits CapCut desktop drafts locally by writing project files, enabling timeline manipulation through MCP tools. | |
| Discord MCP Server alex2neo/discord-mcp Enables LLMs to read messages, discover channels, send messages, and monitor Discord communities using the Discord HTTP API. | |
| yahoo-finance-mcp alex2yang97/yahoo-finance-mcp Enables retrieval of comprehensive financial data from Yahoo Finance, including stock prices, company info, financial statements, options, and news, for stock analysis and market research. | |
| strapi-mcp alex2zimmermann-ux/strapi-mcp Connects any MCP-compatible AI assistant to Strapi CMS for content management, media handling, internationalization, and more through natural language. | |
| YouTube Transcript MCP Server alex2zimmermann-ux/yt-transcript-mcp Enables users to extract, search, and analyze YouTube video transcripts directly within MCP-compatible clients. It supports advanced features like time-chunked summaries, keyword searching with surrounding context, and batch processing for | |
| mindbody-mcp-server alex454-byte/mindbody-mcp-server Enables MCP clients to query Mindbody Public API v6 for schedules, attendance, sales, services, contracts, and client details, with PII masked before results reach the model and per-site rate pacing. Read-only by default, with writes and we | |
| Document Converter MCP Server alex5025/document-converter-mcp Converts between Markdown and Word documents using pandoc, with support for conversion options, pandoc installation check, and listing supported formats. | |
| html5-games-token-saver alex88ryabov/alex-apps-html5-games-token-saver Validates a built HTML5 game against CrazyGames portal rules — build checks, an emulated SDK v3 session, and frame/layout audits — returning dense JSON lists of failures, warnings and rules it could not exercise instead of screenshots or ad | |
| cc-channel-mem alexai-mcp/cc-channel-mem An MCP server and background daemon that captures Discord and Telegram conversations locally to provide persistent memory for Claude Code sessions. It enables hybrid search and automatic context injection of chat history to maintain continu | |
| K-Beauty MCP Server alexai-mcp/k-beauty-mcp Provides comprehensive Korean Beauty information through real-time web search, AI-powered skin analysis from photos, and curated knowledge of 58+ K-Beauty brands, ingredients, and personalized skincare routines. | |
| OpenCrab alexai-mcp/opencrab OpenCrab provides an MCP interface for the MetaOntology OS, enabling structured knowledge management across graph, vector, and document databases. It allows agents to perform hybrid searches, manage complex entity relationships, and conduct | |
| PlantOntology alexai-mcp/plantontology Enables querying a plant knowledge graph for companion planting, climate suitability, and landscape design recommendations via natural language. | |
| super-loop-mcp alexalexalex222/loop-factory-mcp-public A referee for self-improving AI agent loops that mines past sessions for effective workflows, improves them, and requires measured proof before declaring anything better or done, never stopping until the user stops it. | |
| Petamind MCP alexalexalex222/petamind-mcp Enables agentic coding workflows in Claude Code through a multi-candidate patch evaluation loop that generates code variants, validates builds, scores results with mandatory vision testing, and automatically selects the best implementation. | |
| super-loop-mcp alexalexalex222/super-loop-mcp A referee for self-improving AI agent loops that mines past sessions for working workflows, improves them, and never stops until you stop it. | |
| super-loop-mcp alexalexalex222/super-loop-mcp-merged A referee for self-improving AI agent loops that mines past sessions, improves workflows, and never stops until told. | |
| Product Pulse MCP Server alexalghisi/product-pulse Enables agents to explore a project's captured events and properties, then run trend, funnel and retention analyses and create or list saved insights. Tools are model-oriented, returning trimmed, budgeted results and actionable errors, with | |
| Wise Currency Converter MCP Server alexalok/wise-currency-converter-mcp Provides currency conversion using the Wise API, supporting real-time and historical rates with caching and cross-rate calculation. | |
| swisstransfer-mcp alexaltovate/swisstransfer-mcp Enables file sharing through SwissTransfer, allowing users to upload files, create shareable download links, check transfer status, and manage transfers with configurable expiration, password protection, and email notifications. | |
| CoinMarketCap MCP Server alexander-herranz/coinmarketcap-mcp Provides access to cryptocurrency market data, exchange information, and blockchain metrics through the CoinMarketCap API. Supports price quotes, historical data, trending tokens, global metrics, and DEX information across different subscri | |
| Telegram MCP Server alexander-surf/tg_mcp Read-only MCP server for Telegram channels. Provides access to posts, comments, reactions, and aggregated statistics via MTProto. | |
| Joplin Server MCP alexander-zhukov/joplin-server-mcp MCP server for Joplin Server that gives LLMs full access to notes, notebooks, tags, and attachments via the REST API. | |
| Ozon MCP alexander-zhukov/ozon-mcp Enables LLMs to read and manage a buyer's Ozon account data, including orders, purchase history, cart, favorites, product cards, and catalog search, using an authenticated session over the internal composer-api. | |
| Kollektiv | Your private LLM knowledgebase alexander-zuev/kollektiv-mcp Kollektiv |
26,101–26,150 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.