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 |
|---|---|
| artagon-vault-mcp artagon/artagon-wiki Read-only MCP server for querying an evidence-aware knowledge vault with temporal and provenance-aware data, supporting agent memory and semantic graph projections. | |
| ncm-fast-writer artapaher-max/ncm-code-doc Enables local generation of concise technical documentation and one-line docstrings from source code fragments through the Model Context Protocol, using non-autoregressive NCM inference exposed as the fast_ncm_redaction tool. | |
| zenmoney-mcp artarasov/zenmoney-mcp Enables AI clients to read and manage ZenMoney personal finance data: syncing, browsing accounts, categories, merchants and transactions, adding expenses, incomes and cross-currency transfers, and recategorizing or correcting existing trans | |
| Field Control MCP Server artarcondicionado/fieldcontrol-mcp Enables querying and creating clients, service orders, collaborators, service requests, equipment, and other resources from the Field Control API directly in conversations with Claude. | |
| scrapyard artboarding-hash/scrapyard Local MCP server for web search and page extraction, providing clean markdown from URLs, search results, site mapping, and research endpoints without API keys or accounts. | |
| agent-delegation-mcp artcar12/agent-delegation-mcp Enables Claude Code to delegate implementation tasks to Antigravity CLI and OpenCode, run them fully autonomously, and then review and gate the results. | |
| express-mcp artdaal/express-mcp Enables macOS agents to read eXpress chats and threads, search contacts, send messages and attachments, and download verified files through MCP, while a Keychain-backed session broker manages authentication. | |
| artefact-mcp-server artefactventures/artefact-mcp-server Revenue intelligence MCP server: RFM analysis, 14.5-point ICP scoring, pipeline health scoring. Embeds Artefact Formula methodology. HubSpot integration. | |
| Gemini CLI MCP Server artegy/gemini-cli-mcp Enables comprehensive codebase analysis using Google's Gemini AI through CLI integration. Provides architectural reviews and targeted code analysis with code2prompt integration for efficient context extraction. | |
| Amplemarket Knowledge Base MCP Server artem-amplemarket/amplemarket-pylon-mcp Enables access to Amplemarket's knowledge base through Pylon's API. Supports searching articles, retrieving full content, and browsing collections with built-in caching for improved performance. | |
| rn-device-mcp artem-pavlenko/rn-device-mcp Enables coding assistants to drive iOS Simulators and Android emulators or USB devices for React Native and Expo work, including taking screenshots, reading app and device logs, opening deep links, installing builds, and launching or relaun | |
| trello-mcp artem-pavlenko/trello-mcp Enables Claude Code and other MCP clients to read Trello boards, lists and cards—including checklists, comments, members and labels—directly from the editor. Users can tick or untick checklist items, post comments, move cards between lists, | |
| video-brief-mcp artem-pavlenko/video-brief-mcp Converts screen-recorded walkthrough videos into timestamped transcripts, extracted frames, scene-change anchors, and interleaved slices that pair each frame with the speech following it, so a coding assistant can read video feedback. All p | |
| docs-mcp artemartemov/docs-mcp A secure MCP server providing intelligent documentation search across multiple frameworks using ChromaDB vector storage, enabling semantic search and integration with AI tools. | |
| Bitrix24 MCP Server artemfilin1990/bitrix24-mcp-server1 Enables AI agents to interact with Bitrix24 CRM for managing contacts, deals, tasks, and leads via a comprehensive set of tools. It supports advanced features like sales team monitoring, performance analytics, and automated CRM searching. | |
| Yomio MCP artemgontar/yomio-mcp Connects MCP-compatible AI clients to a Yomio account through browser-based sign-in, using tokens kept in the operating system credential store. It exposes hosted read-only tools for the signed-in account, excluding Family Group members' re | |
| MCP Platform Service artemida1609/mcp-service A minimal Model Context Protocol (MCP) service for integration with external platforms. Provides CRUD operations, reference data fetching, and authentication capabilities. | |
| pi-femboy-mcp artemidagre/femboy-mcp It enables clients to manage a shared virtual companion state—outfits, mood, memories, achievements, toasts, and terminal presence—through reactive MCP resources, tools, and prompts. It also supports background mood decay, gated wardrobe un | |
| Artemis MCP Server artemis-xyz/artemis-mcp Enables interaction with the Artemis API to retrieve and analyze cryptocurrency data, including accessing metrics, generating formulas, and validating API connections. | |
| roku-dev-doc-mcp artemisaiev/roku-dev-doc-mcp Provides local, offline searchable access to Roku and BrightScript development documentation via MCP tools and resources, including full-text search, sectioned reading of large docs, and background syncing from the upstream repo. | |
| Cloudflare Playwright MCP Server artemisiavertus/playwright-mcp-own Enables AI assistants to control a browser for web automation tasks, including navigation, typing, clicking, and taking screenshots, deployable to Cloudflare Workers. | |
| notes-box artemki207775/my-mcp-server-kit Enables managing a local JSON notes file through five MCP tools: add, get, update, delete, and list notes, with atomic saves and a write lock. | |
| Azure Infrastructure MCP Server artemkozlenkov/azops-mcp An MCP server for managing Azure infrastructure from AI assistants, supporting subscriptions, VMs, storage, networking, identity, and more through natural language commands. | |
| aichallenge-mcp-kit artemkyslicyn/aichallenge-mcp-kit Enables users to attach child MCP servers, run sandboxed Python, and transfer large outputs via artifacts through one authenticated Streamable HTTP endpoint exposed by tunnel to a cloud chat client. | |
| aichallenge-rag artemkyslicyn/aichallenge-rag Enables indexing a folder of documents or uploaded files into a Qdrant vector store and retrieving relevant chunks with cosine similarity, metadata filters, and heuristic reranking. Exposes rag_stats, rag_search, and rag_index tools over HT | |
| Stand Pulse artemkyslicyn/stand-pulse Enables probing a live AI stand's health and latency, retrieving model Pareto and down-votes, and scheduling recurring digest summaries. | |
| trello-mcp artemnikov/trello-mcp Enables AI assistants to manage Trello boards, lists, cards, comments, checklists, labels, and members through natural language. | |
| shortcuts-mcp-server artemnovichkov/shortcuts-mcp-server Shortcuts + MCP = ♥️ | |
| Crypto MCP Server artemoalin28-afk/crypto_mcp_server_v2.0 Provides real-time and historical cryptocurrency market data using ccxt, with tools for ticker, OHLCV, and streaming updates. | |
| MCP Elicitation and Apps Demo artemreva-hub/otus.ai_for_dev.webinar14.mcp MCP server demonstrating elicitation for booking appointments and an interactive MCP App for viewing appointments with SQLite persistence. | |
| basic-react artemreva-hub/otus.dev-ai-agents.webinar7.mcp Provides a get-time tool with a linked React UI for displaying the current time. | |
| igaming-odds-mcp artemsoldatov/igaming-odds-mcp MCP server providing deterministic betting odds tools including conversions, margin, parlay pricing, settlement, and Kelly staking. | |
| Figma MCP PRO artemsvit/figma-mcp-pro Professional Model Context Protocol server that enables AI-optimized Figma design analysis and comprehensive design-to-code conversion through a structured 5-step workflow. | |
| S3 Uploader MCP Server artemu78/mcp-server-s3-uploader Enables file uploads to AWS S3 buckets with automatic MIME type detection. | |
| GRACE Orchestrator MCP artemyx-datascientist/grace_mcp MCP server orchestrating local multi-agent workflows with gated lifecycle, handoff events, and host-level continuation. | |
| mcp-3xui arteshokv/mcp-3xui Enables managing 3x-ui panels through their current API, including creating and updating clients across inbounds, monitoring online clients, and accessing panel features like nodes, routing, and backups via runtime-discovered API tools. | |
| Agent Scraper MCP artespraticas/scrape-agent-mcp Service name: Scrape Agent
Service base URL: https://scrapeagent.xyz
Website URL: https://scrapeagent.xyz
Email: your email
Category: Data
Description: Pay-per-use web scraping API built on x402. Extract clean text, links or HTML from any U | |
| kylin-sentinel-agent artforests/kylin-sentinel-agent MCP server for secure intelligent operations on Kylin OS, converting natural language requests into auditable, policy-controlled workflows. | |
| Documize MCP Server artfulhacker/documize-mcp-server A Model Context Protocol (MCP) server that provides seamless integration with the Documize API. This server enables AI assistants like Claude to interact with your Documize knowledge base - search documents, manage spaces, handle attachment | |
| obsidian-mcp artgustavobarros/obsidian-mcp Enables AI agents and WSL/Linux terminal users to connect to a Windows Obsidian vault via the Local REST API, supporting note reading, creation, updates, search, file listing, tags, and command execution. | |
| omni-memory arthaxgarage/omni-memory A fully-local AI memory system that saves notes, code, and terminal output to a vector database via Ollama and LanceDB, enabling context retrieval from terminal, API calls, or inside Claude Code. | |
| code-reviewer-mcp arthdh/code-reviewer-mcp An MCP server that performs automated code reviews by analyzing git diffs against configurable review standards with custom reviewer personas. | |
| DODO MCP arthittakun/dodo-mcp A local-first MCP server that enables AI-assisted coding through workspace-scoped tools for file reading/editing, command execution, jobs, Git, LSP, media, browser, and desktop workflows. It enforces OAuth, workspace ACL, trust policies, an | |
| school-record-validator-mcp arthong1/-school-record-validator-mcp Validates 2026 elementary school record narratives against official Korean MOE guidelines, detecting prohibited or review-required expressions, checking input lengths, and providing cited official sources via seven MCP tools. | |
| leboncoin-mcp arthur-c/mcp-leboncoin Enables AI assistants to search and consult Leboncoin classified ads through the MCP protocol, with tools for ad search, detail retrieval, user profiles, and category/region listings. | |
| stm32-rag-mcp arthur19940725/stm32-rag-mcp Provides read-only retrieval of STM32 datasheet and reference manual content with exact citations, page numbers, register details, and source hashes so Claude can answer questions or generate code from verified evidence. | |
| SerpApi MCP Server arthur72939/serpapi-mcp Enables querying Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and other engines for search results, real-time weather, and stock market data, returned as JSON or token-efficient Markdown. It also exposes per-engine parameter schemas as MC | |
| OpenAI MCP Server arthurcolle/openai-mcp A Model Context Protocol server implementation that enables connection between OpenAI APIs and MCP clients for coding assistance with features like CLI interaction, web API integration, and tool-based architecture. | |
| Substack MCP Server arthurcolle/substack-mcp Enables AI tools to programmatically manage Substack content, including creating drafts, publishing posts, and posting to Substack Notes. It supports image uploads, live blogging, and document formatting compatible with Substack's ProseMirr | |
| Helmo arthurcoulston/helmo A self-hosted work dashboard for AI agent teams, where agents create and manage tickets through MCP tools and humans review an awaiting-human queue backed by an append-only event log. Enables ticket lifecycle management and evidence-based p |
30,701–30,750 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.