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 |
|---|---|
| radar-papers-mcp fabianofilho/radar-papers-mcp Monitors PubMed and medRxiv for configurable research topics, summarizes papers using a local LLM, and stores deduplicated results in a local database. | |
| revisor-notas fabianofilho/revisor-notas-mcp Enables validation of clinical notes in SOAP format, checking required fields and semantic coherence using a local LLM, all processed locally with no data leaving the machine. | |
| Universal Firefly III AI Bridge fabianonetto/mcp-server-firefly-iii Provides comprehensive AI-agnostic access to all Firefly III personal finance features via 66 tools, enabling natural language management of accounts, transactions, budgets, and more. | |
| Azul Logistica MCP fabianoomura/azul-logistica Integrates Azul Cargo Express logistics operations with MCP clients like Shopify and TOTVS Moda, enabling freight quotes, tracking, CTe downloads, remittance issuance/cancellation, and invoice queries through the Azul API using secure authe | |
| Jadlog MCP fabianoomura/jadlog-mcp MCP server that integrates with the Jadlog logistics API, enabling shipping order creation and cancellation, freight simulation, tracking queries, CT-e XML retrieval, pick-up/drop-off point lookup, QR code generation, and TOTVS Moda integra | |
| Pagar.me MCP Server fabianoomura/pagarme-mcp MCP server that integrates Pagar.me v5 and Shopify to provide financial insights such as receivables, cash flow, order data, reconciliation, and refunds through natural language queries. | |
| AbletonMCP fabiantinkl/abletonmcp A powerful MCP server that enables Claude Desktop to control Ableton Live for automated music production, specializing in techno and industrial music generation. | |
| Google Search MCP Server fabien-desablens/google-search-mcp An MCP server that provides Google Search functionality with automatic API key rotation and intelligent quota management, enabling natural language search queries with advanced filtering options. | |
| MCP Webpage Timestamps fabien-desablens/mcp-webpage-timestamps A Model Context Protocol server that extracts webpage creation, modification, and publication timestamps from various sources including HTML meta tags, HTTP headers, and structured data. | |
| LearningSuite MCP Server fabienbutz/learningsuite-mcp A Model Context Protocol (MCP) server that provides tools for interacting with the LearningSuite API, enabling AI assistants to manage members, courses, groups, bundles, hubs, and community features. | |
| ansible-galaxy-mcp fabiendupont/mcp-ansible-galaxy An MCP server that lets AI agents discover Ansible Galaxy collection input/output contracts, including module arguments, return values, and role facts, to help generate accurate playbooks. | |
| MCP Gateway fabienfrfr/mcp-gateway A generic MCP gateway that exposes any HTTP-based SQL portal as LLM-friendly MCP tools and standard REST endpoints, serving both human users and AI agents simultaneously. | |
| LED Display Server fabienhamot/mcp_mqtt_server MCP server for controlling LED displays via MQTT. It enables AI agents to list devices and send text, images, colors, or clear commands with authentication and permission checks. | |
| Onboarding MCP Server fabimelo/onboarding-mcp A local-first MCP server that enables AI coding assistants to map codebases, transcribe onboarding videos with keyframe screenshots, and maintain structured Obsidian knowledge vaults directly from IDE chat. | |
| web-search-mcp fabio-barboza/web_search_mcp MCP server that searches the web, reads pages, and returns concise summaries with cited sources via the research_web and read_url tools. | |
| Claude Telegram Supercharged fabio79910/claude-telegram-supercharged Enables running Claude Code continuously from Telegram, with two-way voice notes, memory that survives restarts, scheduled reminders and calendar access, and live visibility into every tool call as it happens. | |
| mem0-mcp-selfhosted fabiob933/mem0-mcp-selfhosted Enables Claude Code to persistently add, search, update, and delete memories across sessions, backed by self-hosted Qdrant vector storage plus optional Neo4j knowledge-graph entity and relationship exploration using local Ollama embeddings. | |
| mcp-adzuna fabioba/mcp-adzuna MCP server exposing Adzuna's job search and salary analytics APIs as tools, including job search, category listing, salary histograms, top companies, regional data, historical salary data, and API version checking. | |
| youtube-mcp-tools fabioc-aloha/youtube-mcp-tools Evidence-first YouTube research server enabling search, transcript citation, video analysis, flashcards, and collateral generation for MCP hosts and VS Code. | |
| Discord MCP fabiocg01/discordmcp Enables MCP clients such as Claude, Cursor, or Codex to build and manage Discord servers end to end — creating channels, roles, permission overwrites, threads, webhooks, events, and messages, plus whole-server blueprints applied idempotentl | |
| contractmesh fabiodepin/contractmesh ContractMesh is an MCP server that provides a trust-aware engineering knowledge layer, enabling agents to retrieve confirmed decisions, constraints, and known risks with provenance. It grounds AI changes in explicit engineering knowledge ra | |
| @gnaws/mcp fabiodominio/gnaws-mcp Enables AI agents to scan AWS accounts, build resource relationship graphs, detect unused resources, and export data via MCP tools. | |
| Natal IBGE MCP Server fabioff30/mcp-ibge-natal Provides AI models with direct access to official IBGE Censo 2022 and PIB data for Natal (RN), including neighborhood-level demographics, sanitation, and comparisons. | |
| Shell MCP Server fabiogomez/mcpsevers Enables execution of shell commands through a terminal tool and provides access to a custom readme file from OneDrive Desktop or local Desktop directory. | |
| MCP Vista CRM Loft fabiohsan-dev/mcp-vista-loft Enterprise-level MCP server integrating with Vista CRM (Loft Edition) for real estate operations, offering 40+ tools for property search, pipeline management, lead capture, and agenda control. | |
| GenImgMCP fabiojbg/genimgmcp Enables local image generation and editing via OpenRouter models, saving files directly to the project and returning paths and metadata for coding agents. | |
| mem0-mcp-selfhosted fabiolenine/mcp_deepmen0 Self-hosted mem0 MCP server for Claude Code that adds durable async ingestion, document support, and reranking, enabling persistent memory management with Qdrant, Neo4j, and Ollama. | |
| nuzo-memory fabionfsc/nuzo-memory Local-first, auditable memory for AI agents. Provides durable context for MCP hosts with SQLite storage, CLI, and MCP tools for memory management. | |
| Webflow MCP Server fabiopham886/mcp-server Enables AI agents to interact with Webflow's Data API and Designer, supporting site content management, design updates, and OAuth or API-token authentication through natural language. | |
| MySQL MCP Server (Optimized) fabiovige/mcp-mysql-simple An MCP server for MySQL that enables users to execute SQL queries, inspect table structures, and explore database schemas through a clean, SOLID-based architecture. It includes built-in security validations to protect against dangerous oper | |
| the-i18n-mcp fabkho/the-i18n-kit MCP server for managing i18n translation files — gives your AI agent full control over your app's translations without dumping entire locale files into context. | |
| earth-data-mcp fablackner/earth-data-mcp An MCP server that makes live Earth data usable by AI agents. Its initial data sources cover natural hazards: earthquakes from the USGS FDSN event catalog and volcanic activity from the Smithsonian Global Volcanism Program. | |
| AI Conversation Logger fablefang/ai-conversation-logger-mcp Enables AI assistants to automatically log and manage conversation history with developers in structured markdown format. Provides powerful search and context suggestions to help AI understand project history and maintain continuity across | |
| KiCadMCP faboai/kicadmcp Enables inspection of existing KiCad boards and schematics — layer/component/net reading, native DRC and ERC, XML netlist generation, Gerber/Excellon export, and GND continuity auditing — plus running LTspice or ngspice simulations with RAW | |
| Acopia faborubio/acopia MCP server for querying and simulating the dispatch plan of a solar PV + battery system in the Chilean electricity market, using deterministic optimization and optional DRL. | |
| fabplane fabplane/fabplane-cli A stdio MCP server that lets agents list organizations, search and edit shopping carts (BOMs) with per-item purchase destinations, and search, add or adjust parts inventory, optionally gaining access to the local desktop app's status, proje | |
| Fizzy MCP Server fabric-pro/fizzy-mcp Enables AI assistants to interact with Fizzy project management boards, cards, and tasks through natural language. It provides full API coverage for managing project workflows, comments, and notifications across multiple transport protocols | |
| FABRIC Infrastructure Metrics MCP Server fabric-testbed/fabric_metrics_mcp Enables LLM clients to ask natural-language questions about FABRIC Testbed infrastructure metrics, with responses grounded in fixed Grafana/PromQL queries for node, switch, and link metrics. | |
| mflib Slice Metrics MCP Server fabric-testbed/mflib_portal_mcp Enables LLM clients to ask natural-language questions about nodes in a FABRIC slice, returning grounded answers from the Node Exporter Full dashboard's fixed PromQL queries. | |
| Expeditto fabrica-de-inovacao/expeditto Enables AI assistants to prepare the SUAP IFMA Work Individual Report (RIT) by gathering receipts, organizing them by semester and topic, drafting the narratives, and leaving the report as a saved draft for review, without ever submitting i | |
| Fabkit MCP Server fabricatorsltd/fabkit-mcp Provides AI agents with comprehensive documentation and code patterns for the Fabkit Svelte 5 UI library. It enables users to search for components, icons, and theming APIs to ensure accurate implementation and prevent hallucinations. | |
| librascript-mcp fabricioartur/librascript-mcp Enables AI assistants to translate Portuguese text into LIBRAS glosses and scripts using VLibras official APIs, supporting content auditing, validation, and batch translation. | |
| MCP SQL Server fabriciofs/mcp-postgres An MCP server for Microsoft SQL Server integration that enables users to query, monitor, and analyze databases directly through Claude. It supports schema exploration, performance analysis, and optional write operations via natural language | |
| MCP SQL Server fabriciofs/mcp-sql-server A Model Context Protocol server that enables Claude to query, monitor, and analyze SQL Server databases, with support for schema exploration, performance analysis, and optional write operations. | |
| pr-ready-mcp fabriciopirini/pr-ready-mcp Enables coding agents to verify whether a GitHub pull request is genuinely ready by checking draft state, conflicts, check results on the head commit, review requirements, merge queue status, and expected commit, returning a verdict with re | |
| fabrikka fabrikkadotxyz/core Enables teams and their existing AI agents to join shared live sessions over MCP, where participants can watch an agent work, redirect it, and hand off tasks while each agent keeps its own credentials and machine. | |
| Agent Office MCP Server fabrimat/lesscubicles Enables coding agents and humans to join temporary in-memory rooms and exchange messages through an MCP endpoint, with browser access via REST and WebSocket. | |
| UTN-MCP fabrizio9898/tecnicatura-mcp Enables AI agents to query and interact with a virtual classroom for a video game development program, covering courses, forums, assignments, grades, and files, and allowing write actions such as posting, submitting assignments, sending mes | |
| SCD MCP Docs fabrizioid/sc-mcp-google-workspace Enables MCP clients like Claude Desktop and Cursor to interact with Google Docs, Sheets, and Drive, providing tools for reading, writing, formatting documents, managing spreadsheets, and searching Drive files. | |
| l0-memory fabriziosalmi/l0-memory Minimal long-term memory MCP server for AI assistants backed by SQLite FTS5 full-text search, optional hybrid vector retrieval, scoped memory graphs, and VSCode extension. |
49,351–49,400 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.