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 |
|---|---|
| cwe-search_mcp bilel-eljaamii/cwe-search_mcp Enables querying MITRE's Common Weakness Enumeration database for vulnerability information, supporting CWE lookup, search, taxonomy navigation, and relationship mapping through MCP. | |
| RevolutX MCP Server bilel-eljaamii/revolutx-mcp Provides AI agents with tools to interact with the Revolut X crypto exchange for order management, market data, portfolio analysis, and more via the Model Context Protocol. | |
| RAG Banking Regulatory MCP Server bilelammouri/rag-banking-regulatory-agent Enables querying banking regulatory documents via a RAG pipeline with hybrid search and multiple LLM backends. | |
| Open-Meteo MCP Server bilelselmiai2026/open-meteo-mcp Provides weather information through MCP tools, including city search, current weather, forecasts, comparisons, and warmest day identification, using the Open-Meteo API. | |
| MCP Flow bilgili/mcpflow Enables agents to reach many child MCP servers through a single gateway endpoint, where each child's tools are published as namespaced tools behind one bearer token. It also provides an admin web UI, REST API, and built-in tools for adding, | |
| skill-store bilgili/skill-store Enables persistent skill management over the Model Context Protocol, allowing agents to use, write, list, and migrate skills backed by directory, Git, or S3 stores. | |
| Dress Rehearsal bilgin-kocak/dress-rehearsal Provides a safe paper-trading twin of the Binance Agent OS MCP API so agents can be rehearsed, scored, gated for go-live, and shadow-compared against live calls without using real funds. | |
| CrawMcp bilginerdem/craw-mcp Self-hosted MCP server for web crawling that bypasses anti-bot walls and JS challenges, using RabbitMQ, MinIO, and Redis for asynchronous content handling with automatic cleanup. | |
| Model Context Protocol Server bilgisayarkavramlari/mcp-server A stateful gateway server for AI applications that solves the memory limitations of Large Language Models by maintaining separate conversation contexts for each user. | |
| Web Accessibility MCP Server bilhasry-deriv/mcp-web-a11y Provides web accessibility analysis and color blindness simulation using axe-core and Puppeteer, enabling detailed accessibility checks and visual simulations based on WCAG guidelines. | |
| openmud bilhokista/openmud Enables AI agents to discover companies showing buying signals, enrich them with public homepage data, score them against custom rules, and draft review-ready briefs. | |
| bh-pdfdoc-reader bilhosdev/bh-pdfdoc-reader Enables AI-powered IDEs to read PDF and DOCX files directly, supporting structured output in Markdown, JSON, or plain text. | |
| MediaSearch bili14/mediasearch Enables AI agents to perform local semantic searches over a user's own images and videos using natural-language queries, with tools for incremental indexing, status checks, and scope management while keeping data and inference on the local | |
| Proof Publisher MCP biliman1-work/proof-publisher-mcp This MCP server publishes commit-bound proof summaries to a specified HTTPS webhook, featuring fail-closed writes and a clear authority boundary for safe external actions. | |
| mcp-sqlserver bilims/mcp-sqlserver A Model Context Protocol (MCP) server that enables AI agents to interact with Microsoft SQL Server databases through secure, intelligent database operations. This server provides comprehensive CRUD capabilities, schema introspection, stored | |
| gwanggo-mcp bill-950207/gwanggo-mcp Enables AI agents to generate images and videos using 30+ models (Seedream, Sora, Veo, etc.) via the Gwanggo API. Provides tools for model listing, image/video generation, task checking, and credit balance. | |
| File Server MCP bill-gtl-group/mcp-file-server Enables accessing and managing files from configured folders with filtering and size limits, allowing listing, reading, and searching files via MCP tools and resources. | |
| Claude Code CLI MCP Server bill-kopp-ai-dev/claude-code-cli-mcp Provides a secure interface to run Anthropic's Claude Code CLI as an MCP server, enabling task execution, persistent memory, and integration with MCP-enabled IDEs. | |
| Percival Deep Research bill-kopp-ai-dev/percival-deep-research An MCP server that provides autonomous, multi-source web research capabilities for AI agents. It delivers comprehensive, validated information through deep research tools while maintaining security and compatibility with various LLM provide | |
| Percival Ubuntu bill-kopp-ai-dev/percival-ubuntu-mcp Percival Ubuntu is a security-focused MCP server for safe Ubuntu operations, optimized for the Nanobot agent. It enables file management and command execution under strict security policies. | |
| Supabase MCP Server bill143/supabase-mcp Connects Supabase projects to AI assistants, enabling them to manage database tables, execute SQL queries, and deploy Edge Functions through natural language. It provides a comprehensive suite of tools for project administration, including | |
| trip-mcp bill666666/trip-mcp Enables locally running MCP clients to log into Ctrip and Trip.com/Trip Moments, query notes, prepare image-text posts, and submit them through browser automation without a central server. It also supports destination lookup, preview screen | |
| URL Text Fetcher MCP Server billallison/brsearch-mcp-server Enables AI models to fetch text content from URLs, extract links from web pages, and search the web using Brave Search with automatic content retrieval from top results. Provides comprehensive web scraping and search capabilities with robus | |
| Code Explainer MCP billduke13/code-explainer-mcp A Cloudflare Worker that analyzes source code to provide comprehensive explanations including architecture diagrams, core functionality analysis, and component breakdowns across multiple programming languages. | |
| Catalyst MCP Server billebel/catalyst_mcp An MCP server that loads and serves Knowledge Packs to connect AI assistants with business systems like databases, DevOps tools, and APIs. | |
| mcp-bambu billford/mcp-bambu Enables Claude Code to see and drive Bambu Lab 3D printers over the local network via MQTT, providing status, file management, print control, filament, maintenance, and diagnosis without any cloud dependency. | |
| X Browser MCP billioncodes001/x-browser-mcp Enables browser-based Twitter/X research and account workflows through a signed-in browser, supporting search, timeline/profile reads, saved searches, snapshot exports, and prepared account actions without requiring an X developer API key. | |
| whamlink-mcp billkinddev/whamlink-mcp Lets MCP clients publish a single file to a permanent, shareable link via whamlink. Supports tools for managing links, including registration, publishing, listing, updating access, replacing content, and deleting links. | |
| jira-mcp-server billnobill/jira-mcp-server Enables AI agents to manage Jira projects and issues using natural language, including creating, updating, searching issues, managing sprints, and more via the Jira API. | |
| Apple Mail Summary MCP billshiyaozhang/apple-mail-summary-mcp Enables AI agents to fetch emails from local Apple Mail accounts and mailboxes, and parse Google Scholar alert emails to extract paper titles and links. | |
| sub2api-imagegen-mcp billsjc/sub2api-imagegen-mcp Enables AI assistants to generate and edit images using a Sub2API API key, with local file saving and support for reference images. | |
| Python Simple MCP Weather Server billumi/mcp-sample A tutorial-based MCP server that fetches real-time weather data from the OpenWeatherMap API for specified locations. It serves as a practical example for implementing the Model Context Protocol using Python and the FastMCP library. | |
| DIYworld MCP billxfan/diyworld-mcp Enables MCP-capable agents to connect to a persistent shared-world service, discover people and worlds, and participate via natural-language actions. | |
| React MCP SPA billy-yoyo/mcpreactspa A React single-page application served as an MCP server that renders different UI pages based on the invoked tool name from the host context. It enables embedding interactive React components directly within MCP clients like Claude Desktop | |
| plan-mode-mcp billy12151/plan-mode-mcp Cross-platform MCP server providing Claude Code-style plan mode via four tools (enter_plan_mode, get_plan_mode_standards, todo_write, exit_plan_mode) with soft guidance through SKILL.md. | |
| Xiaohongshu MCP Server billyangbc/xiaohongshu-mcp-nodejs Enables enterprise-grade multi-account management and automated operations for Xiaohongshu (Little Red Book) platform. Supports content searching, publishing, user data collection, and anti-detection features through browser automation with | |
| WellSaid Claude Connector billyatminyawns/wellsaid-connector An MCP server that wraps the WellSaid Labs text-to-speech API, enabling Claude to generate lifelike voiceovers with voice selection, prosody control, and caption support directly from text. | |
| local-apple-data billybunn/local-apple-data MCP server for privacy-gated local Apple data access including Mail, Messages, Notes, Calendar, Contacts, Photos, Reminders, Voice Memos, and iCloud Drive. | |
| mcp-evolution billyfranklim1/mcp-evolution MCP server that integrates Evolution API to enable WhatsApp messaging, chat management, group operations, and instance control through natural language tools. | |
| tggroupMCP billyhargroveofficial/tggroupmcp Enables interaction with Telegram groups via MTProto, including message retrieval, sending, and semantic search with RAG support. | |
| Foxxy Bridge billyjbryant/mcp-foxxy-bridge MCP Foxxy Bridge is a one-to-many proxy for the Model Context Protocol (MCP). It lets you aggregate and route requests to multiple MCP servers through a single endpoint, so you can centralize configuration for all your MCP servers. | |
| aptabase-mcp billylo1/aptabase-mcp Unofficial MCP server that lets AI agents query Aptabase analytics using cookie-authenticated dashboard endpoints, providing tools for metrics, events, and sessions. | |
| alpine-mcp billynoyes/alpine-mcp Provides the complete Alpine.js documentation as resources, enabling AI assistants to accurately reference directives, magics, globals, and plugins. | |
| DaVinci-Resolve-MCP billyraz/davinci-mcp A stdio MCP server for DaVinci Resolve on macOS, enabling project control, timeline navigation, frame capture, grade application, and validation through the official Resolve scripting API. | |
| trust-mcp billythemanbot/trust-mcp MCP server that enables AI agents to verify each other's trust scores, register, submit reviews, and find trusted agents before transacting. | |
| DREAMVFIA Windows MCP billyu2025/win-mcp A lean local Windows automation server providing tools for mouse and keyboard control, screenshot capture, and process management. It enables programmatic interaction with the Windows desktop environment through the Model Context Protocol. | |
| DeepSeek Search & Fetch MCP Server billyuan01/qwenpaw-deepseek-search-mcp Adds two tools to QwenPaw agents: one for live web search returning titles, URLs, summaries, sites, dates, and authority scores, and one for fetching a single page as Markdown. It reuses the provider key already configured in QwenPaw, so no | |
| etherscan-actions billywgd/etherscan-actions A stdio MCP server that gives agents read-only access to Ethereum public data scraped from etherscan.io with no API key, covering first funder, address metadata, ERC20 holdings, token holder lists, transaction history and transaction detail | |
| emacsclient-mcp bimawa/emacsclient-mcp An MCP server that provides LLMs with direct access to Emacs via its server protocol, offering 22 tools for editing, search, buffer management, and a PR review agent. | |
| Speckle MCP Server bimgeek/speckle-mcp A bridge between Speckle's API and client applications that enables users to list/search projects, access model versions, and retrieve/query objects and their properties from the Speckle collaborative data hub for AEC tools. |
34,201–34,250 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.