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 |
|---|---|
| AegisMCP bennedictquanton/aegismcp Local, type-safe multi-agent CLI for financial PDF risk notes with a default-deny MCP tool gateway, enabling structured risk report generation via LLM or heuristic paths. | |
| SearchAtlas MCP Server bennethuzochukwu-cloud/searchatlas-mcp-server Connects MCP-compatible AI clients to the SearchAtlas platform, enabling access to 10 specialized SEO and marketing agents, project management, and playbook automation. | |
| Discord MCP Server bennettschwartz/discord-mcp An MCP server for interacting with Discord. | |
| benni-operator-gateway benni-os/benni-operator-gateway An open-source MCP gateway for AI operators, connecting any LLM to a hot-reloadable connector registry with production-grade approval gates and a built-in control plane for session management. | |
| mcp-forge benni-os/mcp-forge A FastAPI-style framework for building MCP servers in Python, enabling declarative tool definitions with automatic schema validation and multiple transport options. | |
| browser-mesh bennialencar/agent-browser-mesh Enables AI agents to control a browser via the Model Context Protocol using compact semantic DOM snapshots for navigation, clicking, and data extraction, with built-in SSRF and prompt-injection protection. | |
| agent-code-sandbox bennialencar/agent-code-sandbox Enables AI agents to safely execute Python code and shell commands in an ephemeral, isolated scratchpad with pre-execution AST security checks, timeout enforcement, token-shielded output, and file diff tracking. It also exposes static code- | |
| agent-deep-research bennialencar/agent-deep-research Enables AI agents to conduct zero-key multi-source deep research, run quick searches across DuckDuckGo, Wikipedia, and ArXiv, and cryptographically verify claims with token-compressed, citation-backed evidence. | |
| Weather MCP Server bennibeni/mcp-weather Provides US weather alerts and forecasts via the National Weather Service API with no API key required. | |
| strava-mcp benniblau/strava-mcp Enables querying and analyzing personal Strava activity data through natural language, including activities, segments, gear, and training trends. | |
| zwift-mcp benniblau/zwift-mcp Exposes Zwift training history stored in a local SQLite database to MCP clients and a REST API, enabling queries for activities, power curves, race results, and training load. | |
| emqx-mcp-server benniu/emqx-mcp-server A Model Context Protocol (MCP) server implementation that provides EMQX MQTT broker interaction. | |
| Houdini MCP bennyjoel/-houdini-mcp- Enables AI assistants to connect directly to a live Houdini session and act as a technical director by creating nodes, wiring networks, querying scene data, running Python/HScript, and modifying parameters in real time. | |
| BytesJev PlanningChecker bennyp11/bytesjev Enables coding agents to submit their original request, proposed plan items, and observed repository conventions for per-item necessity scoring before making edits. It returns advisory keep, simplify, or review recommendations with reasons | |
| lightwave-mcp bennythecoder/lightwaverf_mcp Enables AI agents to discover and control LightwaveRF Smart Series devices (lights, switches, sockets) via the official REST API, using natural language commands like 'turn off the kitchen light'. | |
| Smartlife Tuya MCP Server bennythecoder/smartlife_mcp Local MCP server for reading temperature/humidity sensors from Tuya/SmartLife devices, exposing tools to list devices, get capabilities, and read sensor data. | |
| Claude GPT Launcher bennyyy28/claude-gpt-launcher Enables Codex chat to use the Claude Code harness for repository consultation and editing, routing through GPT models via a local proxy. | |
| MCP Color Converter bennyzen/mcp-accessibility-checker A comprehensive toolkit for color conversion, manipulation, and accessibility analysis supporting formats like OkLCH and WCAG compliance. It enables AI agents to manage design systems by generating harmonious palettes, transforming color sp | |
| MCP Color Converter bennyzen/mcp-color-convert Provides comprehensive color conversion, manipulation, analysis, and WCAG accessibility tools supporting multiple formats (hex, rgb, hsl, oklch, oklab) for design systems and web development. | |
| ROAST MCP App benoib/roast-mcp-app Enables authenticated ROAST users to view their dashboard, profiles, photoshoots, and images via MCP tools. | |
| Omni-mcp benoit-sigwald/omni-mcp Omni-mcp is a unified Model Context Protocol gateway combining the Behavioral Profiler BP v3 forensic analysis engine, Prisme engine, and dynamic Meta-Skills routing, with PostgreSQL 18 persistence on Oracle Cloud Infrastructure, exposing M | |
| climatiq-mcp benoitlehnig/climatiq-mcp A TypeScript-based Model Context Protocol (MCP) server with web interface for calculating CO2 emissions using the Climatiq API. | |
| mcp-pubmed benoitleq/mcp-pubmed An MCP server that provides direct access to PubMed and PubMed Central via the NCBI E-utilities API. It enables AI models to search biomedical literature, retrieve detailed article metadata, and download open-access full texts. | |
| touch-mcp benoitliard/touch-mcp High-performance MCP server that enables AI assistants to control TouchDesigner live via WebSocket, providing 37 tools for nodes, parameters, scripting, and more. | |
| DVF Paris benoitvx/dvf-mcp-app An MCP app that displays interactive Paris real estate price statistics per arrondissement inside Claude, with map, comparison, and address search. | |
| Carbon Intensity MCP benomahony/carbon-intensity-mcp Provides access to the UK Carbon Intensity API, enabling users to retrieve current, historical, and forecast carbon intensity data, regional data by postcode, and generation mix information. | |
| Jira CLI MCP benomahony/jira_cli_mcp A Model Context Protocol (MCP) server that wraps the Jira CLI tool, exposing Jira commands through MCP resources, tools, and prompts for AI assistant integration. | |
| Gorgias MCP Server benpalmer1/gorgias-mcp-server An MCP server that exposes the full Gorgias helpdesk API to AI assistants, enabling ticket management, analytics, and customer operations through natural language. | |
| MCP Boilerplate Next.js benpdev/mcp-boilerplate-nextjs A minimal Next.js starter for building MCP Apps, enabling MCP hosts to render interactive UIs alongside tool calls via an MCP server endpoint and a React widget UI. | |
| Turbify Store MCP Server benpeke/turbify_store_mcp Provides tools to create, update, delete, and search catalog items through the Turbify Store Catalog API. | |
| owa-mcp benpeter/owa-mcp Provides full access to Microsoft Outlook calendar and email through Claude Code by intercepting browser tokens from an existing signed-in Edge profile, eliminating the need for Azure app registration. | |
| LLDB MCP Server benpm/claude_lldb_mcp Provides structured debugging capabilities through LLDB, enabling AI assistants to set breakpoints, inspect variables, analyze crashes, disassemble code, and evaluate expressions in C/C++ programs. | |
| wc3-mcp benqsxd/wc3-mcp Enables creating and editing Warcraft III maps with Claude, including terrain, triggers, objects, and scripts, and can drive the World Editor and game for testing. | |
| SearXNG MCP Server benreichman/searxng-mcp-server Enables web search and content scraping from multiple engines via a local SearXNG instance, allowing AI assistants to retrieve and extract web content. | |
| sql-assistant-mcp benrishty/sql-assistant-mcp A Model Context Protocol (MCP) server for SQL Server / Azure SQL that enables querying, monitoring, and analyzing databases directly from Claude. | |
| Personal Productivity MCP Server benro/personal-productivity-mcp A multi-domain productivity tool that currently enables job search automation, application tracking, and pipeline analysis for Career management. Future phases plan to add health tracking, workout management, and family expense monitoring c | |
| defi-yield-mcp bensacc/defi_yield_mcp_server Enables querying DeFi yield pool data and risk signals from DefiLlama, including APY, TVL, exploit history, and a gate-then-score risk assessment for curated protocols. | |
| nport bensacc/nport-mcp MCP server serving a normalized graph of fund holdings and service providers built from SEC Form N-PORT and N-CEN data joined to the GLEIF LEI register. Currently only the ingest layer is implemented, with the MCP server not yet built. | |
| CryptoTwitter.Space x402 MCP Server benschiller/cts-x402-mcp Enables programmatic access to premium crypto alpha reports from Twitter Spaces with pay-per-use pricing via x402pay and automated revenue distribution to hosts, curators, and platform using CDP Wallet smart accounts. | |
| devpilot benseverndev-oss/devpilot Manages dev server lifecycles for AI coding agents, providing structured process awareness, health checks, and JSON outputs to prevent panic cycles. | |
| Sport5 Fantasy League MCP Server benshabbat/sport5-fantasy-mcp Enables full automation of Sport5 Fantasy League management including team analysis, player searches, automatic transfers, captain selection, and optimization recommendations. Supports Hebrew interface and provides comprehensive fantasy foo | |
| Weather MCP Server bensinclair/weather-mcp-server A Model Context Protocol server that retrieves current weather information for any city using the OpenWeatherMap API, designed for integration with Claude Code. | |
| Career Compass MCP benskamps/career-compass-mcp Turns Claude into a career co-pilot that manages resumes, cover letters, job applications, and interview prep using local YAML files. | |
| Jazz MCP Server bensleveritt/jazz-mcp-server Enables AI assistants to create, read, update, and delete data in local-first apps built with the Jazz framework, with support for sync, auth, and rich data types. | |
| FastAPI Todo MCP Server bensonaddo/fastapi-mcp-todo Enables AI assistants to manage a todo list with full CRUD operations, including creating, reading, updating, and deleting todos via a FastAPI backend with SQLite persistence. | |
| Roon Desktop MCP bensonmaxai/roon-desktop-mcp Enables AI assistants to observe and control the Roon desktop application on Windows via MCP, supporting screenshots, OCR, playlist editing, and guarded UI actions with explicit verification. | |
| MCP-Exec bensons/mcp-exec A secure, context-aware MCP server for shell command execution with comprehensive logging and AI optimizations, enabling interactive sessions and safe system administration via Claude Desktop. | |
| CodeTour benstaniford/codetour Enables LLMs to create animated, narrated tours of GitHub pull requests, with a local browser viewer showing diffs and code highlights while speaking the narration aloud. | |
| playbook benteigland11/playbook Enables agents to search, create, edit, and step through JSON-based procedures with intent-driven search and step-by-step execution. | |
| lineus-mcp benteoneb/lineus-mcp Enables an AI agent to control a Line-us pen plotter over the local network by compiling declarative scenes of expressions, single-stroke handwriting and Quick Draw! doodles into strokes, then planning, simulating and drawing them. Includes |
33,651–33,700 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.