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 |
|---|---|
| xtalk 8w6s/xtalk Cross-agent messaging for MCP clients, enabling agents to discover one another, exchange threaded messages, and resume work in a persistent project room. | |
| AQICN MCP Server 8xiang5hao/aqicn-mcp Enables querying real-time air quality index (AQI) data for Chinese cities, including PM2.5, PM10, and other pollutant information with health recommendations from the World Air Quality Index Project API. | |
| Destiny MCP 8z2wz746tv-png/destiny_mcp Manage your Destiny 2 inventory, weapons, and loadouts through AI. Integrates with MCP clients like Claude Code. | |
| Destiny MCP 8z2wz746tv-png/destiny-web-mcp Enables AI to manage Destiny 2 gear, weapons, and loadouts through MCP clients, with tools for player profiles, inventory, builds, and activities. | |
| JMComic MCP Server 8z2wz746tv-png/jmcomic-mcp Wraps the jmcomic Python library so MCP clients can search albums, fetch album/photo details and rankings, read favorites, and download albums to a local directory with task progress, cancellation, and a two-step write-confirmation gate. It | |
| 9bot 9-bot/mcp Automate and manage WhatsApp groups, communities, and channels with scheduling, moderation, analytics, and more. | |
| projectbrain-mcp 9-trinkets/projectbrain-mcp ProjectBrain MCP is a Model Context Protocol (MCP) server for project planning and execution workflows. It exposes tools for tasks, decisions, facts, milestones, comments, and team messaging through a Streamable HTTP endpoint. | |
| SolidWorks MCP Server 906grown/solidworks_mcp_2026 Enables Claude to control SolidWorks through natural language, supporting part and assembly creation, sketches, advanced features, dimension editing, selection inspection, screenshots, and rebuilds. | |
| BrainLess 90acatz/brainless-mcp A persistent memory MCP server that saves AI context across sessions and IDE restarts using a global log file. | |
| MSFS SDK MCP Server 90barricade93/msfs-sdk-mcp A modern MCP server that provides fast, structured access to Microsoft Flight Simulator SDK documentation through natural language and structured queries. | |
| pablo-obsidian-mcp 90pabloromero/pablo-obsidian-mcp An MCP server that provides full read/write access to an Obsidian vault, enabling searching, task management, wiki-link graph analysis, and attachment organization from an MCP client like Claude Code. | |
| Codex Team Workbench 912925635/codex-team-workbench Enables persistent SQLite-backed tasks, recorded parent/child agent relationships, workflow groups, and lead-mediated conversation snapshots and navigation requests through compatible ChatGPT/Codex hosts. | |
| playwright-browser-skill 91fapiao-cn/playwright-browser-skill Provides 101 browser automation operations via Playwright, including navigation, interaction, content extraction, network control, and more, integrated with OpenClaw through the MCP protocol. | |
| chatgpt-daily-token-tracker 927242768-dotcom/chatgpt-daily-token-tracker Enables querying daily and date-range token usage, recording exact API usage, estimating tokens, and retrieving tracker info through MCP tools. | |
| files-vector-mcp-server 928871247/files-vector-mcp-server 一个基于FastMCP协议的文件向量化服务，支持自动目录监控、多格式文件处理和高效向量搜索，帮助构建个人或团队知识库。 | |
| screenshot-mcp 937327493/screenshot-mcp Enables AI agents to capture screenshots of windows (e.g., WeChat developer tools) and save them locally, allowing the agent to read the image directly and close the code-change-to-review loop without OSS or network. | |
| Coach AI 94aharris/coach-ai A productivity coaching assistant designed for ADHD support that provides intelligent task management, goal tracking, and personalized recommendations. It utilizes a persistent memory system to learn user patterns and preferences, helping t | |
| PredictEdge Data MCP 94gvmz9fcz-rgb/pickaxe-public-ledger Live analytics at the edge across prediction markets | |
| Remote MCP Server on Cloudflare (Authless) 94halldah/remote-mcp-server-authless Enables the deployment of remote Model Context Protocol servers on Cloudflare Workers without requiring authentication. It allows users to integrate custom tools into AI clients like Claude Desktop or the Cloudflare AI Playground via Server | |
| Aizex MCP 94series/aizex_mcp Controls Aizex shared ChatGPT/Claude account pool via Playwright browser automation, exposing tools through MCP protocol for AI agents to get advanced model responses or batch generate content. | |
| icloud-reminders-mcp 94youshin/icloud-reminders-mcp A cross-platform MCP server for managing Apple Reminders, enabling creation, updating, completion, deletion, and listing of reminders with timezone and child-task support. | |
| Doubao Image Description MCP Server 9527wow/doubao-image-mcp Enables visual understanding and image description capabilities for iFlow CLI and Claude Desktop using Doubao's vision model. It supports 18 image formats and features automatic optimization, caching, and Chinese language optimization. | |
| AIDarknet 95369149/aidarknet-mcp Machine-readable AI market data for AI agents: subscription prices, free credits, free LLM models, China-exclusive AI pricing. 6 MCP tools, Streamable HTTP, no auth. | |
| pixel-workshop 956005596/pixel-asset-workshop A local stdio MCP server that lets agents describe, render, inspect, and preview procedural 2D pixel-art skill effects and baked sprite animations entirely offline. It reads supplied local PNG/JSON projects and writes transparent sprite she | |
| cloudflare-html2sprite-mcp 958877748/remotedesktopcloud A remote MCP server running on Cloudflare Workers, currently exposing a test tool that echoes messages and returns server metadata. | |
| TimeReverse 964nbtrkhb-eng/timereverse Provides verifiable, append-only context handoffs for Codex and MCP clients, enabling memory persistence and resume across chat sessions. | |
| MCP-with-Playwright 9697-mali-lo/mcp-with-playwright An MCP server that enables LLMs to automate browser interactions using Playwright to fetch real-time Israeli weather data. | |
| imap-mail-mcp 96b2gwbdg8-dev/imap_mail_connector An MCP server that lets Claude read, search, and send email over standard IMAP/SMTP. | |
| dex-mcp 972jesko/dex-mcp Debug and inspection tooling for Roblox projects, exposed as an MCP server so an AI agent can explore the instance tree, read/write properties, call remotes, and run Luau in a Roblox client driven by an executor. | |
| MCP Audio Server 97k/mcp-audio-server Enables audio transcription, intelligent splitting, and meeting analysis for MCP-compatible clients like Claude Desktop. | |
| gdevelop-mcp-server 982945902/gdevelop-mcp-server Provides a local control plane for GDevelop game projects, enabling Codex to open projects, build previews, and serve them over HTTP for debugging. | |
| feishu-bot-mcp 983033995/feishu-bot-mcp Enables sending text messages, files, and images to Feishu (Lark) group chats via MCP, with support for automatic default group configuration. | |
| Nutrition MCP Server 984fht6/nutrition-mcp-server Enables intelligent nutrition tracking through natural language meal logging with automatic macro calculation using the FoodData Central API. Users can set daily macro goals, review meal history, and monitor nutritional progress through loc | |
| roblox-DEX-AI-MCP 986mn/roblox-dex-ai-mcp Bridges a Roblox executor's DEX explorer with an AI client so the AI can see which instance the user has selected and, conversely, select, highlight, or inspect instances inside DEX on the user's behalf. It also exposes execution, inspectio | |
| DuckDuckGo MCP Server 988664li-star/duckduckgo-mcp-server Enables web search through DuckDuckGo and webpage content fetching with intelligent text extraction. Features built-in rate limiting and LLM-optimized result formatting for seamless integration with language models. | |
| Simulator MCP 992429169/simulator-mcp Enables AI to control iOS simulators through the MCP protocol. Supports device management, UI automation, and network interception including screenshot capture, text input, and HTTP request mocking. | |
| project-kb 993030293/project-kb Provides a local, evidence-first knowledge base over source snapshots and summaries stored in SQLite, with bounded search and exact readback while preserving provenance. | |
| meso MCP Server 996688p/meso-sdk Enables agent frameworks to query live protocol state and build unsigned BNB Chain transactions for minting, hatching, feeding, evolving, listing, buying, and claiming without writing RPC code or handling private keys. | |
| e-debug-bridge 997375857/e-debug-bridge Enables AI to read, reliably edit, compile, and observe a local E5.95 EasyLanguage IDE over MCP, including project snapshots, declarations, native listview preparation, support-library metadata, and fault/variable capture. It works without | |
| docctx 999aryadharma/local-mcp Local-first context retrieval engine that serves precise documentation chunks to coding agents via MCP, ensuring high-confidence context for code generation. | |
| FiveM MCP 999luan/fivemmcp A focused MCP server for FiveM teams to scaffold resources, generate NUI templates, and perform safe file edits. | |
| Project Data Standardization MCP 999luan/mcp This MCP ensures consistent naming conventions for variables, database structures, and file organization by validating against project standards and providing smart naming suggestions. | |
| k-prevention MCP 999purple999/k-prevention MCP server for k-prevention, enabling AI assistants to access decrypted financial data, run Monte Carlo simulations, optimize scenarios, and manage scenarios locally while preserving end-to-end encryption. | |
| vsphere-mcp-extended 999yurik666/vsphere-mcp-extended Enables VMware vCenter management via MCP, adding real-time and historical performance monitoring, VM lifecycle operations, snapshots, ISO mounting, and network/host management through natural language. | |
| CodeWeaver MCP Server 99hansling/codeweaver-mcp-server Converts entire codebases into a single, AI-readable Markdown document with structured directory trees and syntax highlighting. It enables AI assistants to analyze complete project contexts for tasks like code reviews, documentation, and re | |
| mcp-django-server 99rig/django-mcp-server A Django MCP server that exposes tools and resources to AI agents using simple decorators, with auto-discovery, type safety, and custom authentication. | |
| Hiito MCP Server 9churze/hiito-mcp Enables AI assistants to query nearby parties, retrieve party details, and generate WeChat mini-program share links for the '螺母车尾派对' app. | |
| patent-mcp 9g2s6g2cnh-arch/patent-mcp A local MCP server that provides patent search, similarity lookup, and detailed patent information to AI agents, with extensible data sources. | |
| resume-maker-mcp 9ikhil/latex-resume-mcp Analyzes job descriptions and automatically tailors LaTeX resumes, then pushes changes to GitHub where Actions compiles a fresh PDF. | |
| MCP Server 9kman/job-20260613144931-000091 Enables natural-language querying of structured data via Model Context Protocol, allowing AI agents to answer questions without SQL or API knowledge. |
22,401–22,450 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.