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 |
|---|---|
| CodeRabbit CLI MCP 2001y/coderabbit-cli-mcp Enables AI code reviews through the CodeRabbit CLI by exposing a run_review tool that executes CodeRabbit with full flag coverage for analyzing committed, uncommitted, or all changes in a repository. | |
| RepoSqueeze 2002-rokkam/reposqueeze Enables coding agents to retrieve task-relevant repository code, pack verbatim excerpts within a configurable token budget, expand cited line ranges, and optionally use local semantic search or verified JSON/TOON compression. | |
| Squeze 2002-rokkam/squeze An MCP server that turns a task, error or stack trace into a few verbatim, line-cited source excerpts from a local repository index, staying inside a token budget the caller chooses. It also exposes tools to expand a cited range, outline or | |
| weather 2005wr/mcp_server_weather MCP server that provides real-time weather and daily forecast for the nearest city station from China Meteorological Administration based on given latitude and longitude. | |
| Power BI PBIP/PBIX MCP 2012952877/powerbi-pbip-pbix-mcp-demo Enables bidirectional conversion between editable project folders and packaged desktop files, using an authenticated portal and a controlled Windows desktop worker, with per-user job queues and verification. | |
| chrome-feedback 2019-02-18/mcx MCP server for interactive feedback collection via Chrome extension, enabling users to submit text, images, and page elements. | |
| Chrome MCP Bridge 2021feiyu/chrome-mcp-bridge Enables MCP clients to operate an already-logged-in Chrome tab through a browser extension and chrome.debugger, exposing navigation, page reading, interaction, screenshots, cookies/storage, network and console debugging, downloads, and batc | |
| Date-MCP Server 2022124030jc/date_mcp A Model Context Protocol service that handles date and time conversions for China's timezone (UTC+8), supporting current date retrieval, timestamp conversions, and date-time formatting. | |
| first-mcp-server 2022f-mulbscs-100-del/first-mcp-server Enables deploying a remote MCP server on Cloudflare Workers without authentication, allowing users to define custom tools and connect clients like Claude Desktop or Cloudflare AI Playground. | |
| Remote MCP Server on Cloudflare 2022f-mulbscs-100-del/relay-mcp-server Enables deployment of a remote MCP server on Cloudflare Workers without authentication, with customizable tools and connectivity to Cloudflare AI Playground and Claude Desktop. | |
| DSH ⇄ ChatGPT Fusion Gateway 2025ashore/dsh-brain-bridge Enables DeepSeek Harness agents to use ChatGPT Web as an external, stateless reasoning provider while keeping DSH as the single agent runtime. | |
| deep-websearch 2046698389-code/deep-websearch Enables configuration-driven, budgeted multi-source web research across platform and web search adapters, merging duplicate links, preserving provenance, and returning honest source coverage reports. | |
| linkedin-mcp 2060-io/linkedin-mcp Enables AI agents to publish posts, images, comments, and reactions to LinkedIn as the authenticated user, with built-in safety features like daily budgets and deduplication. | |
| Codex Harness MCP 2091k/a_harness_mcp Enables MCP-compatible AI clients to invoke CLI-driven agent tools over Streamable HTTP, including shell execution, file operations, patching, image viewing, web search, and nested agent tasks, with permission modes and real-time progress s | |
| MyClawn Computer MCP 20vision/myclawn-computer-mcp Enables an AI assistant to run tasks on a hosted cloud desktop that belongs to the user, with a browser that stays signed in to their accounts, its own email address, and its own files, so it can fill forms, download and edit documents, and | |
| mymemory-mcp 20vision/mymemory-mcp User-owned portable memory vault as an MCP server: agents can fetch context, search entries, and propose new memories, while humans curate the vault via a web app. | |
| NotebookLM MCP Server 20youssef10/notebooklm-mcp Enables AI agents to programmatically access Google NotebookLM through browser automation for managing notebooks, sources, and chat interactions. It supports automated content generation including audio overviews, study guides, and quizzes | |
| TMDB MCP Server 20youssef10/tmdb-mcp-server Provides 34 tools to search and discover movies, TV shows, and people from The Movie Database (TMDB) API. | |
| TrendRadar 2134863176/trendradar MCP server for real-time trending news aggregation, AI-powered analysis and filtering, and multi-channel push notifications. | |
| Skillz 214140846/skills-mcp An MCP server that transforms Claude-style skills and resources into callable tools for any MCP-compatible agent or client. It automatically discovers, exposes, and executes scripts from skills organized in local directories or packaged arc | |
| VM MCP 2143shi/vm-mcp Enables AI clients to control VMware Workstation virtual machines by viewing the console, operating the mouse and keyboard, running guest commands, and managing power and snapshots across multiple named Windows and Linux VMs. | |
| douyin-lead-workbench MCP Server 2160039878-cyber/douyin-lead-workbench Enables AI clients to read status and records, control collection tasks, prepare drafts, and execute approved queues, with manual approval required before sending. | |
| AI Router MCP Server 2188195028-crypto/ai-router Enables Claude Code to analyze images using multiple visual models (Kimi, OpenAI, etc.) and summarize results with DeepSeek. Supports dynamic switching of visual providers and handles both text and image inputs. | |
| MCP Enhanced Server 21967201/mcp-enhanced-server Provides file system tools, code analysis prompts, async tasks, and secure HTTP transport following the 2025-03-26 MCP specification. | |
| MCP News Server 21omk21/mcp-server Fetches news from trusted global sources using NewsAPI and RSS feeds, enabling search, headline retrieval, and source listing. | |
| TIA Codex Bridge 220154178jjy-alt/tia-codex-bridge An MCP bridge for Siemens TIA Portal that enables AI assistants to inspect PLC projects, import/export programs, and compile with read-only defaults and opt-in writes. | |
| Bilibili Comments MCP 222wcnm/bilibili-comments-mcp Enables retrieval of comments from Bilibili videos and dynamic posts with support for pagination, sorting, and nested replies in both Markdown and JSON formats. | |
| Martin MCP Toolbox 2234839/mcpserver A multi-modal AI toolbox based on Model Context Protocol, integrating Zhipu GLM, Pollinations.AI, SiYuan Notes, and Perplexity web search to enable image/video analysis, image/text/audio generation, note management, and intelligent web sear | |
| mcp-server 223n/mcp-server Exposes local Ollama as an MCP server so Claude can delegate drafting, summarization, translation, code review, error explanation, model listing, health checks, and file reading to local models via stdio or HTTP. | |
| telegram-user-mcp 22syn/telegram-user-mcp An MCP server that connects to Telegram as your real user account and exposes read-only tools to read and search messages, list chats and folders, inspect group info, and download media. | |
| obsidiyan 22wayan/obsidiyan-engine Enables AI coding agents to search a shared, sourced corpus of past Claude Code and Codex sessions and curated notes, retrieve full conversations and timelines, and write or extend memory in either a committed or confidential, git-ignored l | |
| 2328 Wallet MCP Server 2328io/mcp MCP server for managing a 2328 merchant account, providing tools for balances, exchange rates, invoices, static wallets, payouts, and conversions via natural language. | |
| NovelAI_MCP 2332239652/novelai_mcp MCP server for NovelAI image generation, supporting V4.5 models with multi-character prompts and multiple transport modes (Stdio, HTTP, SSE) for flexible deployment. | |
| vocotype 233stone/vocotype-cli VocoType 是一款运行在本地端侧的隐私安全语音输入工具，通过快捷键即可将语音实时转换为文字并自动输入到当前应用。支持语音转文字MCP、AI 优化文本、自定义替换词典、录音视频转文字等功能，让语音输入更高效、更安全。 | |
| Aion Memory Nexus 234194027-cpu/aion-memory-nexus A trusted memory and predictive analysis MCP server for AI agents, enabling evidence-based memory management, pattern analysis, and decision support with full audit trails. | |
| Agent Bridge 234sainsa/automata-system A Python MCP server that connects AI clients to a running Unity game over a local, token-gated HTTP endpoint, letting the agent read only what a player can see and hear and act through the same virtual pad a human uses. It also exposes back | |
| agent-drugs 2389-research/agent-drugs Digital drugs that modify AI behavior through prompt injection, enabling agents to list, take, and manage active drugs across sessions. | |
| MCP Agent Social Media Server 2389-research/mcp-socialmedia Provides social media functionality for AI agents, enabling them to login with unique handles, read filtered posts, and create posts or replies within team-based discussions. | |
| Slack MCP 2389-research/slack-mcp Enables Slack workspace integration including channel creation, user invites, message posting, and thread management through natural language. | |
| after-effects 23d1/after-effects-mcp Lets Claude drive Adobe After Effects to build comps, animate layers, apply effects, write expressions, and render frames back so the model can see its own work. | |
| Nimbus MCP Server 23viv/nimbus_mcp Provides live user account lookup tools over HTTP for the Nimbus Furniture platform. Enables AI agents to retrieve customer account details by email or user ID via MCP. | |
| system-monitor 2428424081cn/mcp-system-monitor A secure, read-only MCP server for AI-powered system monitoring. It provides real-time OS metrics, config discovery, and safe log tailing to enable autonomous infrastructure audits without shell access risks. | |
| Skill-MCP 2428424081cn/skill-mcp Enables AI agents to manage, search, plan, and execute reusable skills while automatically enforcing always-on coding and reasoning guidelines. It provides workflow orchestration, permission-controlled execution, dynamic skill registration, | |
| reading-buddy 244t/reading-buddy Enables Claude Code or Codex CLI to see the exact sentence and section you are viewing in Chrome, so you can discuss books with context, take notes, and track reading progress. | |
| Curl MCP Server 247arjun/mcp-curl An MCP server that enables AI assistants to make HTTP requests and download files using curl, allowing them to interact with web APIs and content. | |
| Grep MCP Server 247arjun/mcp-grep Provides powerful text search capabilities using the grep command-line utility, allowing users to search files and directories using both natural language descriptions and regex patterns. | |
| A Share MCP 24mlight/a-share-mcp-is-just-i-need A Model Context Protocol server providing tools for querying A-share stock market data, including historical prices, financial reports, market indices, and macroeconomic indicators. | |
| obsidian-mcp 24thabhinav/obsidian-mcp Exposes an Obsidian vault with full-text and semantic search, and Anki-style spaced repetition active recall. | |
| VMWare MCP 2501-ai/vmware-mcp Enables AI agents to manage VMware vSphere infrastructure through 55 typed tools built on the govc CLI. It supports comprehensive operations including VM lifecycle management, snapshot control, datastore navigation, and networking configura | |
| MySQL MCP Server 2506013878/mysql_mcp Enables MySQL database management via MCP, allowing users to list databases, tables, views, and functions, inspect table schemas, create tables, and modify table fields. |
21,951–22,000 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.