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 |
|---|---|
| BailingHub MCP Server bailinghub/bailinghub-dsh-plugin Enables submission, tracking, and retrieval of governed tasks from DeepSeek Harness against BailingHub routes, allowing job management without opening embedded chat interfaces. | |
| USPS Address Validation and Standardization MCP Server bailur/usps-mcp-server Enables AI assistants to validate and standardize US addresses using the official USPS Address Validation API with secure OAuth2 authentication. | |
| EagleEye MCP baimaomaomao556/eagleeye-mcp A pixel-accurate visual toolbox MCP server for agents, enabling screen capture, pixel measurement, OCR, template matching, and visual regression with deterministic-first approaches. | |
| LINK MCP Server baimimitu-stack/link-toy-bridge Enables mobile characters and Grok to control Intiface-connected devices through ten MCP tools, using a server-hosted bridge and a thin local relay while keeping Bluetooth access on the user's computer. | |
| agent-fleet baiqiaw/agent-fleet MCP server that enables Claude Code to delegate tasks to Codex for real-time collaborative code generation and execution. | |
| Latchshot for Claude Code baiqingl/latchshot-claude-code Enables Claude Code to capture public web pages as images or PDFs via Latchshot's hosted API, and check rendering quota, without requiring a local browser. | |
| Latchshot for Gemini CLI baiqingl/latchshot-gemini-cli Provides two MCP tools (capture_page and get_usage) that let Gemini CLI capture public web pages as PNG/JPEG/PDF and check render quota, all via a hosted Streamable HTTP endpoint without local browser. | |
| agent-bm25-knowledge-mcp bairuizhang/agent-bm25-knowledge-mcp A local BM25 knowledge retrieval MCP server that indexes configured files and directories for agents like Claude Code, Kiro CLI, and Codex, providing interpretable search and chunk retrieval tools. | |
| Polymarket MCP Server baisedagent/polymarket-mcp MCP server that exposes Polymarket prediction markets via CLI wrapper. Enables AI agents to discover markets, check prices, and place trades programmatically. | |
| godot-mcp-lite baitang-bt/godot-mcp Provides a secure, authenticated MCP bridge to control a local Godot editor from Cursor, enabling scene/node management, script validation, editor diagnostics, and runtime inspection through a whitelisted set of tools. | |
| database-mcp-server baitianxia/database-mcp-server Enables Claude Code to interact with MySQL databases through configurable tools for inspecting configuration, listing tables, describing schemas, and running parameterized SQL queries, with optional write/DDL operations guarded by permissio | |
| anime-image-mcp baiwoww/image-generation-mcp MCP server for generating high-quality anime/CG images via ARK and Agnes engines, supporting text-to-image, image-to-image, multi-image, and sequence generation with 16 style presets. | |
| langchain-mcp baixianger/langchain-mcp Provides semantic search across the entire LangChain ecosystem, including documentation and source code for LangChain, LangGraph, LangSmith, and DeepAgents. | |
| SEO MCP Connector baixinyao2011-beep/seo-mcp-connector Local management console and permission wrapper for integrating Google Search Console, GA4, Bing Webmaster Tools, PageSpeed, and SEO analysis through a controlled MCP endpoint. | |
| Jev MCP for Cloudflare baize7815/jev-mcp-open-source Enables AI assistants to perform intent routing, retrieval reranking, and batch semantic judgments on Cloudflare Workers, returning structured answers with confidence scores instead of generated prose. | |
| CapCut MCP Server baizo7/capcut_mcp_server- Enables AI assistants to fully control CapCut video editing projects, including creating projects, importing media, adding text/subtitles, managing audio, and editing timelines. | |
| gmail-research-mcp bajor/gmail-mcp-read-only A read-only Gmail MCP server that searches email, fetches complete threads, and stores them as local Markdown and JSON for offline analysis by other agents. | |
| gmail-mcp-send-to-list-only bajor/gmail-mcp-send-to-list-only An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security. | |
| Travel Planner MCP Server bajpaih22/dt1_assigment_2_mcp_server_claude Enables AI-assisted travel planning with real-time weather forecasts, place discovery, customized itinerary generation based on interests and budget, and travel distance calculations between cities. | |
| travel-planner bajpaih22/travel-planner-mcp Enables travel planning through natural language, providing weather forecasts, attraction search, itinerary generation, and distance calculations using free APIs. | |
| Delta MCP Server bajpainaman/deltamcp Brings git-delta's beautiful syntax highlighting and diff formatting to AI assistants, providing colorized diffs, side-by-side comparisons, blame information, and grep results with clickable browser links. | |
| codegraph bajpayeeritik/gitatlas Indexes a codebase into a live symbol graph and serves it via MCP to AI coding tools for context-aware code queries. | |
| jev-browser baka3k/jev-browser-ultrafast-mcp Enables coding agents to drive a real, indexed Chrome browser over MCP stdio, navigating pages, observing numbered interactive elements, and performing click, type, and select actions without the server itself calling any model. | |
| codinfy-agent-monitor bakalagoin/codinfy-agent-monitor Provides real-time monitoring of AI agents, context, usage limits, workflows, files, Git, tests, builds, errors, secrets, and model-economy advice for tools like Claude Code, Codex, and Cursor, with 30 MCP tools for comprehensive observabil | |
| Codinfy MCP bakalagoin/codinfy-mcp MCP server that connects AI agents to Codinfy platform APIs for validating licenses, creating checkouts, listing products, tracking analytics, managing OAuth identity, and handling ad placements. | |
| Codix Build MCP bakalagoin/codix-build-mcp A build accelerator for AI coding assistants that scaffolds complete projects from short prompts using Smart Context Mode to reduce token usage. | |
| codex_schedule bakapiano/codex-cli-schedule Enables users to schedule and manage prompts for Codex CLI sessions, supporting one-time, interval, and cron triggers for both existing and newly created sessions. | |
| blender-chatgpt-mcp bakaroart/blender-chatgpt-mcp An MCP server that enables AI assistants like Codex or ChatGPT to inspect and control a local Blender scene, including creating objects, editing materials, setting cameras and lights, rendering previews, and saving safe copies of .blend fil | |
| TypeScript MCP Server Boilerplate bakcoder/my-mcp-server A starter project for rapidly developing Model Context Protocol servers using TypeScript and the official SDK. It includes pre-implemented examples of tools and resources to help developers jumpstart their custom MCP server development. | |
| agent-memory bakebakebakebake/agent-memory MCP server for zero-config, traceable long-term memory using SQLite, enabling agents to store, search, trace, and monitor memory with tools like memory_store, memory_search, and memory_health. | |
| Memory MCP - Redis Stack Backend bakemark/mcp-memory-redis A drop-in replacement for mcp-memory-duckdb with full concurrent access support using Redis Stack. Enables persistent knowledge graph storage with full-text search and multi-session concurrent access. | |
| mcp-runrun baker-brands/mcp-runrun MCP server that gives Claude access to Runrun.it tasks, projects, clients, users, boards, and more via the Runrun.it REST API v1.0, including listing, creating, updating, deleting, and time-tracking operations. | |
| tv-control baker-scripts/tv-control Enables an AI agent or script to control Android TV and LG webOS devices over streamable HTTP, including key presses, app launches, power and wake, input switching, sleep timers, toasts, status checks, screenshots, and device scans, with be | |
| MCP GitHub Project Manager baker0225/mcp-github-project-manager Enables AI coding agents to register, self-assign and coordinate tasks, track progress, review work, and manage GitHub Projects v2 with AI-powered PRD generation, sprint planning, issue triage, and PRD-to-issues pipelines backed entirely by | |
| Luma MCP baker488/luma-mcp Gives AI coding models without native vision the ability to analyze images — screenshots, error messages, UI mockups, and documents — through a single unified image understanding tool. It routes requests to multiple vision model providers ( | |
| LAPRAS MCP Server baker71/lapras-mcp-server Enables users to search and view job postings, and to retrieve or update their professional history, job summary, career aspirations, and technical skills through natural language. | |
| pyhood-mcp bakernyc/pyhood-mcp Connect your Robinhood account to Claude Code (or any MCP client) for conversational portfolio management and automated trading. | |
| Notion-Anki MCP Server bakhruhk/notion-anki-mcp Automatically generates Anki flashcards from Notion pages by extracting questions and answers from toggle blocks. Uses OpenAI to enhance card quality and imports them directly into Anki via AnkiConnect for spaced repetition learning. | |
| @bakhshb/proxmox-mcp-openapi bakhshb/proxmox-mcp-openapi An OpenAPI-driven MCP server for Proxmox VE that provides 2 generic tools to execute any of 480+ API operations dynamically, plus tools for executing commands inside VMs and containers, saving ~95% tokens. | |
| UniFi MCP Server bakhshb/unifi-mcp-openapi Control your UniFi network via AI with a lightweight 2-tool MCP server that supports both cloud and local UniFi controllers. | |
| hamravesh-mcp bakhtarimohammad/hamravesh-mcp MCP server to manage Hamravesh (Darkube) apps via the console's internal API, supporting read and write operations like listing apps, viewing logs, restarting, scaling, and updating environment variables. | |
| ChromeWire MCP bakhtiersizhaev/chromewire-mcp Real browser tabs for AI agents through a safe localhost MCP bridge, enabling control of Chrome tabs via MCP-compatible AI CLIs. | |
| Digest MCP Server bakhtiyork/digest-mcp Enables extraction of fully rendered web content from dynamic pages, SPAs, and infinite scroll sites using browserless.io, with support for configurable scrolling and wait times to capture JavaScript-generated content. | |
| Aare.guru MCP Server baking-bread/aareguru-mcp Provides access to real-time and historical water conditions of the Aare river in Switzerland, including water temperature, flow rates, swimming recommendations, and data from multiple monitoring locations along the river. | |
| Snippy bakker14268/snippy Enables AI assistants to discover and invoke tools for saving and retrieving code snippets, generating language-specific style guides and deep wiki documentation, and orchestrating multi-agent documentation workflows backed by semantic vect | |
| >Luma MCP bakker3211/luma-mcp Adds image understanding to AI assistants that lack native vision, letting them analyze code screenshots, error captures, UI layouts, documents, and OCR content through a single unified image_understand tool. It routes requests across multi | |
| Patent Creator MCP Server bakker54/claude-patent-creator Enables any MCP-compatible client to search patent rules and statutes (MPEP, USC, CFR) with hybrid RAG retrieval, hunt prior art across 100M+ patents via Google BigQuery, run automated claim and application compliance checks, and generate p | |
| fcp-mcp-server bakker6109/fcp-mcp-server Enables Claude to read, edit, and generate real Final Cut Pro XML timelines, including cut detection, markers, role assignment, silence removal, transcript-based editing, keyframes, speed curves, and pushing projects into a running Final Cu | |
| Typst MCP Server bakker90/typst-mcp Enables AI models to convert LaTeX snippets to Typst, validate Typst syntax, retrieve documentation chapters, and render Typst code as PNG images. | |
| Tavily Web Search MCP Server bakshidwarak/aie8-mcp-session Enables web search capabilities through the Tavily API, allowing users to search the internet for information using natural language queries. Built as a demonstration MCP server running in stdio transport mode. |
32,751–32,800 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.