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 |
|---|---|
| grok-computer-mcp bo-516/computer-use Enables an agent to observe and operate desktop apps and browsers through an accessibility-tree-first view, with clicking, typing, scrolling, dragging and waiting tools. Screenshot handling, coordinate mapping and fail-closed safety rules ( | |
| MCP Cliniko Server boabai/mcp-cliniko Provides comprehensive integration with the Cliniko API for healthcare practice management, including patient, appointment, and invoice administration. It enables tools for complex clinical workflows and direct access to practice resources | |
| depreciation-mcp boam79/depreciation-mcp Provides Korean corporate tax-based fixed asset depreciation calculations and tax adjustment references through MCP. Enables users to retrieve useful life periods, calculate depreciation schedules, and compute tax adjustments for single or | |
| gov-support-mcp boam79/gov_support_mcp An MCP server that automates the entire process of discovering, evaluating, and applying for government support programs in South Korea using natural language. It integrates multiple public APIs to provide eligibility checks, document prepa | |
| bobs-cloudflare-mcp bob-fornal/ai-bobs-cloudflare-mcp Serves a curated Markdown collection of Cloudflare Workers, Durable Objects, D1, KV, and Workers AI learnings to MCP clients over HTTP, exposing it as a readable resource and a callable tool. | |
| Grok MCP Plugin bob-lance/grok-mcp Provides seamless access to Grok AI's capabilities (chat completion, image understanding, and function calling) directly from Cline via the Model Context Protocol. | |
| Instagram Engagement MCP bob-lance/instagram-engagement-mcp Provides tools for analyzing Instagram engagement metrics, extracting demographic insights, and identifying potential leads from Instagram posts and accounts. | |
| mcp-brasil bob-reis/mcp-brasil MCP Server for accessing 36 Brazilian public data sources and 1 agent, enabling AI agents to query government data on economy, legislation, transparency, judiciary, elections, environment, health, and more. | |
| Reel Studio MCP bob-six/reel-studio-mcp Enables creating and editing RezonAI reels, preparing lyrics, and rendering previews and exports through MCP tools, with rendering and storage handled by the RezonAI backend. Supports hosted OAuth connections or a local stdio connector with | |
| TensorsLab MCP Server bob5-tensorslab/mcp Enables AI-powered image and video generation through the TensorsLab API using models like SeeDream and SeeDance. It supports tasks such as creating high-resolution media from text prompts, image-to-video conversion, and monitoring generati | |
| search-reader-mcp bob56621517/search-reader-mcp MCP server extending Jina Reader to provide web page/PDF to Markdown reading and Bocha AI/web search via a single HTTP endpoint, exposing read, search, and MCP tools. | |
| Google Chat MCP Server bobamayer/google-chat-mcp Enables LLM clients to send messages to Google Chat spaces, list spaces, and search message history. | |
| hn-mcp bobasaki/hn-mcp Enables browsing Hacker News feeds, retrieving stories and flattened comment threads by id, full-text and date-filtered story search, and user profile lookups through five read-only tools backed by the Firebase and Algolia APIs. Comment tre | |
| Unofficial AnyList MCP Server bobby060/anylist-mcp MCP server that integrates with AnyList for managing shopping lists, recipes, and meal planning via natural language. | |
| Weather MCP Server bobby169/mcp-server-weather A Model Context Protocol server that provides current weather forecasts for specific locations and active weather alerts for US states. | |
| Remote MCP Server (Authless) bobby38/remote-mcp-server-authless A deployable MCP server on Cloudflare Workers that doesn't require authentication, allowing connection from the Cloudflare AI Playground or Claude Desktop to use custom tools via the Model Context Protocol. | |
| Andrew Social Bridge bobbygodias/andrew-social-bridge A safety-gated MCP bridge for the Instagram API, enabling read-only profile and recent-post access and draft preparation of image posts with human approval for publishing. | |
| Ordinal-MCP bobbyhiddn/oracle-mcp Implements a structured communication bus that allows AI agents to send 'oracle calls' to human operators for resolving complex decisions or judgment calls. It facilitates hierarchical message passing between agents and humans using a file- | |
| Sympathy-MCP bobbyhiddn/sympathy-mcp An MCP server for managing Incus virtual machines through structured tools for command execution, file management, and snapshot operations. It enables AI agents to puppeteer VMs on a masternode by wrapping the Incus CLI. | |
| service-template bobbylite/service-template Exposes the shared health-check service as an MCP tool, letting clients query status, uptime, and version through the streamable HTTP endpoint. | |
| MCP Server Healthcare bobbynoble/mcp_server_healthcare Enables NHS clinical coding, SAR/FOI tracking, DSAR processing, batch coding, and patient data operations via a Cerner FHIR R4 sandbox through MCP tools. | |
| LightScout MCP bobbyrgoldsmith/lightscout-mcp Core Web Vitals analysis powered by Lighthouse. Four tools: analyze a URL, compare two URLs, check against thresholds, or crawl an entire site. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible AI tool. | |
| apillow-mcp bobbyseamoss/apillow-mcp Zillow property data for AI agents — search listings by city or ZIP, look up any US address, and get 50+ fields per property including prices, Zestimates, price history, and sold data. | |
| Weather MCP Server bobbyyng/weather-mcp-ts A TypeScript-based MCP server that provides simulated weather data including current conditions, forecasts, alerts, and location search functionality through both MCP protocol and HTTP API endpoints. | |
| playwright-fixer-mcp bobchochola/e2e-fixer-mcp Automated Playwright E2E test repair powered by a self-improving, governed MCP server that runs failing tests, collects failure artifacts, reasons about root causes, validates and applies fixes, and re-runs to verify. | |
| ZimaTools bobdivx/zimatools Enables ZimaOS-native file operations, Docker container management, and exclusive GPU VRAM lease arbitration with priority-based preemption and queueing via MCP tools and REST endpoints. | |
| WeChat Publisher MCP bobgod/wechat-publisher-mcp A Model Context Protocol server that enables AI tools to automatically publish articles to WeChat Official Accounts, supporting Markdown-to-HTML conversion, image handling, and both preview and official publishing modes. | |
| MCP ChatGPT Multi-Server Suite bobhuff0/mcpaddin A comprehensive suite of four MCP servers providing real-time stock market data, currency conversion between 160+ currencies, world timezone conversion, and unit conversion across 10 measurement categories. Features beautiful web interfaces | |
| Telegram MCP Server bobidk91-ops/telegram-mcp-server Enables interaction with Telegram channels through the Bot API, supporting comprehensive messaging operations including sending text/photos, creating polls, managing reactions, and editing/deleting messages. Provides complete channel manage | |
| foo-ai bobini1/foo_ai MCP control for foobar2000. Control your music player with an AI assistant! | |
| taf-mysql-mcp bobjoy/taf-mysql-mcp Enables AI agents to safely execute MySQL queries through a TAF data-access service, with read-only defaults, DDL blocking, and no need for local database credentials. | |
| DeepSeek Harness Plugin MCP bobleer/deepseek-harness-plugin-mcp MCP server that lets AI agents discover, inspect, install, and run DeepSeek Harness plugins via MCP, bridging the gap between the MCP protocol and Cordis-based plugin bundles. | |
| windeep-computer-control bobliang1979/windeep-computer-control Windows原生桌面自动化MCP服务器，提供22个工具用于窗口管理、输入控制、截图、OCR和智能元素匹配。 | |
| fetch-log-mcp-server bobliu1996/fetch-log-mcp-server An MCP server that fetches remote logs from specified IP addresses via HTTP, with configurable port and log path. | |
| MCP MySQL Server bobliu1996/mcp-server-mysql A MySQL MCP server with DDL support, permission control, and operation logging, enabling SQL query execution, database info retrieval, and schema management. | |
| Bitbucket MCP Server bobmaertz/bitbucket-mcp Enables AI assistants to interact with Bitbucket Cloud repositories, allowing users to manage pull requests, comments, tasks, and branches through natural language commands. | |
| MCP Browser bobmatnyc/mcp-browser An MCP server for browser automation and console log capture via a Chrome extension, enabling AI-driven DOM interaction, navigation, and screenshot capabilities. | |
| mcp-memory bobmatnyc/mcp-memory A standalone memory service that provides persistent storage for AI assistants via the Model Context Protocol. | |
| MCP Memory Service - TypeScript bobmatnyc/mcp-memory-ts A cloud-based vector memory service that provides AI assistants with persistent storage, semantic search, and entity management via the Model Context Protocol. It features multi-tenant isolation and bidirectional synchronization with macOS | |
| mcp-skills bobmatnyc/mcp-skillset Provides dynamic, context-aware code assistant skills through hybrid RAG (vector + knowledge graph), enabling runtime skill discovery, automatic toolchain-based recommendations, and on-demand loading from multiple git repositories. | |
| mcp-vector-search bobmatnyc/mcp-vector-search A CLI-first semantic code search tool with MCP integration for AI assistants, enabling semantic search, AST-aware parsing, and code analysis across 13 languages. | |
| mdbook bobmatnyc/md-book Enables AI assistants to read, write, and manage markdown books with multi-format support and interactive features. | |
| notion-mpm bobmatnyc/notion-mpm Enables interaction with Notion workspaces through a comprehensive set of tools for managing pages, blocks, databases, users, comments, and search. Provides both a clean Python API and an MCP server for use with Claude Desktop. | |
| slack-mpm bobmatnyc/slack-mpm MCP server for Slack workspace integration, exposing 40+ Slack operations as tools for Claude Desktop and providing a clean async Python API. | |
| mcp-ephemeral-k8s bobmerkus/mcp-ephemeral-k8s Enables spawning ephemeral Model Context Protocol (MCP) servers on Kubernetes using Server-Sent Events (SSE), supporting multiple runtimes. | |
| nodriver-proxy-mcp bobongku/nodriver-proxy-mcp Gives AI agents a browser that bypasses bot detection, a MITM proxy for traffic interception, and a Python sandbox to autonomously write and execute security exploits. | |
| ASCIIFlow MCP Server bobooooo/asciiflow-mcp Exposes ASCIIFlow drawing primitives as tools to enable AI assistants to generate ASCII wireframes and diagrams from natural language descriptions. It provides commands for creating canvases and drawing boxes, lines, arrows, and text using | |
| moysklad-mcp-ru bobrovaolesyaekb/https-github.com-ilyautov-moysklad-mcp-ru Enables AI assistants to query and manage a MoySklad account through the JSON API 1.2 — reading stock, products, orders, counterparties and reports, and creating, posting or deleting documents — with a two-layer safety gate that keeps write | |
| Codebank bobrowsse-tech/codebank Enables users to deposit reusable code selections into a local bank and search, retrieve, and insert them into any project. Everything stays as plain files on the local machine, with nothing written into a project or sent over the network u | |
| Neyvia PDF Studio bobthecomputer/neyvia-app-pdf Interactive PDF workspace shared by a human operator and an AI agent, enabling navigation, search, text extraction, annotations, form filling, and save actions via a PDF.js viewer. |
34,901–34,950 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.