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 |
|---|---|
| MCP REST API Tester annika0476/mcp-rest-api Enables testing and interacting with any REST API endpoints directly from MCP clients such as Claude and Cline, supporting GET, POST, PUT, DELETE, and PATCH requests with detailed status, header, and body responses. It handles Basic, Bearer | |
| Gitingest-MCP annika3475/gitingest-mcp Enables MCP clients such as Claude Desktop, Cline, and Cursor to quickly extract GitHub repository information, including repository summaries, project directory structures, and file contents. | |
| Federal Reserve Economic Data MCP Server annikaaguilar/fred-mcp-server Enables users to browse, search, and retrieve over 800,000 economic time series, with support for transformations, frequency aggregation, and date-range filtering. | |
| Luma MCP annikaharrison8227/luma-mcp Enables AI coding models without native vision to analyze screenshots, errors, UI, documents, and OCR images through a single image_understand tool using multiple major vision LLM providers. | |
| pfSense MCP Server annikaleone557/pfsense-mcp-server Enables natural-language management of pfSense firewalls through MCP clients, covering firewall rules, VPNs, DNS, DHCP, diagnostics, configuration backup, and safety guardrails for destructive changes. It supports wire-format-verified opera | |
| MCP-Discord annikamendoza/mcp-discord Enables AI assistants to log in as a Discord bot and manage servers, channels, categories, forum posts, messages, reactions, roles, members, and webhooks. It supports searching and editing messages, setting channel permissions, and creating | |
| scrcpy-mcp annikaokada61/scrcpy-mcp Enables AI agents to see and control Android devices through ADB and scrcpy, including screenshots, taps, swipes, typing, app management, UI inspection, file transfer, shell commands, audio/video streaming, and clipboard access. | |
| AgentQL MCP Server annikasidorov/agentql-mcp Enables extracting structured data from web pages by specifying a URL and a natural-language prompt describing the desired fields and format. | |
| Blockbench MCP Pro anningui/blockbench-mcp-pro Enables AI clients to control Blockbench for 3D modeling, including geometry, UV, texturing, animation, procedural generation, quality gates, and human review via 95 tools over HTTP or stdio. | |
| byob annnguyen40/byob A local MCP server that lets AI coding tools drive the user's own already-logged-in Chrome through a companion extension, using snapshots and refs to click, type, navigate, read, screenshot, and inspect pages. It enables automation of authe | |
| wow-casc-mcp-server annoft/wow-casc MCP server for reading World of Warcraft client files via CASC storage, enabling file discovery and content retrieval. | |
| ui-kit annondeveloper/ui-kit Native Claude Code integration for @annondeveloper/ui-kit — a zero-dependency React component library with 147 components, 3 weight tiers, physics-based animations, and OKLCH color system. Gives Claude deep awareness of the library's compon | |
| yagna-mcp annoyinggoods/yagna-mcp Exposes a local SQLite catalog of your GitHub stars — READMEs, licenses, topics, tags, notes, and fit scores — as fifteen read and write tools for a coding agent over stdio, with spend-limited live GitHub search, refresh, and sweep calls. I | |
| MiniMax-Coding-Plan-MCP annr31762/minimax-coding-plan-mcp Enables MCP clients to perform AI-powered web searches and analyze images from URLs or local files, returning structured results and visual insights to assist code development workflows. | |
| MS 365-21V MCP Server annr31762/ms-365-21v-mcp-server Enables MCP-capable AI clients to act as the signed-in user against 21Vianet Microsoft 365 through Microsoft Graph China, reading mail, analyzing calendar conflicts, and searching OneDrive and SharePoint files. It preserves existing user pe | |
| CloakBrowser MCP anntrinh99832/cloakbrowser-mcp Enables AI agents to drive a Playwright-compatible browser (with humanized mouse, keyboard, and scroll behavior, persistent profiles, extensions, and GeoIP-aware proxies) to research the web, automate daily tasks, and run tests, with unchan | |
| MCP Security Scanner anntsmart/mcp-security-scanner Automatically discovers and tests MCP services for security vulnerabilities including command injection, SQL injection, SSRF, path traversal, and sensitive data exposure with detailed reports and remediation guidance. | |
| lingbot-mcp annwo2025-a11y/lingbot-mcp MCP server exposing Lingbot's creation tools, public links, and model availability through three simple tools. | |
| Orquestrador de Sites annygabb/orquestrador-de-sites Enables users to browse, search, filter, and select project skills through an interactive interface, then confirms the selection so the chosen instructions and customizations are applied to the site project. | |
| GCAL-MCP annyzhou/gcal-mcp A Model Context Protocol server that provides read-only access to the Google Calendar API v3. It enables users to list calendars, search for events, check free/busy availability, and retrieve calendar settings. | |
| Gmail MCP annyzhou/gmail-mcp A read-only MCP server that enables users to interact with the Gmail API to search messages, retrieve threads, and download attachments. It supports standard Gmail query operators and requires OAuth authentication for secure read-only acces | |
| notion-mcp annyzhou/notion-mcp Provides comprehensive tools to interact with the Notion API, including managing pages, databases, blocks, and comments via OAuth2 authentication. It enables users to search content, create workspace entries, and manage metadata through the | |
| slack-mcp annyzhou/slack-mcp Enables comprehensive interaction with Slack workspaces, allowing users to manage channels, send messages, and search history. It supports managing reminders, pins, reactions, and user information through the Model Context Protocol. | |
| eurostat-mcp ano-kuhanathan/eurostat-mcp A Model Context Protocol (MCP) server that provides tools to query Eurostat APIs for European statistics data. | |
| ui-toolkit-mcp anomal3/ui-toolkit-mcp Local, free MCP server for brand logo search and shadcn/ui component search & source lookup, requiring no API keys or login. | |
| ahk-mcp anomalous3/ahk-mcp Enables AI agents to control Windows systems using AutoHotkey v2 and the UI Automation accessibility tree for efficient, text-based computer interaction. It provides tools for window management, keystrokes, and UI inspection while significa | |
| ember-4 anomalous3/ember-4-memory Gives Claude persistent memory across sessions by recalling stored embers through graph-aware retrieval that fuses semantic embeddings, BM25 lexical search, engagement signals and PageRank-style traversal, with superseded memories hidden un | |
| macbot-mcp anomalous3/macbot-mcp Enables AI agents to control macOS applications through the Accessibility API, AppleScript, and CGEvents, providing structured text output of UI elements and actions without needing screenshots. | |
| AnomalyArmor anomalyarmor/agents Data observability for AI agents. Query alerts, monitor freshness, investigate schema drift, and trace lineage across your data warehouse via 53 MCP tools. | |
| browse anomalyco/browse Lets AI agents drive the user's real Chromium browser, including opening and controlling tabs, taking screenshots, capturing network traffic, recording screen activity, and handing control back for logins or payments while using the user's | |
| citetrail anonb3ll/citetrail Enables AI agents to search and recall locally captured browser pages with full source provenance (URL, title, timestamp) over MCP. | |
| Universal Device MCP anonyme-afk/universal-device-mcp Enables an AI agent to discover connected hardware, inspect host-exposed interfaces, communicate through generic transport operations, and retain per-device knowledge between connections. | |
| Telegram MCP anonymouse8882/telegammcp Enables MCP clients to interact with Telegram user accounts, providing tools for messaging, contacts, groups, channels, and media management through the Telegram API. | |
| PVsyst CLI MCP anonymousnake/pvsyst-cli-mcp Enables local control of an installed PVsystCLI 8 on Windows, letting a client check license quota, list workspace projects and variants, build SFI definitions, run existing project/variant simulations, convert staged weather data into MET | |
| avv-mcp anonymusdeveloper1/mcp-agentvideoviewerdownloader Enables AI agents to download, convert, and visually analyze videos by providing timestamped frames and locally transcribed speech, all without API keys. | |
| precedents anonypotamus/precedent-graph Enables MCP clients to query a FalkorDB citation graph of Indian Supreme Court judgments, determine whether cited authorities remain good law, trace overruling and reliance through multi-hop evidence paths, and access case-law tools or read | |
| UIKit MCP Server anoochit/uikits_mcp_server A Model Context Protocol server that provides Flutter UI templates for development. It enables users to access and integrate pre-built Flutter UI components through MCP-compatible client applications. | |
| VeriSom anoop04singh/verisom Scores contract safety for Somnia Agents using on-chain analysis, RAG, and a VeriSom contract, returning a pre-interaction safety score. | |
| Sweet Assist MCP Server anoopmkmk/sa-mcp Standalone MCP server exposing Sweet Assist transactions, contacts, envelopes, and agent profiles to Claude, behind an OAuth 2.1 login and approve flow. | |
| TfL Journey Status MCP Server anoopt/london-tfl-journey-status-mcp-server Provides real-time access to Transport for London data, enabling users to check tube line statuses, get disruption details, and plan journeys between London locations. Uses the official TfL Unified API to deliver live transport information | |
| Outlook Meetings Scheduler MCP Server anoopt/outlook-meetings-scheduler-mcp-server Allows scheduling meetings in Microsoft Outlook using Microsoft Graph API, with features for creating calendar events and adding attendees by finding their email addresses. | |
| Remote MCP Entra ID Todo anoopt/remote-mcp-entra-id-todo Enables comprehensive Microsoft To Do task management through Microsoft Graph API with Entra ID OAuth authentication. Supports creating, updating, and managing todo lists, tasks, reminders, and due dates through natural language. | |
| tfl-mcp-server anoopt/tfl-mcp-server Provides real-time Transport for London data including line status, journey planning, and disruption information via the TfL Unified API. | |
| MCP ToDo Server anorebel/mcp-todo-server A production-ready Model Context Protocol server for managing tasks and todos with support for both file-based and database storage backends. It enables users to perform bulk operations, track priorities, and access productivity analytics t | |
| Factorio Planner MCP anormlylee/factorio-planner-mcp Enables ChatGPT and other MCP clients to search Factorio recipes and entities and calculate steady-state production networks, including machine and module settings, location restrictions, byproducts, recycling loops, and barrel transport. | |
| COA Goldfish MCP anortham/coa-goldfish-mcp A lightweight short-term memory MCP server that automatically stores and recalls working context, session state, and task progress for AI agents. Memories auto-expire after 24 hours and integrate seamlessly with workspace-aware storage acro | |
| mcp-lab-workshop anoshvi/mcp-lab-workshop A Cloudflare Workers-based MCP server that provides tools to control an interactive dashboard in real-time, including toggling features, updating stats, setting messages, and simulating traffic. | |
| driftglass anotb/driftglass MCP server that maintains cited, current answers to standing research questions by tracking chosen sources, consolidating repeated coverage, and providing evidence-based briefs with change signals. | |
| x-signal anotb/x-signal Let ChatGPT or Codex research X (Twitter) through an existing account: search Top and Latest, follow threads, compare feeds, find accounts, and link posts. Read-only, local Docker service. | |
| standards-mcp anotherben/standards-mcp Transforms static coding standards into a queryable live data store for AI agents, delivering task-specific rules and fix guidance on demand. This optimizes context window usage through progressive disclosure, ensuring agents apply relevant |
29,351–29,400 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.