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 |
|---|---|
| WhatsApp Channel alexeifoster85401/whatsapp-claude-plugin Enables a Claude Code session to send and receive WhatsApp messages through either a linked device or the official Cloud API, including media, voice-note transcription, polls, and per-group personalities. Inbound messages are gated by pairi | |
| repo-reader-mcp alexeiveselov92/repo-reader-mcp Enables AI agents to read and search code across many git repositories — files at any branch, tag or commit, history, diffs, blame and cross-repo search — over local paths or remote hosts like GitHub, GitLab and Bitbucket. It is read-only b | |
| semantic-warehouse-mcp alexeiveselov92/semantic-warehouse-mcp Enables AI agents to safely describe, query, and compute metrics across SQL databases using open-format semantic models, custom context, and skills, with read-only and dialect-checked execution. | |
| Crawl4AI+SearXNG MCP Server alexesom/crawl4ai-rag-mcp-gemini Enables AI agents to search the web, crawl websites, and perform intelligent RAG queries with semantic search capabilities. Includes integrated private search engine, vector database storage, and optional knowledge graph for AI hallucinatio | |
| iCloud CalDAV MCP Connector alexey-fedorov-com/icloud-mcp-old An MCP server that enables interaction with iCloud Calendars via the CalDAV protocol using an app-specific password. It allows users to list, create, update, and delete calendar events through MCP-aware clients like ChatGPT. | |
| AI Content Moderation MCP Server alexey-tyurin/ai-agent-mcp Enables content moderation by checking user input against OpenAI's moderation API via Google ADK, with dual SSE/STDIO transport support and integration with local LLMs. | |
| MCP Connector - Follow Up Boss alexey0424/mcp-connector-followupboss A remote MCP server on Cloudflare Workers that allows real-estate sales teams to query their Follow Up Boss CRM data through Claude, with read-only, role-based access and OAuth authentication. | |
| project-helper alexey5558899-art/mcp Enables AI assistants to safely read and search project files within a configured root directory, supporting regex search, file listing, line-range reading, and symbol usage lookup. | |
| HH JIRA MCP Server alexeydubinin/hh-jira-mcp-server A Model Context Protocol server that enables integration with JIRA, allowing users to interact with JIRA tasks and issues through Claude AI assistant. | |
| Agent Browser Bridge alexeygrigorev/agent-browser Enables AI agents to control an existing signed-in Chrome profile through MCP stdio, using its current tabs, cookies, and logins without pairing or a separate browser. It exposes tab management, page interaction, screenshots, and Chrome Dev | |
| LexiconLocal alexeymohr/lexiconlocal Enables coding agents to search a local, offline archive of past sessions and repository Markdown docs using hybrid lexical and semantic retrieval, and read matching records to ground new work in prior knowledge without external calls. | |
| VaultPDF MCP alexeysamosadov/vaultpdf-mcp A local PDF manipulation server for AI agents that provides tools for merging, splitting, extracting info, and converting images to PDF, all without uploading files. | |
| mcp-memory-sqlite alexfayers/mcp-memory-sqlite A personal knowledge graph and memory system for AI assistants using SQLite with FTS5 full-text search, enabling persistent memory across conversations with Claude or any MCP-compatible AI. | |
| ClickUp API MCP alexfdez1010/clickup-mcp Enables MCP clients to discover and execute 172 ClickUp API v2 and v3 operations using a personal API token, covering tasks, Workspaces, Spaces, Folders, Lists, comments, custom fields, time tracking, webhooks, Docs, and Chat. Includes read | |
| Holded API MCP alexfdez1010/holded-mcp Enables MCP clients to search and execute 360 operations across Holded's accounting, sales, inventory, contacts, CRM, projects, team, calendar, inbox, and developer APIs. Supports read and write calls with an API key, including a read-only | |
| Instagram MCP Server alexfisenkov/instagram-mcp-starter MCP server that connects AI agents to Instagram for reading statistics, insights, and comments via the official Meta Graph API. | |
| Tokopedia Personal MCP alexfisenkov/tokopedia-personal-mcp Enables local import and querying of Tokopedia purchase data, including orders, shipments, payments, chats, and products, with record history, draft seller messages, and budget-aware purchase plans. It supports search, filtering, pagination | |
| VK MCP alexfisenkov/vk-mcp Enables agents to work with VK communities over Streamable HTTP by managing posts, comments, dialogs, statistics, photos, videos, and products with scoped API access, explicit write plans, and secure media workflows. | |
| WhatsApp MCP alexfisenkov/whatsapp-mcp Enables AI clients to read and send WhatsApp chats, messages, contacts, groups, polls, reactions and media through two isolated adapters — a personal linked-device runtime and the official Meta Business Graph API — each with per-profile cre | |
| terminal-emulator-mcp alexforster/terminal-emulator-mcp Enables agents to launch and control interactive terminal sessions, inspecting screen text and formatting while sending keyboard and mouse input. Supports real pseudoterminals with resizing, snapshots, and session lifecycle management. | |
| mcp-shield alexfraser-scotch/mcp-shield Zero-overhead runtime security proxy, reversible secret vault, and audit firewall for MCP servers in Cursor, Claude Desktop, and Windsurf. | |
| Murmur alexfrmn/murmur Encrypted agent-to-agent messaging for AI agents via NATS JetStream, enabling autonomous, secure communication and collaborative workflows. | |
| mcp-ynab alexfu/mcp-ynab FastMCP server that exposes the YNAB API for budget management, enabling interaction with YNAB data through MCP tools. | |
| Garmin Connect MCP alexgarciaper/garmin-connect-mcp Enables querying your Garmin Connect data including recent activities, detailed metrics, and daily stats through natural language. | |
| ecommerce-fashion-market-analysis alexgenovese/ecommerce-fashion-market-analysis A fashion vertical MCP server providing tools for product SEO audits and trend analysis to integrate with AI agents like Claude, Cursor, and Codex. | |
| Matomo MCP Server alexgenovese/matomo-mcp Enables LLMs to directly query a Matomo analytics instance, execute reporting methods, fetch historical trends, report metadata, and dynamically generated chart images through typed MCP tools. | |
| mcp-arxiv alexgenovese/mcp-arxiv An MCP server that enables AI assistants to search arXiv papers, retrieve metadata, and access PDFs. | |
| mcp-fleet-worker alexgenovese/mcp-fleet-worker Spawn headless OpenCode workers on cheap models to delegate expensive tool-using tasks to a fleet of parallel workers with isolated git worktrees. | |
| wordpress-mcp alexgenovese/mcp-wordpress MCP server for WordPress REST API that enables managing posts, pages, media, comments, categories, tags, and users through 20 tools. | |
| strata-mcp alexgenovese/strata Enables AI agents to run multi-layer web search with Hindsight TEMPR ranking, pack results into a strict max_tokens budget, and extract HTML, PDF, and JavaScript SPA content through 12 native MCP tools. It also supports site mapping, simila | |
| agent-memory alexgherrera/agent-memory Enables AI agents to keep and query long-term memory of past conversations, with hybrid keyword-plus-semantic search, session, day, week, month and year summaries, saved notes, and a running set of current facts about the user. Exposes this | |
| Agentic MCP Itinerary alexgherrera/agentic-mcp-itinerary An MCP server that orchestrates parallel searches for flights, hotels, and activities to generate travel itineraries. It features persistent state management via LangGraph and SQLite while ensuring the total cost remains within a specified | |
| Claude Mobile alexgladkov/claude-in-mobile Enables mobile device automation for Android (via ADB) and iOS Simulator (via simctl), allowing you to control devices with natural language through screenshots, UI interactions, text input, and app management. | |
| Wangsu Terraform Knowledge Base MCP Server alexgoflexx/wangsuterraform-mcp A retrieval-only MCP server that searches a vectorized Wangsu Terraform Provider documentation knowledge base and returns relevant snippets with rules to guide the caller's LLM in generating accurate, provider-specific answers. It offloads | |
| Illumio MCP Server alexgoller/illumio-mcp-server A Model Context Protocol server that enables conversational AI interaction with Illumio PCE for security policy management, workload operations, traffic flow analysis, and compliance assessment. | |
| exercicio-4.2-todo-mcp alexgoncalves-cpu/exercicio-4.2-todo-mcp MCP server that provides tools to create and list tasks by consuming a REST API, allowing LLMs to manage a TODO list via natural language. | |
| interclaude alexgoodell/interclaude Enables peer-to-peer communication between Claude Code sessions, allowing them to send messages, hand off tasks, and coordinate across worktrees without manual intervention. | |
| XS Shlink MCP alexgreenuk/xs-shlink-mcp Enables to manage and analyze a Shlink URL-shortener instance with tools for short URLs, visits, tags, domains, redirect rules, QR codes, and Mercure integration. | |
| RemNote MCP Bridge alexhagemeister/remnote-mcp-bridge Bridges RemNote knowledge base with AI assistants via MCP, allowing AI to read, create, search, and update notes in your personal knowledge management system. | |
| Excel MCP Server alexhb-maker/mcp-excel-fiance Local MCP server that connects Claude to real Excel .xlsx files for financial and operational analysis. Enables reading, comparing, cleaning, reconciling, and writing to Excel files without cloud dependency. | |
| MCP PowerBI Controller alexhb-maker/mcp-financial-controller Enables Claude to read, analyze, and write directly to local Power BI semantic models and Excel workbooks without exporting to the cloud. | |
| upservice-mcp alexherbaly/upservice-mcp Manages employees, projects, sprints, tasks, tags, directories, and channel messages via the Upservice Public API. | |
| Canvas LMS MCP Server alexherman11/canvas_mcp Enables Claude to interact with the Canvas LMS API to manage courses, assignments, grades, and communications. It supports both remote and local deployments, allowing users to query academic data and submit assignments via natural language. | |
| MCP Spreadsheets alexherranr/mcp-spreadsheets Provides comprehensive control over Google Sheets to read, write, format, and manage spreadsheets directly through natural language. It includes extensive tools for data manipulation, conditional formatting, and cell protection, along with | |
| MCP Obsidian alexhholmes/mcp-obsidian Enables semantic search across Obsidian vaults using vector embeddings and ChromaDB. Supports multiple vaults with real-time indexing and provides both MCP server and CLI interfaces for natural language querying of notes. | |
| Gmail MCP Server alexhramovich/gmail-mcp A Model Context Protocol (MCP) server that enables Claude Desktop to interact with Gmail through secure OAuth 2.0 authentication. Send emails, search messages, read emails, and manage multiple Gmail accounts directly from Claude Desktop. | |
| Excel MCP Server alexhuangc/excel-mcp-server Enables AI agents to create, read, and manipulate Excel files without requiring Microsoft Excel installation. Supports comprehensive spreadsheet operations including formulas, formatting, charts, pivot tables, and data validation. | |
| MCP Chat Logger alexifeng/mcp_chat_logger A tool that preserves chat history as Markdown files, automatically adding timestamps and supporting conversation identification through session IDs. | |
| MCP Vector Proxy alexiokay/simple-mcp-proxy A semantic proxy that reduces AI agent token usage by exposing only three core tools and using local vector embeddings to search for and execute hundreds of underlying MCP tools. It streamlines communication between agents and MCP Routers b | |
| Cinema4D MCP Server alexiou024/cinema4d-mcp Enables prompt-driven creation and manipulation of Cinema 4D scenes, including objects, cameras, lighting, materials, MoGraph, dynamics, and rendering, through MCP tools. |
26,251–26,300 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.