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-screenshot beekamai/mcp-screenshot A small Model Context Protocol (MCP) server that gives an LLM eyes on your desktop without burning context. It can take one-off screenshots, crop a region around the mouse cursor, and run timed streaming sessions that save frames to disk an | |
| WASM MCP Server beekmarks/mcp-wasm This server enables running a Model Context Protocol in a web browser with functionalities including arithmetic operations and session-based key-value storage. | |
| context-usage-mcp beeltec/context-usage-mcp Exposes a get_context_usage tool that reports raw token usage from session transcripts for Claude Code and OpenAI Codex CLI, enabling agents to check context size and branch behavior. | |
| mailmcp beeltec/mailmcp Enables controlling Apple Mail on macOS through JavaScript for Automation, using already-configured accounts without passwords. Supports listing accounts and mailboxes, searching and reading messages, managing folders and message state, han | |
| Beelzebub MCP Honeypot beelzebub-labs/beelzebub Description:
Introduce Beelzebub, an MCP‑based honeypot framework that enables creating decoy tools to detect prompt injection and malicious agent behavior.
Motivation:
Strengthen the security of LLM workflows by adding a non‑intrusive det | |
| MyChart Care Record Connector beenlouis/mychart-mcp Enables AI assistants to securely read and organize a patient's own health records from Epic MyChart via the FHIR API, including labs, documents, appointments, and attachments, using OAuth-based authorization. | |
| openbanking-mcp beennnn/openbanking-mcp MCP server for read-only access to bank accounts via Open Banking (DSP2/AIS). It retrieves balances, transactions, and forecasts upcoming debits to prevent overdrafts, with optional daily Todoist briefs. | |
| datagovin-mcp beenthatt-rehman/datagovin-mcp Enables natural-language access to India's Open Government Data platform, letting users discover datasets, inspect schemas, and query live data from data.gov.in. | |
| COP Plug beepoo304/cop-plug Enables AI assistants to execute PowerShell commands, manage files, inspect projects, run Git operations, and monitor system information on Windows through a local MCP server. | |
| mcp-mail-macos beeraw/mcp-mail-macos An MCP server that drives macOS Mail: read, search, send, organise. | |
| eqanun-api beerbottle90/eqanun-api MCP server for Azerbaijan's official legal-acts database (e-qanun.az), enabling search, metadata retrieval, and full-text access to legislative and judicial documents. | |
| lex-scholar-api beerbottle90/lex-scholar-api Single-endpoint MCP server federating nine open-access legal scholarship indexes, enabling federated search, multi-jurisdiction comparison, and full-text retrieval via tools like search_legal_scholarship and compare_jurisdictions. | |
| agent-firewall beernathan87/agent-firewall Sits in front of any MCP server to enforce allow/ask/block policies on tool calls, paths, shell commands, and network domains, with local approval prompts and an audit log. | |
| openapi-mcp beernathan87/openapi-mcp-generator Exposes selected operations of an existing REST/OpenAPI app as MCP tools with generated schemas, permission annotations, and a risk class, requiring explicit opt-in before anything is listed and a second flag for destructive calls. Enforces | |
| Spotify Overload - More Tools (18) | More Functions | More Rocking Out beerspitnight/spotify-mcp-enhanced-music-overload MCP server for Spotify playlist curation and management. 18 tools for song analysis, smart playlist creation, top tracks analysis, and automated recommendations. | |
| contextforge-mcp beethovkjfe/contextforge-cli Enables AI-powered IDEs to access live project conventions, prior decisions, and relevant context through four purpose-built tools. | |
| ClawLab beezia/clawlab Enables AI agents to orchestrate high-throughput screening and life-science laboratory workflows through MCP, including experiment planning, simulated instrument execution, assay QC, candidate hit analysis, and next-experiment recommendatio | |
| israel-weather-mcp-agent bef99/israel-weather-mcp-agent Provides MCP tools to fetch weather forecasts for Israeli cities using browser automation with Playwright, without relying on external APIs. | |
| WooCommerce MCP Server (Cloudflare Workers Edition) befantasy/woocommerce-mcp-cloudflare-worker Enables AI clients to manage WooCommerce stores through 100+ tools covering products, variations, orders, refunds, customers, coupons, shipping, taxes, reports, media, and settings via a secure public HTTPS endpoint. | |
| mcp_server befree83/mcp_server A minimal MCP server providing currency conversion, geocoding, and weather tools, with a CLI client supporting Spanish special commands. | |
| bg-unified-publisher beganzzw/bg-unified-publisher Enables publishing image-and-text content to WeChat Official Accounts and Xiaohongshu from a single stdio MCP server, handling drafts, local image uploads, public submission, and idempotent per-platform actions without requiring separate co | |
| purchase-app-mcp begin2019510/purchase-app-mcp Exposes the 个人管家 app's purchasing, expense, todo, project, budget, and analytics data as MCP tools so agents can read and manage records through the app's authenticated business APIs. Each installation logs in with its own account, stores c | |
| ElevenLabs Voice-to-Voice Agent begwen/agentic-voice-ai-system---mcp-native- An MCP server that enables voice-to-voice AI conversations using ElevenLabs for speech synthesis and recognition, with tools for voice management, text-to-speech, and speech-to-text. | |
| MCP 101 Example behavioral-ds/mcp-example A foundational implementation of a Model Context Protocol (MCP) server designed for educational purposes. It demonstrates the complete interaction between an LLM, an inference engine, and a client during an agentic call. | |
| behavior-trees behaviortrees/behaviortrees Validates behavior trees for game AI and robotics, converts them between behavior3 JSON and BehaviorTree.CPP XML (Groot2, ROS 2 Nav2), and returns links that open them in the behaviortrees.com visual editor. Also provides built-in node docs | |
| flow-behind behindofficial/flow-behind-cli Enables MCP clients to generate Google Flow images and videos, check connection status, list jobs, and retrieve job results through a local browser bridge. | |
| Google Studio Behind MCP behindofficial/google-studio-behind-cli Enables AI agents to control Google AI Studio through a signed-in Chrome or Edge browser, including inspecting pages, entering prompts, operating visible controls, selecting models and settings, uploading context files, reading responses, a | |
| BlenderMCP behlulgoker/blender-mcp Connects Blender to Claude AI through the Model Context Protocol, enabling natural language control of 3D modeling, scene creation, and manipulation. | |
| cooper-hewitt-mcp behole/cooper-hewitt-mcp Interact with the Cooper Hewitt API with MCP. | |
| mcpwall behrensd/mcpwall mcpwall is a deterministic security proxy for MCP tool calls — iptables for MCP.
It sits between the MCP client and server, intercepting every JSON-RPC request and enforcing YAML-defined policies. | |
| kickbase-mcp behretv/kickbase-mcp Enables AI assistants to access Bundesliga fantasy football squads, budgets, lineups, transfer markets, player stats, fixtures, and real trading operations to build buy/sell strategies and optionally execute them. Supports read and trade to | |
| CloudreveMCP bei123/cloudrevemcp MCP server integrating Cloudreve with downloaders for Douyin, Bilibili, and Netease, enabling login, parsing links, downloading, and uploading to cloud storage with direct links. | |
| Browser MCP Gateway beifangzhishi-ops/browser-mcp-gateway Enables ChatGPT to securely control an existing Microsoft Edge session on Windows via OAuth-protected HTTPS, including tab management, navigation, page interaction, and file upload/download through an MCP proxy. | |
| CCM beifangzhishi-ops/codex-compatible-mcp Provides a Codex-inspired execution harness for MCP clients, enabling remote worker management, native sandboxing, PTY sessions, file patching, image reads, and deferred tool discovery. | |
| Windows Console MCP beifangzhishi-ops/windows-console-mcp Enables ChatGPT to control multiple registered Windows devices through a self-hosted gateway, routing Desktop Commander tool calls to specific workers by device ID. | |
| memory-palace-mcp beijingwahw/memory-palace Exposes a layered long-term memory store — persistent self blocks, four-tier scoped retrieval, knowledge graph, and signed knowledge capsules — over stdio so any MCP-capable client can use the same 15 memory tools and shared ACL. It lets Cl | |
| WordPress MCP Server beilunyang/wordpress-mcp-server Enables AI assistants to interact with WordPress blog systems for automated content management and publishing via the WordPress REST API. | |
| AutoCAD MCP Server - Codex Edition beiming183-cloud/autocad-mcp MCP server for full AutoCAD automation, AutoCAD LT automation, and headless DXF generation. It provides 8 consolidated tools for drawing, entity, layer, block, annotation, P&ID, view, and system operations via MCP stdio transport. | |
| ecom-mcp beinghadibadami/ecom-mcp An MCP server for e-commerce operations that enables AI agents to investigate stuck orders, surface fulfillment anomalies, and create escalation records via natural language queries. | |
| jambavan beingmartinbmc/jambavan An MCP server that provides coding models with a live code index, inferred code graph, durable memory, and surgical tools to help them leverage their existing reasoning and coding abilities effectively. | |
| @vn-skills/mcp beiryu/vn-skills Enables AI agents to build and parse VietQR payments, convert old 63-province addresses to the 34-province structure, validate tax IDs and e-invoices, turn money amounts into Vietnamese words, and convert between solar and lunar calendar da | |
| ComfyUI MCP Server beiwater/comfyui-mcp-server Enables AI agents to generate and iteratively refine images, audio, and video through natural conversation using a local ComfyUI instance. | |
| VSCode LSP MCP Server beixiyo/vsc-lsp-mcp An MCP server that exposes Language Server Protocol features to external clients, allowing access to hover information, definitions, completions, references, and rename functionalities. | |
| cupbox beizilaoshi/cupbox Enables AI assistants to perform everyday developer chores as MCP tools — organizing and batch-renaming files, searching contents, hashing, converting timestamps, encoding/decoding, converting CSV and JSON, OCR, clipboard and screenshot acc | |
| Bear MCP Server bejaminjones/bear-notes-mcp Provides comprehensive access to Bear notes using a hybrid sync-safe approach - direct database reads for performance and Bear's official API for writes, enabling natural language note management, search, organization, and analysis while ma | |
| hydra-etl bejaouibechir/hydra MCP server for Hydra ETL: lets AI assistants write declarative YAML ETL pipelines (CSV, Parquet, PostgreSQL, MySQL, MongoDB, APIs) and validate them before any data is read or written. | |
| code-context-mcp bek85/code-context-mcp Multi-provider embedding MCP server with local Milvus for semantic code search. Works with Claude Code, Cursor, Windsurf, and other MCP-compatible IDEs. | |
| AG Project Monitor MCP Server bekabiz/ag-mcp-server Enables management of office projects and tasks in Greek through Claude chat, with 11 tools for tasks, entries, announcements, plans, and project summaries via Supabase. | |
| ExaltByte MCP Server bekatechnology/exaltbyte-mcp-server Enables AI assistants like Claude to deploy apps, manage databases, and operate cloud infrastructure on the ExaltByte platform using natural language commands. | |
| The Neural Ledger Intelligence bekirdag/tnl-intelligence Read-only, source-linked news intelligence for AI agents: search The Neural Ledger's stories, retrieve story details with citations and revision history, and resolve related entities and assets. It is an evidence layer, not a trading or exe |
33,451–33,500 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.