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 |
|---|---|
| : elifduong/notebooklm-mcp Enables agents and automation platforms to run citation-backed Q&A over Google NotebookLM notebooks and to generate Studio artifacts such as audio overviews, video, infographics, reports, presentations, data tables, flashcards, quizzes and | |
| k8s-ops-mcp eliffkeskin/k8s-ops-mcp Enables read-only Kubernetes cluster diagnostics through MCP tools, allowing a local LLM to inspect pods and events and debug issues via natural language queries. | |
| Notion MCP Server elifnelson2022/notion-mcp-server Gives AI agents token-authenticated read and write access to Notion, letting them create and edit pages, query databases, append blocks, apply templates, comment, and upload files in plain language. It runs headless for CI and background ag | |
| Basecamp MCP Server elifpatel/basecamp-mcp-server Enables MCP-capable clients such as Codex, Cursor, and Claude Desktop to read and manage Basecamp 3 projects through OAuth-authenticated API calls, covering projects, todos, messages, card tables, documents, uploads, and search. It exposes | |
| memex elifvasiliou18931/memex Enables AI coding agents to save, recall, and link atomic markdown knowledge cards across sessions through MCP tools, with optional git sync and no vector database. | |
| MultiZen elifwagner/multizen-browser Lets MCP clients drive isolated, persistent Chromium browser profiles through tools for navigation, clicking, typing, extraction, screenshots, JS evaluation, tabs, and cookies. Each profile keeps its own login state, fingerprint, and proxy | |
| keenetic-mcp elihucredible450/keenetic-mcp MCP server that bridges AI assistants like Claude Code to Keenetic routers, enabling natural language control of Wi-Fi, devices, VPN, and network segmentation via the router's RCI interface. | |
| Houdini MCP Server eliiik/houdini-mcp Enables natural language control of SideFX Houdini for tasks including node management, parameter editing, and geometry inspection. It leverages RPYC to execute Python scripts and manage scene data through an MCP-compatible interface. | |
| Woolworths MCP Server elijah-g/woolworths-mcp Enables interaction with Woolworths Australia's online shopping platform through browser automation and API integration. Supports product search, browsing specials, managing shopping cart, and accessing product details through natural langu | |
| Google Classroom MCP elijah629/classroom-mcp Enables AI agents to read Google Classroom data—including coursework, submissions, announcements, and Drive attachments—through a remote, OAuth-protected MCP server with interactive Google sign-in. | |
| omp-worker-mcp elijah7x/omp-worker-mcp Lets coding agents delegate bounded background tasks to OMP models via an MCP server, with job control, custom roles and agents. | |
| bscs-mcp elijahbowie/behavioral-state-change-selling Deterministic, no-LLM MCP server exposing six operations from the Behavioral State-Change Selling methodology manifest. | |
| neat-labs elijahbutler/neat-labs Provides coding agents read-only access to the Neat Labs component and style library, enabling them to search and retrieve components, styles, themes, token roles, and preview links. | |
| Runware MCP Server elijahdev0/mcp-runware Enables lightning-fast AI image and video generation, upscaling, background removal, captioning, and masking through the Runware API with automatic model selection and comprehensive validation. | |
| Letta Agents MCP Server elijahdev0/mcp-server Control AI agents creation and modification via MCP. | |
| Remote MCP Server on Cloudflare elijahdev0/my-replicate-mcp-server Enables deploying a remote MCP server with OAuth on Cloudflare Workers, allowing MCP clients like Claude Desktop to connect remotely. | |
| AutobotX MCP Server elijahmoses1000-jpg/autobotx Provides access to 141 operational workflows across 17 departments, an intelligent guide bot, real-time communities, document processing, and organizational state management through MCP tools. | |
| Groundtruth elijahslimaj/groundtruth MCP server for the governed knowledge layer, enabling agents to query canonical entries, retrieve conflicts, and manage proposals with strict tenant isolation and audit. | |
| legalize-mx-mcp elimorals/legalize-mx-mcp Enables AI agents to search and read Mexican federal, state and municipal legislation, retrieving the current text or the version in force on any past date, comparing reform versions, tracing amendment history and returning official links f | |
| MCP Time Server elims2/mcp-time-server A lightweight Model Context Protocol server that provides current UTC time in various formats, including ISO 8601 and Unix timestamps. It is designed for seamless integration with Cursor IDE to provide consistent time-related capabilities a | |
| TimeVerse Code Reader elimyliu/timeverse-code-reader A read-only MCP server for code reading with intelligent caching, line-range selection, and language detection, enabling AI assistants to efficiently and safely explore file systems. | |
| timeverse-command-mcp elimyliu/timeverse-command-mcp An MCP server that enables AI clients to execute shell, Python, and Node commands on the local machine across platforms. | |
| TimeVerse HyperFrames MCP elimyliu/timeverse-hyperframes-mcp Wraps HyperFrames CLI as MCP tools, enabling AI agents to create, preview, and render video projects from HTML/CSS/JS, with text-to-speech and transcription capabilities. | |
| Timeverse InfCanvas MCP Server elimyliu/timeverse-infcanvas-mcp Enables AI clients to read and write local infinite canvas data via MCP protocol, with support for image generation and web visualization. | |
| timeverse-omni-converter-mcp elimyliu/timeverse-omni-converter-mcp Enables broad media and document format conversion (audio, video, images, Office, data, ebooks, PDF, subtitles) through an MCP server with smart routing, batch processing, and multiple conversion engines. | |
| timeverse-plugin-search elimyliu/timeverse-plugin-search Searches multiple sources including SkillHub, Smithery, MCP Registry, GitHub, and web for MCP servers and skill packages. | |
| Seedream MCP Server elimyliu/timeverse-seedream-mcp Enables AI assistants to generate high-quality images using Volcano Engine's Seedream models via MCP, supporting text-to-image, image-to-image, multi-image fusion, and streaming output. | |
| Execution System MCP Server elinsky/execution-system-mcp Enables AI-native task and project management through natural language conversation with Claude, eliminating app-switching by letting you add actions, manage projects across multiple areas of focus, and maintain a GTD-style execution system | |
| Jikgu Customs MCP elinysh/jikgu-customs-mcp Calculates estimated import duties, taxes, and customs clearance rules for overseas purchases, with all tools being read-only and operating without external API calls. | |
| agy-worker elio-zwd/agy-worker MCP server for local AGY worker runtime, enabling controlled task execution with permission checks, evidence collection, and status tracking for build, browser, and image workflows. | |
| Salesforce DX MCP Server eliolin/sfoa-enterprise-mcp Enables LLMs to securely read, manage, and operate Salesforce org resources through Model Context Protocol tools. | |
| NPI Registry MCP Server eliotk/npi-registry-mcp-server A Model Context Protocol (MCP) server for searching the National Provider Identifier (NPI) registry. This server provides tools to search and retrieve information about healthcare providers and organizations in the United States. | |
| human_input eliotok/justaskme Enables Codex agents to ask structured questions through selectable, confirm, text, and multi-select forms, and to handle responses with clear statuses such as answered, declined, timed out, or needs user input. | |
| notes-mcp eliotshea/notes-mcp An MCP server for Apple Notes that can read and write checklist state, enabling agents to manage checklists in notes. | |
| lore-mcp eliotshift/lore-mcp Architectural memory layer for AI coding.
Automatically extracts decisions, detects
security gaps, and analyzes git history
from your codebase in one command. | |
| MCP vLLM Benchmarking Tool eliovp-bv/mcp-vllm-benchmark An interactive tool that enables users to benchmark vLLM endpoints through MCP, allowing performance testing of LLM models with customizable parameters. | |
| Codex Context Engine elioz404/panchicodex Indexes a workspace and exposes code-navigation tools to Codex, enabling symbol lookup, reference finding, dependency analysis, and security audit for local codebases. | |
| whaletape-mcp-server elipacosta88/whaletape-mcp-server Provides pay-per-call Hyperliquid whale, funding, open-interest, and liquidation intelligence via x402 payments (USDC on Base, Solana, or Algorand), with free preview routes and no account or API key required. | |
| Nominal MCP Server elirapport1/nominal-mcp Enables pulling test data, inspecting telemetry channels, running analysis, and writing results back from any MCP client. | |
| tab-intentions eliraz-refael/wherefore Lets an AI agent inspect your browser tabs, read page contents, reload sleeping tabs and ask clarifying questions so it can work out why each tab is open and group them into intentions. It then submits those intentions so finished or dead t | |
| mcp-ondemand elis132/mcp-ondemand Enables MCP clients to list and call tools from multiple configured servers while each backend starts only on first use, is shared across sessions, and stops when idle. This reduces memory and process overhead without changing tool names or | |
| Pathgrove elis132/pathgrove-mcp Enables AI agents to search local files by name, path, metadata, and literal text over MCP on Windows, Linux, and macOS, while keeping searches within explicitly configured directories and running locally over stdio. | |
| Timelog MCP Server elisabethfalck/mcp-timelog Enables viewing, creating, and managing time registrations, absences, and timesheet approvals through the Timelog API using natural language. | |
| ecc-memory elisabit-ug/mnemosyne Enables Claude Code to persist and recall cross-repository memories as Markdown files via save, search, read, and health-check tools, with local-only storage and no cloud services. | |
| Forja elisaul77/forja Enables AI agents to design, modify, and verify exact B-rep 3D CAD models by running build123d scripts on an OpenCascade kernel, with live three.js preview, collision and FDM printability checks, text-based spatial perception, user notes/sk | |
| Canva MCP Server elisbanpaco/mcp-canva-gemini-cli Enables AI assistants to connect to Canva through the official Canva Connect API to create, search, export, and upload designs using natural language. | |
| OpenEcoBee MCP eliseorobles/openecobee Enables controlling ecobee thermostats from ChatGPT by connecting a user's ecobee account through normal browser sign-in, without an ecobee developer API key. Supports listing thermostats, reading status, setting temperature or HVAC mode, a | |
| cnbs-mcp-server eliseowzy/cnbs-mcp-server Enables querying statistical data from China NBS, World Bank, IMF, OECD, BIS, census, and department statistics via MCP tools. | |
| MCP SQLite Demo elisha1994/mcp-llama-sqlite-bridge A server that exposes SQLite database operations as tools, allowing natural language interactions with a database through LlamaIndex and Ollama LLM integration. | |
| gitlab-mcp-server elisjetmax/mcp-gitlab A read-only MCP server for self-hosted GitLab, enabling listing projects, inspecting branches and commits, browsing file trees, and reading file contents. |
47,601–47,650 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.