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 |
|---|---|
| OPNsense MCP Server fakebizprez/opnsense-mcp-server Enables natural language management of OPNsense firewalls through AI clients, providing tools for firewall rules, system health, VPN monitoring, and more. | |
| FunPay MCP Server fakelag28/funpay-mcp-server Provides AI agents with full programmatic access to a FunPay account, enabling reading chats and orders, managing lots, processing refunds, and more via FunPay's web API. | |
| vsuet-timetable-api-mcp fakelag28/vsuet-timetable-api-mcp Provides MCP tools to fetch and filter schedules for groups, teachers, and rooms from VSUET's timetable site, with support for JSON or text output. | |
| Base Network MCP Server fakepixels/base-mcp-server An MCP server that enables LLMs to perform blockchain operations on the Base network through natural language commands, including wallet management, balance checking, and transaction execution. | |
| MCP AI Bridge fakoli/mcp-ai-bridge A secure Model Context Protocol server that enables Claude Code to connect with OpenAI and Google Gemini models, allowing users to query multiple AI providers through a standardized interface. | |
| obsidian-mcp-server fal1989/obsidian-mcp-server Enables Claude Desktop to interact with an Obsidian vault through the Local REST API, allowing file listing, reading, searching, creating, and updating markdown notes. | |
| Wisply MCP Connector fal3/wisply-mcp Enables MCP clients on a Mac to access meeting notes, action items, and live transcripts from a locally running Wisply app without an account. | |
| Wisply (this Mac) fal3/wisply-vscode Enables an editor's AI chat to list and search memos, read action items and open questions, and follow the live recording in progress from the local Wisply app. Connects only to Wisply on the same Mac over a local loopback connection. | |
| Brave-Gemini Research MCP Server falahgs/brave-gemini-research-mcp-server Provides web and local search capabilities via Brave Search combined with advanced academic paper analysis using Google's Gemini model. It allows AI assistants to perform real-time information retrieval and structured research synthesis dir | |
| Flux ImageGen MCP Server falahgs/flux-imagegen-mcp-server Enables AI image generation from text prompts using Pollinations AI. Supports multiple models, customizable dimensions, and direct image saving with URL generation capabilities. | |
| Gemini Data Analysis & Research MCP Server falahgs/gemini-data-analysis-research-mcp-server A Model Context Protocol server leveraging Google's Gemini Flash 2 to analyze datasets, generate research papers, and deliver results via email. | |
| Gemini Email Subject Generator MCP falahgs/gemini-email-subject-generator-mcp An MCP server that utilizes Google's Gemini Flash 2 model to generate AI-driven email subjects and detailed reasoning processes. It enables users to send emails via SMTP with dynamic content and save complex brainstorming sessions to local | |
| Gemini Thinking MCP Server falahgs/gemini-thinking-mcp A Model Context Protocol (MCP) server implementation for the Google Gemini language model. This server allows Claude Desktop users to access the powerful reasoning capabilities of Gemini-2.0-flash-thinking-exp-01-21 model. | |
| image-gen3-google-mcp-server falahgs/image-gen3-google-mcp-server Enables high-quality image generation using Google's Imagen 3.0 model via the Gemini API, with support for multiple images per request and automatic file management and HTML preview generation. | |
| Gemini Imagen 3.0 MCP Server falahgs/imagen-3.0-generate-google-mcp-server Generates high-quality images using Google's Imagen 3.0 model via the Gemini API with support for up to four images per request. It provides automated file management and creates HTML previews for seamless image viewing within MCP-compatibl | |
| 3D Cartoon Generator & File System MCP Server falahgs/mcp-3d-style-cartoon-gen-server Enables high-quality 3D-style cartoon image generation using Google Gemini AI alongside secure file system operations like reading, writing, and managing directories. It provides a dual-purpose toolkit for creative asset generation and loca | |
| MCP CSV Analysis with Gemini AI falahgs/mcp-csv-analysis-with-gemini-ai An MCP server that enables advanced CSV analysis and data visualization using Google's Gemini AI and Plotly. It allows users to perform exploratory data analysis, generate interactive charts, and conduct complex reasoning on tabular data. | |
| MCP MiniMax Music Server falahgs/mcp-minimax-music-server Enables AI agents to generate music and audio content using the MiniMax Music API through text prompts, with support for reference audio and lyric generation. | |
| MCP Storybook Image Generator falahgs/mcp-storybook-image-generator Generates children's storybook illustrations in multiple art styles (3D cartoon, watercolor, pixel art, hand drawn, claymation) with matching stories using Google's Gemini AI. | |
| Odoo MCP Server falaksarhan/odoo-mcp-connector Connects MCP clients like Claude to your Odoo ERP, enabling natural language queries, reports, and optional data modifications. | |
| Enfusion MCP falcon-insurance-agency-of-michigan/enfusion-mcp Enables MCP clients to inspect, edit, and validate Arma Reforger addons in Workbench, including Enforce Script source, prefab/world files, resource GUIDs, and Workbench startup diagnostics. | |
| Context7 falcon077/context7-mcp-server Enables AI assistants to access up-to-date library documentation through MCP tools for resolving library IDs and querying docs. | |
| Charlie Work falcon305/charlie-work-mcp Scans a repository for maintenance toil (flaky tests, expiring certificates, TODO rot, dead flags, etc.) and returns a prioritized queue with a credit ledger to track who cleared what. | |
| Nightman falcon305/nightman MCP server for hunting bugs in Python functions via adversarial input generation and minimized regression tests. | |
| Polymarket MCP falconaipro/falcon-polymarket-mcp Enables MCP hosts like Claude and Cursor to query Polymarket data via Falcon AI's external API, including market listings, order books, and trader stats. | |
| Apple Calendar MCP falconbradley/claude-connector-apple-calendar Provides Claude with full access to Apple Calendar on macOS via EventKit, enabling reading, searching, creating, updating, and deleting events with support for recurring series, alarms, attendees, and free/busy availability. | |
| Apple Messages MCP falconbradley/claude-connector-apple-messages Enables Claude on macOS to read, search, and send iMessage, SMS, and RCS messages, with tools for stats, chat history, attachments, and message composition. | |
| Advocu MCP Server falconcr/advocu-mcp-server Enables Google Developer Experts, Docker Captains, and Microsoft MVPs to submit professional activity reports via conversational AI, with support for multiple programs and rate-limited API access. | |
| capcut-mcp falconortiz/capcut-mcp Enables agents to read and write CapCut desktop draft folders on local disk, assembling vertical 1080×1920 shorts with clips, titles, subtitles, music, transitions, and effects as drafts the user then opens and exports in CapCut. All writes | |
| obs-mcp falconortiz/obs-mcp-public Enables supervised control of OBS Studio over obs-websocket v5, including scene and input management, audio/filter toggles, and starting or stopping streams, recordings, replay buffer, and virtual camera, with dry-run writes and redacted se | |
| falcon-mcp-server falconry/falcon-mcp-server A Python MCP server using the Falcon web framework, providing Streamable HTTP transport for connecting AI agents and MCP clients. | |
| agent-bridge falconsw/agent-bridge Lets MCP-speaking terminal agents read, click, type, fill forms, upload files and take screenshots in the user's own already-logged-in Chrome, so existing sessions stay signed in. Connects to the current browser via a Chrome extension inste | |
| sharepoint-mcp falconttu/sharepoint-mcp Exposes SharePoint file operations to Microsoft Copilot Studio, allowing file publishing, listing, link generation, and deletion with secure authentication via Microsoft Graph. | |
| mcp-meilisearch falcosan/mcp mcp-meilisearch | |
| Canva MCP Server falcoschaefer99-eng/canva-mcp-server A Model Context Protocol (MCP) server for Canva integration. Connect Claude Code or any MCP-compatible AI client to your Canva account to search designs, generate AI designs, edit content, manage folders, and collaborate through comments. | |
| muse-tts-embed falcoschaefer99-eng/muse-tts-embed Enables Claude to speak text with an embedded audio player, supporting 54 voices, voice cloning, and playback controls, all running locally. | |
| zoho-projects-mcp falegria86/zoho-mcp Connects Zoho Projects with Claude AI to manage projects, tasks, time tracking, and comments through natural language conversations. | |
| Google Calendar AutoAuth MCP Server falgom4/calendar-mcp Enables AI assistants to manage Google Calendar through natural language interactions with features like creating, updating, and deleting events, searching calendars, and supporting natural language date/time inputs. | |
| asker-mcp falkenslab/asker-mcp Enables AI agents to draft and validate definitions files from notes, generate questions in GIFT or Moodle XML, and review or exclude them before importing into Moodle. | |
| docker-mcp falkenslab/docker-mcp Enables an AI agent to run and inspect containers, build and pull images, manage volumes and networks, drive Compose projects, clean up, and run self-checking practice labs. Startup modes restrict it to read-only, labs-only, or full Docker | |
| h5p-mcp falkenslab/h5p-mcp Enables AI agents to build, validate, preview, and read content-only H5P packages locally for interactive content types such as multiple choice, fill in the blanks, cards, question sets, and course presentations. | |
| mcp-server-template falkenslab/mcp-server-template Provides a ready-to-run stdio server scaffold that agents can launch via npx without installing anything, bundled into a single file with an example tool, strict tool-schema checks, tests, and bilingual documentation. It gives developers a | |
| teuton-mcp falkenslab/teuton-mcp Enables an AI agent to write, check, and run infrastructure tests on students' machines with confirmation, read per-student results and grades, export Moodle-ready grades, and drive a classroom panel from chat while keeping credentials away | |
| Erik Finance MCP falkensson/erik-finance-mcp Enables read-only access to company financial data from Handelsbanken Sweden via Enable Banking, exposing accounts, balances, transactions, monthly spending, and sync status through MCP tools. | |
| FalkorDB MCP Server falkordb/falkordb-mcpserver Allows AI models to query and interact with FalkorDB graph databases through the Model Context Protocol (MCP) specification. | |
| Fundus falkue/fundus-app Exposes roughly forty tools over streamable HTTP so AI assistants can search an archive of sourced evidence, time series, forecasts, slides and datasets, reuse existing material with its citations, and write new sourced findings back. It al | |
| yandex-mcp fall-out-bug/yandex-mcp Enables LLM agents to interact with Yandex Tracker (and future Yandex services) using per-user credentials instead of a shared org-wide token, supporting both single-user and multi-user modes. | |
| Converse MCP Server falldownthesystem/converse Enables Claude to chat with various AI models and obtain multi-model consensus for complex decisions. | |
| imagen-mcp falldownthesystem/imagen-mcp Enables generating and editing images via OpenAI GPT Image 2.5 models (flare and sunburst) through MCP tools for text-to-image and reference-based image editing. | |
| mcp-cloud-deploy fallegri/mcp-deploy MCP server for deploying projects to multiple cloud platforms (Vercel, Railway, Neon, MongoDB Atlas, Docker) and running local dev servers, with orchestration for full-stack deployments. |
49,501–49,550 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.