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 |
|---|---|
| Obsidian MCP Server dbmcco/obsidian-mcp Enables natural language interaction with Obsidian vaults, supporting intelligent search, note CRUD operations, backlink analysis, and advanced knowledge management tools like narrative path generation and note cluster detection. | |
| OpenCDR MCP dbnz-io/opencdr-mcp Enables MCP-compatible clients to access a deployed management API through tools for status, detection and correlation rules, lists, signals, logs, integrations, notification settings, and incident-response roles/actions, with capability pr | |
| mcporacle dbobylev/mcporacle Local MCP server for Roo Code that connects to Oracle DB and returns limited set of metadata through secure MCP tools. | |
| MCP Presentations dboconsultingllc/mcp-presentations Remote MCP server running on Cloudflare Workers that creates PowerPoint presentations with customizable slides, layouts, and bullet points, along with basic calculator functions. | |
| Proxycurl MCP Server dbogardus/proxycurl_mcp A Node.js-based Model Context Protocol server that exposes Proxycurl's LinkedIn data API, allowing MCP-compatible clients to access LinkedIn profile data, company information, and search for employees. | |
| CyberSecurityLab MCP Server dbolatti/cyber-mcp-lab Provides an educational MCP server with cybersecurity examples, exposing a threat-intel lookup tool, an asset inventory resource, and an investigation prompt using simulated data. | |
| Cisco NSO MCP Server dbono711/cisco-nso-mcp-server Enables AI-powered network automation through natural language interactions with Cisco NSO, providing access to device management, configuration retrieval, sync operations, and service orchestration via the RESTCONF API. | |
| pebble-mcp dbonomo/pebble-mcp An MCP server for the Pebble smartwatch ecosystem, offering appstore search, a 64-color design toolkit, and build-emulator-screenshot development workflows as typed tools. | |
| DBOS MCP Server dbos-inc/dbos-mcp Enables LLMs to analyze and manage DBOS workflows, including introspection, workflow management, and authentication, to help debug applications in development or production. | |
| CoCo 3 MCP Bridge dbowlin/coco3_mcp_server Enables an AI assistant to drive a Color Computer 3 emulated in MAME, including entering BASIC commands, mounting disk images, capturing screen snapshots, and peeking/poking memory. | |
| coco3 dbowlin/coco3_mcp_server_python Enables an assistant to control a Tandy Color Computer 3 emulated in MAME, allowing typing, disk operations, screen viewing, and state management. | |
| android-dev-vm dboycht/android-dev-vm-mcp Enables AI agents to bootstrap a self-contained Android SDK and headless emulator from scratch, then debug and test apps through 25 tools covering screenshots, UI-tree inspection, tapping/typing, APK install and launch, shell/file transfer, | |
| mcp-notify dbreugne/mcp-notify Provides sound alerts, voice messages, and macOS notifications for Claude Code and other MCP-compatible AI assistants. | |
| AllTrails MCP Client dbrown540/alltrails-mcp-client Enables searching hiking trails from AllTrails.com via MCP, with smart caching to avoid rate limiting. | |
| OpenWrt MCP Controller dbshadow/openwrt-mcp Enables management and control of OpenWrt devices via a simple API, including reboot, status checks, log reading, and LED control. | |
| Amplify Data API MCP Server dbsmith7491/aws-amplify-data-mcp This MCP server enables users to interact with AWS Amplify Gen2 application data through natural language, allowing AI assistants like Claude to perform operations on Amplify data models using conversational language instead of complex code | |
| jobs-tools-knowledgebase dbsxortime/jobs-tools-knowledgebase A MongoDB Atlas-based Notion-style knowledge base management MCP server that supports user workspaces, project management, page CRUD with tree structure, and text search. | |
| Artifacts dbtlr/muninn MCP server that turns agent-generated Markdown, HTML, and text into persistent links, with tools to create, update, remove, list, and retrieve artifacts. | |
| mcp-server-local dbuddyamaya/mcp-server-local Enables local MCP-compatible clients, such as Claude Desktop, to query an AWS Athena database with read-only tools for listing tables, describing schemas, running SELECT queries, sampling rows, and getting row counts. | |
| TenderAI dbugom/tenderai-mcp-server An MCP server that automates government and enterprise tender workflows, including RFP parsing, proposal generation, and compliance tracking. It provides 18 specialized tools for technical and financial proposal assembly, partner coordinati | |
| kenpom-mcp dburge86/kenpom-mcp Provides access to KenPom basketball analytics through MCP tools. Enables querying ratings, efficiency, player stats, and more using natural language. | |
| Telegraf Controller MCP Server dburton-influxdata/telegraf-controller-mcp-server An MCP server that gives AI assistants full control over Telegraf Controller to manage agent fleets, configurations, labels, and health rules using natural language. | |
| Playwright MCP Server dbustosjr/playwright-mcp-server A production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for relia | |
| google-docs-mcp dbuxton/google-docs-mcp Enables AI agents to edit Google Docs via text anchors rather than character indices, preserving version history and enabling surgical edits without full document rewrites. | |
| litmos-mcp dbuxton/litmos-mcp Read-only MCP server for Litmos LMS that exposes user profiles, course results, and training completion data to AI clients. | |
| Anonymix MCP dbuzek/anonymix-mcp Provides local anonymization of Czech legal documents by replacing sensitive entities with pseudonyms to ensure privacy during LLM interactions. It allows users to safely process documents like contracts and judgments by keeping original da | |
| Browser Agent MCP Server dbwang0130/browser-mcp Provides browser automation capabilities through Claude Desktop and other MCP clients, enabling navigation, screenshot capture, content extraction, and interactive control. | |
| Google Workspace MCP Server dbzavi/google-workspace-mcp A robust, generic Model Context Protocol (MCP) Server that integrates AI agents with Google Workspace, enabling them to interact with Gmail and Google Docs. | |
| The Culture MCP Server dc-4nderson/theculture_mcp MCP server for The Culture, a fashion-focused social media app, exposing Supabase database operations and Hugging Face model inference as tools for use in Claude Code, n8n agents, and the Larry orchestrator. | |
| goodwill-mcp dc28vivek/splittab-mcp Enables natural-language interaction with Splitwise to explain balances, find missing or duplicate expenses, plan settlements, and safely add expenses with confirmation. | |
| Netlify Express MCP Server dc39313n/mcp A basic example MCP server running as a serverless function on Netlify using Express. Demonstrates how to deploy and run Model Context Protocol servers in a serverless environment with proper URL routing configuration. | |
| lanhu-mcp-server dc911360/lanhu-mcp-server Enables AI coding tools to read Lanhu design data and automate Design to Code, including project browsing, layer tree extraction, DDS semantic components, and code generation. | |
| AI-godot-mcp dc925928496/ai-godot-mcp Enables AI-driven game development by providing MCP tools to interact with the Godot editor, including scene editing, node manipulation, script attachment, and scene execution. | |
| Aprimo DAM API MCP Server dcaelopre/ts-aprimodam-api-mcp Enables reading of Aprimo DAM asset metadata, fields, and files through the Aprimo REST API. Designed for deployment on Azure via Docker. | |
| mimoe-agent dcaicedo/mimoe-agent MCP server for the mimOE AI Agent, enabling on-device tools like device discovery, network insight, and persistent note storage via natural language. | |
| ms-todo-mcp dcarrascosa/ms-todo-mcp An MCP server to read and manage your Microsoft To Do tasks through the Microsoft Graph To Do API. | |
| Audio Playback MCP Server dcarter610/mcp-virtual-audio-player Enables playback control of local audio files through a virtual audio output device, supporting play, stop, and status queries with configurable root directory and path safety enforcement. | |
| Boostcamp MCP Server dcaslin/boostcamp-mcp Integrates with the Boostcamp fitness platform to provide workout history, programs, exercises, and analytics via natural language. | |
| resume-kit MCP Server dcassil/resume-kit MCP server that evaluates, compares, aligns, generates, and validates resume materials against specific job postings, including ATS parseability checks, match scoring, and gap analysis. | |
| ElixirOffice MCP dcavalcante/elixiroffice-mcp Enables MCP clients to drive a desktop office editor through a fixed set of Office JavaScript API commands, allowing document, spreadsheet, presentation, and PDF inspection and editing within configured file roots. | |
| LosslessCut MCP dcavalcante/losslesscut-mcp Enables agents to inspect media and project files, create reviewable v2 projects, and perform verified native exports of selected segments as separate files through a private editor instance. It provides a small, safety-checked workflow tha | |
| Claude-Atlas-MCP dcazman/claude-atlas-mcp Self-hosted MCP server giving Claude persistent memory via entities, observations, history, and reminders, backed by a lightweight Node/SQLite backend. | |
| data-bs-mcp dcc-bs/mcp-data-bs MCP server for querying Huwise/Opendatasoft data portals. Enables dataset search, metadata retrieval, record filtering with ODSQL, and data export. | |
| dcc-itchio dcc-mcp/dcc-itchio Enables secure acquisition of itch.io game assets via official RSS feeds and authenticated Butler daemon downloads, and preview-gated publishing of game builds with hash-bound receipts and license verification. | |
| dcc-mcp-autocad dcc-mcp/dcc-mcp-autocad Enables agents to automate AutoCAD DWG drawings—inspecting entities, layers and layouts, creating drawings, managing layers, and adding typed lines, circles, points, and text—over either a live COM session or headless accoreconsole batch ru | |
| dcc-mcp-blender dcc-mcp/dcc-mcp-blender Enables AI clients to control Blender's 3D workflow via an embedded MCP server. | |
| dcc-mcp-capcut dcc-mcp/dcc-mcp-capcut Enables typed, auditable control of CapCut Desktop through a localhost, token-authenticated bridge and bundled CapCut-side panel, covering project setup, media import and proxies, timeline and clip editing, transitions, text and auto-captio | |
| dcc-mcp-fpt dcc-mcp/dcc-mcp-fpt Bridges AI assistants to Autodesk ShotGrid (Flow Production Tracking) data, enabling CRUD, search, batch operations, and schema exploration via typed MCP tools with progressive loading. | |
| gaea-terrain dcc-mcp/dcc-mcp-gaea Enables typed Gaea terrain builds and output verification for DCC-MCP, including inspecting templates, planning CLI arguments, executing bounded builds, and verifying exported height/weight images with dimensions and SHA-256 receipts. | |
| dcc-mcp-godot dcc-mcp/dcc-mcp-godot Enables Godot 4 editor interaction through MCP, including project/scene inspection, script writing, and a 2D roguelike skill for AI agents. |
43,001–43,050 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.