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 |
|---|---|
| r2-uploader-mcp dtinth/r2-uploader-mcp Enables uploading PR screenshots to Cloudflare R2 via presigned URLs, allowing Claude to attach images to PR descriptions without binary data passing through MCP. | |
| read-website-fast dtiwari679/mcp-read-website-fast Enables AI agents and MCP clients to fetch and crawl webpages, strip noise, and convert them into token-efficient Markdown while preserving links and supporting caching, robots.txt, concurrency, and depth. | |
| agent-audit-trail dtjohnson83/agent-audit-trail MCP server providing immutable audit logging, policy enforcement, and compliance reporting for AI agent workflows, enabling regulatory compliance and chain integrity verification. | |
| DimeVision MCP Server dtjohnson83/dimevision-mcp-server Enables AI assistants to analyze weld photos for quality scoring and identify common defects like porosity or undercut. It provides practical bead-building tips and technical guidance for MIG, TIG, and Stick welding processes based on AWS/A | |
| Trackkr MCP Server dtla-professional-services-llc/trackkr-mcp Enables AI agents to autonomously manage incoming packages by logging parcels, cross-referencing unit directories, surfacing aging uncollected items, and recording pick-up signatures without physical locker hardware. | |
| playwright-server dtlele/playwright-plus-python-mcp-master Enables browser automation using Playwright, including navigation, screenshots, clicking, form filling, and JavaScript execution. | |
| manifest-mcp dtm-repo/manifest-mcp Enables AI assistants to read and update a user's personal manifest (portable context) through a secure, token-based connector. | |
| notes-box dtmhed1255/mcp-notes-server-app Enables users to add, get, and list notes, with state persisted to a JSON file in the home directory. | |
| excalidraw-mcp dtour/excalidraw-mcp Enables LLMs to create, read, modify, and render Excalidraw diagrams through a semantic graph abstraction, handling spatial reasoning automatically. | |
| Strava MCP Server dtrain473/strava-mcp Connects Claude to Strava data for natural language queries about rides, stats, and activities. | |
| Running Companion MCP Server dtsiakas/running-companion Gives Claude and ChatGPT read-only access to locally stored Garmin running and health data, so users can ask about recovery status, individual runs, best efforts, sleep and long-term trends, pull computed weekly reports, or run read-only SQ | |
| KaaS dtsipras7651/kaas Enables MCP-capable coding agents to query a self-hosted, LLM-compiled Markdown wiki through a single ask tool, returning cited answers grounded in whole articles rather than embedded fragments. Served either locally over stdio or remotely | |
| pipecat-docs-mcp dtufail/pipecat-docs-mcp Enables searching Pipecat documentation and GitHub issues for grounded answers about APIs, configuration, code examples, and provider comparisons. | |
| line-desktop-mcp dtwang/line-desktop-mcp Enables AI tools to read and send messages through LINE Desktop via MCP, supporting manual or automatic sending without official LINE API tokens. | |
| MCP API Bridge dtyg123/mcp-api-bridge Enables exposing MCP servers as REST/OpenAPI services and converting OpenAPI or Swagger 2.0 APIs into MCP tools, with a web admin UI, reusable credentials, data transforms, and Docker deployment. | |
| zesarux-mcp dtz-labs/zesarux-mcp Controls the ZEsarUX ZX Spectrum emulator via ZRCP protocol for debugging, memory operations, tape/disk loading, and more. | |
| Local MCP for SketchUp dtzhlq/local-mcp-for-sketchup A local, offline MCP server that enables AI agents to collaborate with SketchUp for controlled modeling, editing, and review tasks via 41 MCP tools. | |
| silicon-canvas-mcp du-du-wang/silicon-canvas Enables agents to turn natural-language chip architecture and product visualization requests into image-generation prompts, structural references, and editable source specifications. Supports engineering diagrams, algorithm dataflows, state | |
| xiaozhi-mcphub du-yuxuan/xiaozhi-mcphub Multi-user MCP server with user isolation, permissions, resource sharing, and an admin console for managing MCP tools across users. | |
| File Manage MCP Server duaghwls/filemanagemcp Enables LLMs to organize and manage Windows file systems with intelligent file analysis, automated grouping, renaming with date prefixes, and safe operations through dry-run mode and sandbox restrictions. | |
| DualStream MCP Server dualstream/dualstreammcp Enables AI assistants to control DualStream streaming studio: switch scenes, compose layouts, manage widgets, and react to stream events. | |
| weather-service duan-li/mcp-weather-server-example An MCP server for managing notes, with resources, prompts, and a tool to add notes. | |
| edgeone-mcp duanap/edgeone-mcp Enables MCP clients to manage Tencent Cloud EdgeOne zones, offering tools to list zones, read and modify Layer 7 rules, purge caches, and query purge task status, while validating zone visibility for the current CAM identity. | |
| MCP Markdown Knowledge Base Server duandand/mcp-md-kb Enables AI agents to search and read local Markdown notes through MCP tools for file listing, keyword matching, summaries, and section extraction, without uploading files to third-party services. It supports stdio and Streamable HTTP access | |
| calendar-mcp duanefields/dav-mcp An MCP server for Apple iCloud Calendar over CalDAV, supporting list, search, create, update, delete, RSVP, and free-time finding without local macOS dependencies. | |
| iMessage MCP duanefields/imessage-mcp Enables reading the local iMessage database and sending messages through Messages.app on macOS, with both local stdio and remote HTTP access. | |
| Apple Notes MCP duanefields/notes-mcp Enables macOS users to read Notes' SQLite store directly for fast full-archive search and note retrieval, and to create, update, move, and delete notes through Notes.app. | |
| weather-mcp duanefields/weather-mcp Provides weather forecasts and climate history via Open-Meteo, including daily and hourly outlooks, typical past weather for future trip dates, location disambiguation, and ranked recommendations for pleasant outdoor days. | |
| Competitor Hunter duang777/competitor-hunter AI-powered competitor analysis agent that scrapes product pages and extracts structured data using LLMs, integrated via MCP for use with Claude Desktop and other clients. | |
| DigitalBrain MCP duanyu119/digitalbrain-mcp-kit Enables researchers to query DigitalBrain data catalogs, brain region profiles, gene expression summaries, and paper evidence, and download approved results through MCP-compatible clients. | |
| D-Hub MCP Server duanzgit/d-hub Provides a unified multi-agent coordination layer with shared memory, wiki, skills, and file management via MCP tools, enabling agents to access and collaborate on resources in a single Python process. | |
| paper-broker-mcp dubeyanant/paper-broker-mcp Enables users to search simulated NSE instruments, get quotes and account state, preview trades, and place or cancel orders only after explicit confirmation, using short-lived previews and persistent JSON account state. | |
| Claude Arithmetic MCP Server dubeysanskar1907/mcp-client-server-integration An MCP server that exposes basic arithmetic operations (addition, subtraction, multiplication, division) as tools, usable locally with Claude Desktop or deployed remotely. | |
| ClickHouse MCP Server dubin555/clickhouse_mcp_server A Model Context Protocol server that enables AI assistants to securely interact with ClickHouse databases, supporting table exploration and SQL query execution through a controlled interface. | |
| PDF MCP Flow dublin1231/pdf_mcp_flow Enables AI-driven PDF document processing including PDF to Markdown conversion, intelligent text and table extraction, image extraction, format conversion between PDF/Word/Markdown, batch processing, and fuzzy search - optimized for LLM con | |
| ffmpeg-mcp dubnium0/ffmpeg-mcp Enables comprehensive video/audio processing, analysis, and streaming via natural language by exposing 40+ FFmpeg tools as MCP tools. | |
| KAP MCP Server dubnium0/kap-mcp-server Enables AI agents to search Turkish companies, funds, and members and to retrieve their public disclosures, attachment files, and financial statements. It also parses fund portfolio PDFs into structured positions and totals, reports corpora | |
| ctx4-ai dubzdubz/ctx4-ai MCP server for portable context management across AI assistants, providing tools to store and retrieve persistent context, instructions, and execute sandboxed bash commands with automatic git commits, using OAuth 2.1 and magic link authenti | |
| Google Workspace MCP for Antigravity IDE duc-long/antigravity-google-suite Enables Antigravity IDE to directly interact with Google Docs, Sheets, Drive, Gmail, and Calendar, with token-optimized operations to reduce context usage by 70-90%. | |
| claude-ops-mcp ducampcarlos/claude-ops-mcp Enables Claude to run safe, read-only diagnostics against servers and websites — certificate chains and expiry, HTTP status/redirects/security headers, DNS records, email authentication (SPF, DKIM, DMARC, MTA-STS, TLS-RPT) and sitemaps. Eve | |
| Backlog MCP Server ducbachsong/backlog-mcp Exposes Backlog project management as tools for Claude Desktop, enabling search and management of issues, comments, wiki pages, milestones, custom fields, notifications, and more. | |
| api-docs-mcp ducda177/api-docs-mcp An MCP server that enables AI agents to explore, search, and query API definitions from OpenAPI/Swagger JSON files. | |
| moodle_mcp duck-5/moodle-mcp Enables AI assistants to access and manage academic course information, assignments, submissions, grades, calendars, materials, recordings, and announcements through authenticated LMS sessions. | |
| brindley duckasteroid/brindley Enables AI agents to plan and implement work as numbered Markdown initiative files inside a git repository, coining collision-free numbers, tracking status and cross-collection dependencies, and running design-review, implement, and complet | |
| valorant-mcp duckling1169/valorant-mcp Provides VALORANT account and match data through HenrikDev's API. Enables querying profile, recent competitive matches, and match details. | |
| Netbox MCP Server duckmak14/netbox-mcp A powerful integration server that combines Netbox's network infrastructure management capabilities with MCP (Multi-Cloud Platform) functionality. | |
| Woven ducksss/lifehack-2026 Enables building complete, compatible shopping carts from a single natural-language request inside ChatGPT or Codex, with explicit user confirmation before simulated Visa authorization. | |
| duckuments-mcp duckuments/duckuments-mcp Enables code agents to read, write, search, and manage notes in an Obsidian vault via the Local REST API plugin, along with workflow prompts for planning, debugging, summarizing, and committing. | |
| Google Drive MCP Server ducla5/gdriver-mcp Enables AI agents to efficiently access and process Google Drive documents by converting them to markdown and offering selective content extraction. Features intelligent caching, advanced search capabilities, and respect for Drive permissio | |
| Muse-Chat-MCP duclm1x1/muse-chat-mcp Lets any MCP host or OpenAI-compatible client chat with Meta's Muse (muse.ai Hatch) agent by driving your own logged-in Chrome, exposing tools for status, login, new chat, prompting, and reading replies. It also serves an OpenAI-compatible |
46,251–46,300 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.