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 |
|---|---|
| Siemens Docs MCP czarnak/siemens-docs-mcp Lets AI assistants search and read vendor documentation from the TIA Portal and Industrial Operations X portals in real time, exposing search, table-of-contents, publication-listing, and Markdown page-reading tools. | |
| tui-canvas czaruno/tui-canvas MCP server for creating interactive terminal canvases (calendar, document, flight) in AI coding assistants. Supports multiple TUI frameworks and integrates with tmux. | |
| pywss MCP Server czasg/pywss A lightweight Python web framework that enables building MCP servers with SSE, StreamHTTP, and MCPO protocols for tool integration. | |
| My MCP Server czcz0009/my-mcp-server A template for deploying and monetizing MCP servers on Apify, supporting stdio and streamable HTTP transports with authentication and pay-per-event billing. | |
| SF Bay Area Transit MCP czekaj/sf-transit-mcp Enables Claude to find Bay Area places and stops and plan complete door-to-door journeys — walking legs, transit routes, transfers, and departure/arrival times, including deadlines and comparisons with walking or cycling — without API keys | |
| NetPilot-MCP czgreg/netpilot-mcp Enables large language models to manage network devices (Cisco, Huawei, H3C, Ruijie) via Telnet/SSH, supporting command execution, configuration, and diagnostics. | |
| Cocos MCP Log Bridge czh2774/cocosmcp A powerful log bridging tool that synchronizes log information between Cocos Creator editor and Cursor AI, helping developers analyze and solve problems more effectively. | |
| VisualWebScraper czhh006564/websearchcontenttomd_mcp MCP server for web scraping using Playwright headless Chromium. It provides tools to fetch webpage screenshots, search article listings, and generate article briefs via local LM Studio models. | |
| Ombre Brain czielinski212/ombre-brain Gives Claude persistent cross-conversation memory by tagging recollections along Russell's valence/arousal dimensions, storing them as Obsidian-compatible Markdown buckets that decay on a forgetting curve and surface automatically when emot | |
| F5 MCP Server czirakim/f5.mcp.server A Model Context Protocol server that enables management of F5 devices through natural language commands, allowing users to create, update, list, and delete network objects like virtual servers, pools, and iRules via the iControl REST API. | |
| n8n Manager for AI Agents czlonkowski/n8n-manager-for-ai-agents Enables AI agents to manage n8n workflow automation instances through tools for workflow CRUD operations, execution monitoring, and webhook triggering. It facilitates programmatic interaction with n8n instances via the n8n API with AI-optim | |
| dsh_everything czm1998/dsh_everything Exposes the local voidtools Everything index over MCP stdio on Windows, letting AI agents search, filter, aggregate, detect duplicates and grep file contents across millions of index entries in milliseconds instead of recursively scanning d | |
| jira-service-desk-mcp czsadykov/jira-service-desk-mcp Connects AI assistants to Jira Service Management instances, providing 40 tools for managing service desks, requests, comments, customers, organizations, queues, SLA, approvals, and attachments. | |
| C2C Bridge czstudio/codex-with-chatgpt-pro Enables ChatGPT Pro web to securely read workspace files, git diffs, and test records through OAuth-protected read-only MCP tools, so it can plan and review while Codex handles execution without uploading the repository. | |
| SolidworksMCP czuryk/solidworksmcp MCP server for controlling a live SOLIDWORKS session through the Windows COM API, enabling native CAD operations like sketches, features, bodies, views, and exports, plus transactional plans and vectorization. | |
| scholar-toolkit-mcp czwziy/paper-toolkit-mcp Comprehensive MCP server for academic research workflows, enabling paper searching across multiple sources, manuscript processing with citation placeholders, search caching, and citation export. | |
| Code Audit MCP Server czx1111/code-audit-mcp An AI-native code security audit MCP server that supports multi-language AST analysis, call graph analysis, vulnerability detection, and AI deep audit. | |
| lyx-mcp czxdev/lyx-mcp Enables AI assistants to edit LyX papers with tracked changes, including text and selected document structures, and export PDFs. | |
| RenderDoc MCP d-bkk/renderdocmcp Exposes RenderDoc capture analysis to AI clients via MCP, enabling offline analysis of .rdc files (action tree, pipeline state, textures, shaders) and GUI state interaction on Windows. | |
| users-demo d-bui/mcp-from-scratch Enables AI agents to interact with a user management REST API, providing list, get, and create operations while preventing destructive actions like update/delete through an explicit access registry. | |
| Gemini MCP Server d-diaa/gemini-mcp A Model Context Protocol server that enables Claude to interact with Google's Gemini AI models, allowing users to ask Gemini questions directly from Claude. | |
| Mistral OCR MCP Server d-diaa/mistral-ocr-mcp An MCP server that enables Claude to perform OCR on local files using Mistral AI's document processing capabilities. It converts documents and images into markdown format for seamless analysis and interaction. | |
| TheoTown MCP Server d-init-d/theotown-mcp Enables AI agents to inspect city states, design urban layouts, and construct roads, buildings, zones, and utilities in the TheoTown city simulation game via hot-reload IPC. It provides plan validation, staged batch execution, job monitorin | |
| File MCP Server d-issy/mcp A Model Context Protocol (MCP) server that enables AI assistants to perform comprehensive file operations including finding, reading, writing, editing, searching, moving, and copying files with security validations. | |
| loot-agent-mcp d-kek/loot-agent-mcp This MCP server enables agents to trade LOOT tokens, play the full loot game loop, and launch their own tokens on Robinhood Chain, all at the same prices and rules as human wallets. | |
| ESA MCP Server d-kimuson/esa-mcp-server Enables interaction with esa.io's API through the Model Context Protocol, supporting article search and retrieval with a compliant MCP interface. | |
| Modular MCP d-kimuson/modular-mcp A proxy MCP server that manages multiple upstream MCP servers by grouping them and loading tool schemas on-demand, reducing LLM context usage. | |
| gmail-mcp d-mato/gmail-mcp MCP server for Gmail that enables searching, reading, archiving, and managing email from any MCP client. | |
| mcp-kdenlive d-ogi/mcp-kdenlive Enables AI agents to control a running Kdenlive video editor instance via D-Bus for tasks like importing media, building timelines, adding transitions, markers, effects, and rendering. | |
| studio d-onworks/blender-mcp-studio Enables Claude Code and Codex to drive Blender through natural language: searching Sketchfab and importing ranked models with auto-recorded credits, auto-rigging characters and applying Mixamo animations, converting a single image to 3D, an | |
| MCP-WEDECODEMCP d-rn/mcp-wedecodemcp A WeChat Mini Program decompilation MCP server that enables scanning, decompiling, and analyzing local WeChat mini program packages through MCP clients like Cherry Studio. | |
| agc-analytics-mcp d-sp-wq/agc-analytics-mcp Connects Huawei AppGallery Connect operational data to any MCP-capable AI client, letting users analyze report trends across 16 report types, crash and AppFreeze metrics, review and rating insights, and generate Markdown daily or weekly dig | |
| zhizhen-db-mcp d-uoduo/zhizhen-db-mcp Enables AI assistants to search and retrieve academic papers from the Dalian University of Technology library discovery platform, returning structured citations and full abstracts while caching results locally. | |
| SW_MCP d-veloping/sw_mcp Enables an AI assistant to drive an already-running SOLIDWORKS session over its COM API, so it can build sketches, solid features, reference geometry, assemblies, mates, and engineering drawings, then inspect the result through topology lis | |
| macos-desktop-control d-wwei/macos-desktop-control Provides native macOS desktop automation for AI agents, enabling screen capture, mouse/keyboard control, window management, and iOS/Android simulator control in both foreground and background modes without focus stealing. | |
| @d-zero/mcp-server d-zero-dev/mcp-server Enables AI assistants to retrieve Figma data and access D-ZERO frontend coding guidelines through CLINE integration. | |
| whoop-mcp d00ennis/whoop-mcp Local MCP server for the WHOOP API v2 that provides tools to access recovery, sleep, strain, and workout data, with local history and JSON export. | |
| Pentest-mcp d01ki/pentest-mcp Unified penetration testing MCP server for Claude Desktop providing 34 security tools for reconnaissance, web scanning, code analysis, and authenticated testing. | |
| MCP Kali d0gesec/mcp-kali Enables AI agents to execute any command in a Kali Linux environment, with features like interactive sessions, background tasks, and HTTP interception for security testing. | |
| MCP Memory d0kwon/mcp-memory MCP server that gives MCP clients (like Cursor, Claude, Windsurf) the ability to remember user information across conversations using vector search technology. | |
| linear-eye d0lim/linear-eye Enables read-only intelligence over a Linear workspace by serving snapshot and change-history data stored in Cloudflare D1, so clients can answer questions about current work, project and milestone progress, member activity, and weekly repo | |
| JEV Gateway d0ng231/jev-gtw Enables coding agents to discover registered data sources, receive only policy-approved text or image views, and run sandboxed local probes on withheld records so work can continue without exposing protected data. | |
| open-med-mcp d0ng231/open-med-mcp Enables AI coding agents to perform end-to-end medical image analysis locally, from inspecting CT/MRI/X-ray studies and running containerized segmentation models like MedSAM2, TotalSegmentator, and HD-BET to refining masks, measuring volume | |
| pbix-mcp d0nk3yhm/pbix-mcp MCP server for creating, editing, and evaluating Power BI (.pbix/.pbit) files without Power BI Desktop. Supports 101 tools including report creation, data sources, DAX measures, and file manipulation. | |
| SkyDemon MCP Server d0rsegal/skydeamonmcp Enables authenticated access to a pilot's flight-planning account, letting an assistant search installed airfield charts offline, pull full airfield records with pilot notes and live feedback, and list, read, or download flightplans from lo | |
| EGIPCI MCP Server d0whc3r/egipci-mcp MCP server for querying archaeological site information from the EGIPCI service of the Generalitat de Catalunya, enabling AI editors to access Catalan archaeological data. | |
| servo-mcp d11r/servo-mcp Enables AI agents to see and control your desktop with tools for screenshots, clicks, typing, and more, all locally on macOS and Windows. | |
| Stealth-Browser-MCP-Server d18626250363/stealth-browser-mcp-server Provides a real Chrome fingerprint browser with 32 MCP tools for undetectable web automation, navigation, interaction, and data extraction. | |
| unlimited-tavily-mcp d1alect-tech/unlimited-tavily-mcp Provides a local stdio MCP proxy that distributes Tavily tool calls across multiple API keys, automatically handling rate limits and invalid keys to enable uninterrupted search, extract, crawl, map, and research operations. | |
| qwen-local-mcp d1dac0/qwen-local-mcp Enables MCP clients such as Codex and Claude Code to delegate bounded coding tasks to a local Ollama Qwen model, with workspace, branch, and command guardrails plus safe file editing and test execution. |
41,501–41,550 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.