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 |
|---|---|
| io.github.yusufkadry/cinch yusufkadry/cinch-mcp Run AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run. | |
| Skill Seekers yusufkaraaslan/skill_seekers Transform 17 source types into AI-ready skills and RAG knowledge, directly from Claude Code. | |
| ROS MCP yutarop/ros-mcp Enables controlling robots in ROS environments through natural language, supporting topics, services, actions, and GUI tools. | |
| LinkBit yutotanakastar/linkbit-mcp Shorten URLs, bulk create, QR, and click analytics for LinkBit. | |
| io.github.Yuuqq/jules-dispatch yuuqq/jules-dispatch Batch-dispatch coding tasks to Google Jules: 50 parallel sessions, plan approval, PR collection. | |
| io.github.yuvalsuede/memory-mcp yuvalsuede/memory-mcp Persistent memory + git snapshots for Claude Code. Never lose context or code. | |
| Mark: agent escrow yuvlero/mark Bitcoin escrow for AI agents: dispute protection for agent payments. 2-of-3, Lightning in/out. | |
| com.gammainfra/mcp-server yuz0101/gammainfra-mcp-server Smart LLM routing across every major provider via one OpenAI-shape API. | |
| VoltPlan Wiring Diagrams yuzu-hub/wiring-diagram-mcp Generate 12V/24V/48V wiring diagrams and size wires, fuses, batteries, solar, and inverters. | |
| io.github.Yveshby27/brick-bacnet-mcp yveshby27/brick-bacnet-mcp Read-only BACnet/IP MCP gateway with Brick + Haystack semantic tagging at ingest | |
| MCP-Typescribe yworks/mcp-typescribe An MCP server that enables LLMs to understand and work with TypeScript APIs they haven't been trained on by providing structured access to TypeScript type definitions and documentation. | |
| EcomPick yxcerk/ecompick-mcp Find and compare ecommerce tools by task, platform and pricing, with sources and last checked dates. | |
| Multisim MCP yxy050208/multisim-mcp Generate Multisim circuits, run simulations, export data, and create experiment reports. | |
| Secret MCP yyeongjin/secret_mcp Local MCP server for isolated, evidence-backed GDWEB design analysis and web search. | |
| io.importly/importly-mcp yyildiz/importly-mcp Download, transcribe, and get metadata for any video/audio URL. Managed yt-dlp + speech-to-text. | |
| io.github.yyordanov-tradu/stock-scanner-mcp yyordanov-tradu/stock-scanner-mcp Stock and crypto market data — 49 tools for quotes, technicals, options, SEC filings, and more. | |
| NDEX Pricing yyunozor/ndex-pricing Swiss market prices for video games and consoles, with provenance. Read-only, OAuth 2.1. | |
| AgentPay yyxqqq777/mcp-server-agentpay x402 micropayments MCP: Xiaohongshu notes and paid APIs settled in USDC on Base. | |
| Nash-Arena yyyhy/nash-arena Chess and Card Game Arena For LLM | |
| io.github.yzonur/sap-adt-mcp yzonur/sap-adt-mcp Give Claude live access to SAP ABAP via ADT: read, search, check, test, and edit objects. | |
| Apple Music Playlist Curator z-han-z/apple-music-playlists Deep Apple Music curation: language-led selection, catalog grounding, and thoughtful listening flow. | |
| Z1N z1nprotocol/z1n-mcp MCP server for the Z1N Protocol - on-chain identity for AI agents on Polygon | |
| io.github.Z333Q/p402 z333q/p402-protocol Multi-provider AI router with x402 micropayment settlement on Base L2. 1% flat fee. | |
| io.github.z416479660/avc-test-py-mcp z416479660/avc-test-py-mcp MCP server for video enhancement (create_task, get_task_status, enhance_video_sync) | |
| Claude-Read-Outlook-Attachments zacccck/claude-mcp-read-email-attachments A MCP server for Claude that reads Outlook emails its attachments through the Microsoft Graph API. | |
| bbkt zach-snell/bbkt A Bitbucket CLI and MCP server written in Go for managing workspaces, repositories, pull requests, pipelines, issues, and source code. Supports stdio and HTTP transport. | |
| Agent API Gateway zachdreamz/agent-api-gateway-mcp Extract structured web data (product, article, company) for AI agents via Agent API Gateway | |
| AgentAtlas zachhhhh/agentatlas-mcp Sourced setup answers, MCP config for 15 clients and trending agent repos. | |
| io.github.zachlikefolio/tunnel-mcp zachlikefolio/tunnel-mcp Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16. | |
| Zactonz zactonz/zactonz-mcp Screenshots, page to Markdown, link previews, DNS, SSL, WHOIS, QR codes and more for AI agents. | |
| Clanksquare zacxdev/clanksquare Read Clanksquare's public channels, where AI agents post signed messages. Read-only, no key. | |
| p-e relay zaebee/p-e Read-only access to an append-only corpus of provenance-bearing coordination records. | |
| Grimoire for Gamemasters zafety-vibin/grimoire-mcp D&D and TTRPG campaign manager for GMs: your AI reads and writes a live, typed campaign database. | |
| Crypto Market Data zaffy18/crypto-market-data-mcp Live crypto market data and Hyperliquid wallet reports for AI agents, paid per call with x402. | |
| Bit Lantern zaguanlabs/atlas-scout-mcp Local, read-only structural code navigation and bounded dependency analysis for source repositories. | |
| io.github.Zahid-Abbas-Ali-Baig/document-converter zahid-abbas-ali-baig/document-converter Convert documents to Markdown using MarkItDown | |
| io.github.ZahiriNatZuke/local-delegate zahirinatzuke/local-delegate Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota. | |
| Whisper Transcribe zahirinatzuke/whisper-transcribe-mcp Transcribe audio locally with faster-whisper or through the OpenAI Whisper API. | |
| citable-mcp zaialamm/citable-mcp SEO and AI-visibility checks an agent buys per call: keyword research, on-page audits, Google rank and SERP data, backlinks, and AI-citation checks across ChatGPT, Claude, Gemini and Perplexity. 19 tools, $0.005–0.30 each, paid in USDC on S | |
| Capy zain/capy Startup cap table: ownership, SAFEs, vesting and round modeling, plus drafts for admin approval. | |
| Zain Saeed: hire a web developer zainsaeed615/zainsaeed-mcp Hire Zain Saeed (Fiverr Millionaire) for WordPress, Shopify and Next.js: services, prices, quotes. | |
| Mcp-Swagger-Server zaizaizhao/mcp-swagger-server A Model Context Protocol (MCP) server that converts OpenAPI/Swagger specifications to MCP format, enabling AI assistants to interact with REST APIs through standardized protocol. | |
| SPARDA zakariagharzouli/sparda AI writes. SPARDA proves. Deterministic, offline security gate for AI edits. | |
| Perplexity Agent zalez/perplexity-agent-mcp Multi-step web research with citations via Perplexity's Agent API. Standard library only. | |
| io.github.zamansheikh/memory-lean zamansheikh/memory-lean Token-lean memory for AI agents: a knowledge graph searched cheaply. Drop-in for server-memory. | |
| Zambo zambodotdev/zambo-mcp The verifiable work layer for AI: 153 tools, cross-AI handover, a verifiable receipt for every job. | |
| Baron zanaat-dev/baron Baron gives an AI coding agent one normalized contract for work orchestration: create and transition issues, cut branches, open and merge pull requests, and read CI and deployment status across Azure DevOps, GitHub and Slack. | |
| io.github.zaojiaoci/verified-rec zaojiaoci/verified-rec Hash-chained audit ledger for AI agent work — record, verify and replay what the agent did. | |
| io.github.zaplitny/atimelogger-mcp zaplitny/atimelogger-mcp MCP server exposing the ATimeLogger REST API (activities, reports, types) | |
| AgentPay zapnikita95/agentpay-mcp RU merchant catalog for AI agents: live price, stock, choices and controlled checkout. Not x402. |
21,201–21,250 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.