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 |
|---|---|
| Kolonie AI kolonie-ai/kolonie-platform A colony of AI citizens: join with no credential, prove skills, earn, vote on the rules. | |
| io.kolvera/kolvera kolverahq/kolvera-mcp AI sales & BD platform for Australian recruiters: search, enrich, campaign, research, reports. | |
| komnet komdosh/komnet Lets AI coding agents coordinate asynchronously through a private git repository. No server. | |
| koment koment-dev/koment Read and write checked code rationale stored outside source comments. | |
| Komplyt Zero komplyzen/komplyt-zero Persistent working memory for AI agents: a knowledge graph with semantic search and decay. | |
| Kompressr kompressrcdn/clients Upload, optimize and manage files, wait for processing, and generate private delivery links. | |
| Kodecz konecz/kodecz Render, preview and check videos written as web pages (HTML to MP4 on NVIDIA GPU or CPU) | |
| Kongen Labs — Pattern Intelligence kongenlabs/kongen-mcp LLM reasoning regime detection, cross-domain pattern transfer, and model routing. | |
| KongMing Growth MCP kongming-ai/mcp-server Cross-border growth tools: mentions, pain points, competitors, GEO, synthesis, AI media. | |
| OpenToonz MCP konkomaji/opentoonz-mcp Animate in OpenToonz from an AI assistant: native vector levels, xsheet timing, rigs and physics. | |
| io.github.konni-arcadia/moontide konni-arcadia/moontide Claude steers live music by writing Strudel code played in a browser page | |
| io.github.konstantinbozukov/pathmint konstantinbozukov/aave-keeper-paper Before you pay an x402 URL, ping it live or dead. One cent, USDC on Base. | |
| Agent Docs konstantinstarovoytov/agent-docs Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily. | |
| Koopscan koopscan-com/koopscan-mcp Dutch address data for AI assistants: BAG building facts, energy labels, reviewed crime signals. | |
| io.github.koreal6803/finlab-ai koreal6803/finlab-ai Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples. | |
| com.koreastockcheck/mcp koreastockcheck/mcp Background checks for Korean stocks - 10 years of DART filings for all KRX companies, in English | |
| Korext: AI Code Governance korext/enforce-action Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles. | |
| Kortexio Memory kortexio/contextmemory Hosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth. | |
| kosa8 kosa8ai/kosa8-claude-plugin Secure infrastructure for AI agents: sealed microVM sandboxes you can checkpoint, rewind and fork. | |
| tidex6 — private payments on Solana koshak01/tidex6 Private USDC/USDT payments on Solana: hidden amounts, unlinkable, optional auditor. | |
| logr koshikraj/logr Query any public logr profile — timelines, events, full context — plus owner-authorized writes. | |
| com.mographr/motion-tools kossik/mographr-mcp-docs Render animated motion-graphics overlays as MP4: lower thirds, titles, callouts | |
| io.github.kota1026/bridgeguard-mcp kota1026/quantum-shield BridgeGuard MCP Server - Cross-chain bridge security audit tools for AI coding agents. Scan bri... | |
| io.github.Kotaro-Studio/curanz-sounds kotaro-studio/curanz-sounds 生年月日から占いを計算して答える。星座・九星気学の本命星と年盤・四柱推命の日干と流年・天中殺・数秘術の個人年。出生時刻は不要。古典の暦法による計算。 | |
| io.github.Kotaro-Studio/kuongeo kotaro-studio/kuongeo-py Japan: next bus/tram/boat from 26 places, RTK bases, JMA warnings, municipality facts. No key. | |
| io.github.Kotaro-Studio/kurashigram kotaro-studio/kurashigram 日本の暮らしの値段を毎日調べて答える。日用品・家電の最安値、81市の物価、ふるさと納税、給付の手引き。出典つき、推定なし。 | |
| Prozorro kotiniiqq/prozorro-mcp Ukrainian public procurement (Prozorro): open tenders, plans, competitors, red flags. No keys. | |
| Kourier kourierai/mcp Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup. | |
| Kova kovatools/kova-agent-plugin Saves a declared investment strategy so any agent can check a portfolio against it. | |
| Blackbook Protocol Advisor koynlabs/mcp-blackbook Purchaser-gated MCP for Vault, HMRC TRS, 95/5 equity, and Companies House PSC. | |
| KOYN FX koynlabs/mcp-koynfx Remote MCP for KOYN FX: account, markets, and TradeLocker tools over OAuth. | |
| Plott koynlabs/mcp-plott UK planning MCP: applications, workspace, and outreach over Streamable HTTP OAuth. | |
| KrabiClaw krabiclaw/krabiclaw Manage and publish restaurant and local business websites through MCP. | |
| MONARK kraidleai/monark Commit / defer / abstain over a conformal coverage region - not a probability of being right. | |
| Grant Search kramer-hans/krimskrams-product Search U.S. federal grants and EU funding topics; monitor changes and download snapshots. | |
| io.github.krampslaag/uniteddepin krampslaag/uniteddepin UnitedDePIN MCP server for aggregating DePIN nodes. | |
| Make Effects krasnoperov/inventory Generate reproducible image, video, and audio assets with leading models and your own provider keys. | |
| io.github.krayinc/docbase krayinc/docbase-mcp-server DocBase MCP server for AI agents | |
| KissMySkills kreal-51/kissmyskills-plugin Search a catalog of AI skills and load one into your chat; small AI CRM board. OAuth sign-in. | |
| Kreuzcrawl kreuzberg-dev/kreuzcrawl Scrape, crawl, and map websites to Markdown or JSON via local CLI. | |
| DesiData krishnakaushik195/desidata Search India datasets; inspect sources, licences and previews; get notebook and Python examples. | |
| RobotActions — AI-Driven Mobile + Web Test Automation krishtoautomate/robotactions Drive real Android & iOS devices and web browsers from natural language for mobile + web QA. | |
| Rowfeed Search & Market Data kristerkb-pixel/rowfeed-seo-mcp ChatGPT visibility, SERP, Ads, Maps, Hotels, traffic, backlinks, News, Amazon, jobs, Trends. | |
| Zhihu kristhl181/zhihu-cli Zhihu CLI for AI agents: search, read, download, and publish from the terminal. | |
| EcoScope krnzt/ecoscope Agent-native ecological data discovery, analysis, visualization, and provenance | |
| io.github.Kromatic-Innovation/fermi kromatic-innovation/fermi Calibrated probability ranges for forecasting questions, with the assumptions behind them. | |
| Neumann kromatic-innovation/neumann Monte Carlo ranges for uncertain plans: project cost, budget, timeline, capacity, NPV/IRR/payback. | |
| Vector DB MCP kroq86/plojure Assembly-accelerated DuckDB MCP server for code search, indexing, and symbol lookup. | |
| ouicu kroqdotdev/ouicu-js Share a dev server or upload a built site at a public https link, and hand the link back. | |
| webhooks.cc kroqdotdev/webhooks-cc Capture, inspect, send and assert on webhooks and inbound email from your coding agent. |
24,851–24,900 of 50,909
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.