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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Hub-Equity MCP hub-equity/hub-equity-mcp Standardized, restatement-aware SEC + European (ESEF) XBRL fundamentals, served to your agent. | |
| io.github.hubertgajewski/playwright-report-mcp hubertgajewski/playwright-report-mcp Run Playwright tests and surface structured results for AI agents doing test failure analysis. | |
| Hubertino: Google Maps leads hubertino-app/hubertino-mcp Scrape Google Maps business leads (phones, websites, emails, socials) with Hubertino. | |
| Nostr Signer hudhaifahz/nostr-signer-chatgpt Approve Nostr signatures with your own browser signer without exposing a private key. | |
| io.github.hufirst/onsense hufirst/onsense Android phone camera, sensors & files for any MCP client — local, no cloud, no ADB. | |
| Evernode MCP hugegreencandle/evernode-mcp Evernode/HotPocket dApp helper: templates, non-determinism lint, lease math, live host lookup. | |
| Xahau MCP hugegreencandle/xahau-mcp MCP server for the Xahau network — offline Hook WASM VM + static analyzer, read-only ledger tools. | |
| mcp-baostock-server huggingagi/mcp-baostock-server A stock data MCP server based on BaoStock that provides multiple interfaces for retrieving stock market data. | |
| Heventure Search MCP hughescuit/heventure-search-mcp Enables web search without API keys using DuckDuckGo and Bing search engines, and retrieves webpage content. Supports multiple search engines simultaneously with privacy protection and asynchronous processing. | |
| CodeCartographer huginnindustries/codecartographer Turn an unfamiliar codebase into validated architecture, contracts, and a reimplementation spec. | |
| io.github.HugoF1234/gilbert-mcp hugof1234/gilbert-mcp Gilbert meetings: list, search, and fetch transcripts & summaries via MCP. | |
| langfuse-mcp hugoles/langfuse-mcp a typescript mcp to a langfuse MCP that enables you to see and connect agents to lanfuse data | |
| Agentic MCP hugolsramos01-bit/mcp-agentic-server Local coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution. | |
| Traintrackr hugorodgerbrown/traintracker GB (National Rail) train times: live departures, platforms, timetables and journey planning. | |
| WeChat FastBridge huj28-creator/wechat-fastbridge Local macOS MCP server for verified WeChat reading, sending, media, and token-efficient allowlisted monitoring. Its Docker image supports registry introspection only; real WeChat automation requires macOS Accessibility. | |
| io.github.hulin42/keynote-harvest-mcp hulin42/keynote-harvest-mcp Harvest Keynote and PDF slide decks into previews, text, image assets, and a manifest for agents. | |
| humanbottasks humanbottasks/humanbottasks Human fallback for AI agents: delegate tasks to a human over MCP. | |
| io.github.humanjesse/textarttools-mcp humanjesse/textarttools-mcp Unicode text styling and ASCII art generation with 23 styles and 322+ figlet fonts | |
| MagicScreenshots humanleap/magicscreenshots-mcp Search real App Store screenshots and preview videos; generate and localize your own. | |
| ToolRouter humanleap/toolrouter-mcp The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call. | |
| Label Studio MCP Server humansignal/label-studio-mcp-server Label Studio MCP Server | |
| io.github.humantextpro/mcp-server humantextpro/mcp-server AI text detection and humanization for Claude Code, Cursor, and Windsurf. | |
| tabpilot-mcp hunglp97/tabpilot-mcp Drive the real, logged-in Chrome you already have open — cross-platform, token-budgeted reading (90%+ savings), and 24/7 headless Ubuntu support. | |
| Bruno MCP hungthai1401/bruno-mcp MCP Server for running Bruno Collections | |
| io.github.hunta-ai/gather hunta-ai/gather Attestable memory for AI agents: curated writes, verifiable tenant isolation, bi-temporal facts. | |
| Signal Desk paid tools huntercarver24/signal-desk x402-paid tools: render pages, host files, delayed callbacks, pump.fun launch feed, trend radar | |
| AdvertiserLeads hunterint/advertiserleads-mcp Ecommerce brands that just started, scaled or stopped Meta ads, with store platform and pixels | |
| io.github.hunterpercival/apex hunterpercival/apex-mcp-server APEX — AI operating system for founders. Join waitlist or request a demo. | |
| Google Workspace MCP VE huntsdesk/ve-gws Most Google Workspace MCPs let you read. This one lets you write — 28 authoring tools on top of taylorwilsdon/google_workspace_mcp, including markdown-to-Docs, smart chips, and recursive Drive copy. | |
| io.github.huoshuiai42/huoshui-fetch huoshuiai42/huoshui-fetch An MCP server that provides tools for fetching, converting, and extracting data from web pages. | |
| io.github.huoshuiai42/huoshui-file-converter huoshuiai42/huoshui-file-converter An MCP server that provides document format conversion | |
| io.github.huoshuiai42/huoshui-file-search huoshuiai42/huoshui-file-search An MCP server that provides fast Spotlight file search capabilities for macOS | |
| io.github.huoshuiai42/huoshui-pdf-converter huoshuiai42/huoshui-pdf-converter An MCP server that provides PDF file conversion | |
| io.github.huoshuiai42/huoshui-pdf-translator huoshuiai42/huoshui-pdf-translator An MCP server that provides PDF translation service | |
| io.github.HurleySk/can-see hurleysk/can-see Let AI agents see and interact with terminal/CLI apps via PNG screenshots | |
| io.github.husain-zaidi/ros-mcp husain-zaidi/ros-mcp MCP for ROS 2 monitoring, debugging, and managing nodes, topics, services, and TF2 frames. | |
| io.github.Hustada/collective-memory hustada/collective-memory MCP server for persistent, semantic memory across AI sessions | |
| MCP ECharts hustcc/mcp-echarts Generates Apache ECharts diagrams and charts with AI dynamically, supporting all ECharts features and exporting to png, svg, and option formats. | |
| Hustle Got Real hustlegotreal/hustlegotreal-mcp Dropshipping for eBay, Amazon and Shopify: products, listings, prices, stock, orders and analytics. | |
| dsh-cua - Windows Computer Use hutusion/dsh-cua Windows computer-use MCP server for dsh (DeepSeek Harness), client-neutral, 19 tools. | |
| ai.smithery/huuthangntk-claude-vision-mcp-server huuthangntk/claude-vision-mcp-server Analyze images from multiple angles to extract detailed insights or quick summaries. Describe visu… | |
| All Paint Colours hwam91/allpaintcolours-api Every UK paint colour, matched across brands by ΔE and priced; palettes, planner projects, trends. | |
| io.github.hxckya/pkgtruth hxckya/pkgtruth Catches hallucinated and slopsquatted npm and PyPI packages before an agent installs them. | |
| Check AI Free — Image Source Clues hyai-dev/checkaifree-mcp Inspect editable image source clues. No C2PA signature verification or authenticated origin. | |
| io.github.hybridforgelab/distill-mcp hybridforgelab/distill-mcp Web pages to clean Markdown for AI agents, honouring robots.txt and AI opt-outs. | |
| io.github.hybridforgelab/shipshape-mcp hybridforgelab/shipshape-mcp Dockerfile and Kubernetes lint for AI agents: Pod Security Standards, A–F grade, a fix per finding. | |
| io.github.hybridforgelab/specwise-mcp hybridforgelab/specwise-mcp OpenAPI and JSON Schema validation and OpenAPI breaking-change diffs for AI agents. | |
| io.github.hybridforgelab/unfold-mcp hybridforgelab/unfold-mcp PDF, DOCX, PPTX and XLSX documents to Markdown for AI agents, from a URL or a local file. | |
| K-Work Trust hycore220/k-work-trust-public-demo Korean business record validation and workflow safety gates for AI agents. | |
| Hydrata - ANUGA Flood Simulation hydrata/hydrata-mcp-server Run ANUGA flood simulations, track progress, and retrieve results on Hydrata Cloud. |
9,001–9,050 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.