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 |
|---|---|
| Ployz getployz/ployz Deploy apps, databases and previews to your own servers. Run Ployz Cloud from your agent. | |
| io.github.jaygould/getpronto getpronto-io/getpronto-mcp Upload, transform, and manage images on Get Pronto from AI agents. | |
| Docsy getremcp/docsy-plugin Read versioned developer documentation with original source links using five public MCP tools. | |
| io.github.getsentry/sentry-mcp getsentry/sentry-mcp MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants | |
| com.xcodebuildmcp/XcodeBuildMCP getsentry/xcodebuildmcp XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities. | |
| SPM - Structured Project Memory getspm/spm-agent-connectors Durable, shareable and governed project memory with smart triage and explicit project composition. | |
| STACK getstack-run/stack Command your AI agents: verifiable passports, credential injection, full audit, revoke in 60s. | |
| dev.getstub/check getstub/recipes Verify what an AI agent did for someone, and what commercial influence the operator disclosed. | |
| Verdict — Compliance for AI-Generated Code getverdict-ai/releases Compliance verdicts for AI-generated code. SOC 2, HIPAA, HITRUST for healthcare IT. | |
| ai.getvet/vet getvetai/vet Discover and vet MCP servers: search 200K+ AI tools with security verification and schemas. | |
| getwowlink getwowlink/mcp Check link previews (Open Graph, Twitter cards) on X, LinkedIn, Slack; OG images per page. | |
| MCP OAuth Connect gfb2026/mcp-oauth-connect Ping-only MCP origin for claude.ai, Desktop, Cursor, and Grok Connectors. | |
| Corent gg13121/corent-mcp Generate images, videos, voice, and text via the Corent API. Auto model routing with fallback. | |
| com.useweckr/weckr ghiles3232/weckr-sdks Ask which of your customers cost more in LLM calls than they pay, per user and per feature. | |
| Buddy phone tools ghorbelhamdi/buddy-android Android phone tools for AI agents (read the screen, tap, type, open apps), served by the Buddy app. | |
| Ghost Networks ghost-networks/ghost-mcp Private, programmable networking for the AI age: manage networks, devices, hubs and VPN. | |
| Tesla Wrap Design ghostcatcg/wrap-design Design Tesla Paint Shop wraps from your AI assistant with 3D preview and export links. | |
| Ghostchars ghostchars/ghostchars Find and remove invisible Unicode: zero-width, tag smuggling, bidi, homoglyphs. Offline. | |
| io.github.GhostlyGawd/codeweb ghostlygawd/codeweb See what your AI edits affect. Structural checks for AI code changes. 28 MCP tools, no LLM. | |
| io.github.GhostlyGawd/engineering-board ghostlygawd/engineering-board Repository-owned engineering pattern intelligence - 19 MCP tools over stdio. | |
| io.github.giancarloerra/januscope giancarloerra/januscope Local MCP proxy for tool restrictions, response redaction, audit logs, and database schema context. | |
| GigHQ.ai gighq-ai/gighq-skill Job-search tracker for AI agents: applications, stale follow-ups, skills gaps, H-1B lookup. | |
| io.github.gigsoul/x402-api gigsoul/x402 AI API for marketing, content and outreach. 22 endpoints. Pay with USDC on Base via x402. | |
| Fantasy Premier League (FPL) gilbertkamau/fpl_mcp FPL data, points predictions, and transfer, captain and chip advice for any team. | |
| io.github.Gildaraio/mcp-server gildara/mcp-server Operating contracts for AI agents. Structured instructions compiled into system prompts. | |
| Analook — Competitor Intelligence gingiris/competitor-analysis-tool Competitor intelligence for AI agents — SEO, traffic, social, Product Hunt, pricing, AI insights. | |
| io.github.ginokino/swarmpay ginokino/swarmpay-sdk Payment layer for AI agents. Send USDC, manage escrows on Base blockchain. | |
| MemoStem girapphe/memostem-plugins Your reviewed knowledge, across AI conversations. | |
| Geobble giseity/geobble Geospatial workspace: manage sources and maps, run spatial analysis, and publish interactive maps | |
| AI Pricing Hub gishh/aipricinghub Source-backed AI model pricing, rankings, history, and benchmark data. | |
| Giskard Origin giskard09/mcp-origin Free bootstrap MCP server for new agents. Pointers to the Mycelium ecosystem. | |
| Yandex Direct gistrec/mcp-yandex-direct MCP server for Yandex Direct API v5: manage PPC campaigns, ads, keywords, and statistics. | |
| SMS en Masse git-acet/smsenmasse-mcp Envoyez des SMS et gérez vos campagnes directement depuis vos agents IA. | |
| io.github.git-akki/sendpookie git-akki/sendpookie Create and send cinematic digital gifts for birthdays and anniversaries via Claude. | |
| Earth-2 Elevation MCP gitcookman/earth-2-elevation-mcp Local stdio MCP server for Open-Elevation single, batch, and profile lookups. | |
| KnowFirm gitdhillonai/knowfirm-mcp U.S. business lookup and search via KnowFirm. Bring your own API key; each call uses 1 credit. | |
| io.github.GitGudatCodeing/vault-index gitgudatcodeing/claude-second-brain Local hybrid keyword + vector search (SQLite FTS5 + sqlite-vec) over markdown vaults and code. | |
| io.github.GitHub30/note-mcp-server github30/note-mcp-server MCP server for note.com: create, edit and retrieve posts. | |
| io.github.GitHub30/qiita-mcp-server github30/qiita-mcp-server Publish articles to Qiita via MCP tools. Minimal, fast, and focused on Qiita authoring. | |
| io.github.GitHub30/zenn-mcp-server github30/zenn-mcp-server MCP server that posts to Zenn. | |
| duke-book githubdujianfeng/duke-book Manage Duke Bookmark notes, categories, and plan-enabled knowledge search over MCP. | |
| SEO Content Machine gitterebi/seo-content-machine-plugin Run SEO Content Machine tasks from an MCP client: scraping, crawls, Google Maps, Workspace pages. | |
| GitWhy — The Context Layer for Git gitwhy-cli/gitwhy The shared AI context engine for git — save, search, and share the reasoning behind code changes. | |
| CRA AGENT giupy997/arcagentx402 Lets an agent pay for x402 APIs in USDC on Arc, under a spending policy it cannot change. | |
| ListSignal giushansen/listsignal-mcp B2B sales intelligence: tech stack, Shopify apps, revenue, hiring, contacts and change signals | |
| PuppyMacro giuvincenzi/puppymacro Auto clicker, macros and hotkeys for PC. AI-ready. Needs the PuppyMacro app installed. | |
| Gizmos Audacity gizmos-quest/gizmos-audacity-mcp Safe local audio editing, analysis and production in Audacity 3.7 through mod-script-pipe. | |
| gjalla gjalla/engineering Hosted self-curating shared memory that keeps your agents working like a high-performing team | |
| com.theartofservice/compliance-intelligence gjb65/compliance-mcp-skill-example What one compliance standard already evidences of another, with the reasoning and the rejections. | |
| io.github.gkcogz/1trippulse gkcogz/onetrip-beta 1trip PULSE: 21-tool AI travel planner. Flights, hotels, visa, safety, weather, 120+ cities. |
23,401–23,450 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.