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 |
|---|---|
| Yandex Search MCP stufently/yandex-mcp MCP server for Yandex Search API (v2, Cloud) | |
| Yandex Webmaster MCP stufently/yandex-mcp MCP server for Yandex Webmaster API — site analytics, indexing, search queries | |
| Yandex Wordstat MCP stufently/yandex-mcp MCP server for Yandex Wordstat API — keyword research for Russian/CIS markets | |
| Zabbix AI CLI stufently/zabbix-ai-cli Task-shaped Zabbix access for AI agents: problems, host triage, metrics, maintenance windows. | |
| Voicely stulkovld/voicely Offline speech-to-text on macOS: transcribe audio/video files, read dictations and calls. | |
| Polar Health Data (self-hosted) stumason/polar-flow-server Self-hosted Polar health analytics with a built-in MCP server: sleep, HRV, workouts, baselines. | |
| com.stytrix/stytrix-mcp stytrix-ai/stytrix-mcp AI fashion design MCP: generate concepts, models, fabrics & looks live on your StyTrix canvas. | |
| VibeCodePicks suanrongbaicai/vibecodepicks Pick AI coding tools by goal: community-sentiment rankings, pricing, free tiers, alternatives. | |
| Cloak Proxy subcloak/cloak-proxy Read, mock, pause and replay HTTPS traffic captured by Cloak Proxy, a free macOS debugging proxy. | |
| io.github.subhajitlucky/rls-doctor subhajitlucky/rls-doctor Read-only Postgres/Supabase RLS audit with a rolled-back probe that proves who can read which rows. | |
| am.sublime/sublime sublime-co/skills Crie, avalie, calibre e publique agentes procedurais confiáveis em produção na Sublime. | |
| Subo subo-gg/subo-mcp Run Discord forms, surveys, polls and quizzes from your AI app: build, launch and analyze projects. | |
| LLMVerify subodhkc/llmverify-npm Local-first MCP server for LLM output verification — risk signals, injection and PII checks. | |
| Cloudinary Asset Management subomi/sample-mcp Upload, organize, search, and transform images, videos, and files with AI-powered tools. | |
| Subotiz Dev MCP(Deprecated) subotiz/dev-mcp Connect AI assistants to Subotiz - Using Subotiz's external capabilities through natural language | |
| Substrate substrate-memory/substrate-memory-plugins Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable. | |
| io.github.RAHULTRIPGAIN/tripgain-mcp-server sudheerrepala/tripgain-mcp-server Corporate travel booking and expense management for TripGain, exposed as an MCP server. | |
| StatOrigin sudoai-app/statorigin Sourced industry statistics. Read-only. | |
| io.github.sudomichael/gizmoanalytics sudomichael/analyticsautopilot Cookieless analytics for AI coding agents. Install in one prompt, 28 tools, OAuth onboarding. | |
| io.github.sudzikcoin/pingpoint sudzikcoin/pingpoint-freight-mcp Live truck GPS: create loads, read position, ETA, driver state, trip stats. API key or USDC x402. | |
| io.github.JasonColapietro/agentic-commerce-catalog suede-ai/suede-ai-app AI music, video, image, and voice tools callable by agents with USDC payments via x402 on Base. | |
| HerStack suggestic/herstack-mcp Read-only UK women's midlife health guidance: search, PubMed-backed evidence, supplement picks. | |
| io.github.Suigar-Gaming/mcp suigar-gaming/ts-sdks AI agent MCP server for Suigar casino game, SweetHouse, NFT, and referral transactions. | |
| Project Paced suleman-k/project-paced-v2 Plan, preview and edit timelines. Permanent Free tier; paid reporting and enterprise tools. | |
| AI Form API sum-eet/aiformapi-mcp Create forms, share the link and read responses as JSON or CSV from your AI agent. | |
| io.github.sumanaddanki/suma-memory sumanaddanki/suma-mcp Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session. | |
| AgentRaaS wrap sumedhchatse/agentraas Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged. | |
| Email Verifier (SMTP, MX, Catch-All) sumitrmardy/email-verifier-api Bulk email verification: live SMTP mailbox check, MX, catch-all, disposable and role detection. | |
| nepse.link summonshr/nepse.link Nepal Stock Exchange data: prices, company filings, signals, broker flow, IPOs, fund NAVs. | |
| Sunbird AI sunbirdai/sunbird-mcp African-language translation, chat, speech-to-text and text-to-speech from Sunbird AI. | |
| ai-audit-trail sundsoffice-tech/ai-audit-trail Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready. | |
| AILANG Parse sunholo-data/ailang-parse Parse 17 document formats and generate DOCX, PPTX, XLSX, ODF, HTML, Markdown and Quarto files. | |
| cliphou.se release videos sunmer/cliphouse Turns every release into a social video. Finds the selling points, picks the angle, writes the copy. | |
| Sunrise & Sunset Times sunrise-sunset-org/mcp Sunrise, sunset, twilight, golden hour and moon times for any place on Earth. Free, no API key. | |
| Contribution Exchange sunrisesillneversee/sigrank-app Contribution Exchange MCP: domain discovery, policies, preflight, proposals, and signals. | |
| io.github.suomimasuda/rightos-mcp suomimasuda/rightos-sdk RightOS MCP: privacy-first QR queue/EV/pickup. 20 tools, no end-user PII. | |
| Supabase supabase/mcp MCP server for interacting with the Supabase platform | |
| com.superagnt/superagnt superagnt/plugins superagnt: marketing plugin for Claude and ChatGPT. Find customers through outbound, SEO and ads. | |
| Evocrawl MCP Server superaihuman/evocrawl-mcp MCP server for Evocrawl — search, scrape, and interact with the web. | |
| superbot.gg · your own AI agent superbot-gg/superbot-mcp superbot is your own AI agent: anything you can do on your computer, it can do, fast. | |
| TrueCal superboxai/gptbot-food-calendar Use TrueCal from AI agents to review progress, meals, targets, trends, and supported updates. | |
| SuperCompress supercompress/supercompress Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex. | |
| Superdemands: Google Search Trends & Demand superdemands/google-search-trends-mcp Google search trends and search demand: 5 years of interest, momentum and seasonality per topic | |
| treg.to superdesigndev/treg OpenRouter for tools and data. Compare catalog providers and call them from one hosted MCP endpoint. | |
| SuperDuperBundle game prices superduperbundle/game-price-api Live PC game key prices: lowest listed price across official and key stores, with the compare link. | |
| Claimora superexposed/claimora Scientific and legal claim graph. Query claims, evidence, contradictions, and innovation flags. | |
| Sprites MCP Server superfly/sprites-mcp Manage Sprites: sandboxed compute environments with exec, services, and checkpoints. | |
| io.github.superlcr/hs superlcr/huasheng-cli Turn a script into a finished video with Huasheng: storyboard, narration, footage, export. | |
| Superlist superlistapp/superlist-mcp Manage Superlist tasks and lists in plain language from any MCP-compatible AI agent. | |
| Superlog superloglabs/superlog Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents. |
49,301–49,350 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.