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 |
|---|---|
| Bing Webmaster AI CLI MCP stufently/bing-webmaster-ai-cli-mcp Read Bing Webmaster data and change it, directly or through a reviewed plan. | |
| io.github.stufently/cloudru-s3-mcp-ai-cli stufently/cloudru-s3-mcp-ai-cli Cloud.ru S3 MCP server and AI CLI with scoped access and human approval for destructive actions. | |
| Google Webtools MCP stufently/google-webtools-mcp Google Search Console + GA4 for AI agents: properties, reports, indexing, verification, SEO. | |
| io.github.stufently/mws-s3-mcp-ai-cli stufently/mws-s3-mcp-ai-cli MWS S3 MCP server and AI CLI with scoped access and signed human approvals. | |
| io.github.stufently/selectel-s3-mcp-ai-cli stufently/selectel-s3-mcp-ai-cli Selectel S3 MCP server and AI CLI with scoped access and human approval for destructive actions. | |
| Telegram AI CLI MCP stufently/telegram-ai-cli-mcp Read a personal Telegram account over MTProto; every write is a plan a human applies. | |
| io.github.stufently/timeweb-s3-mcp-ai-cli stufently/timeweb-s3-mcp-ai-cli Timeweb Cloud S3 MCP server and AI CLI with scoped access and signed human approvals. | |
| io.github.stufently/vkcloud-s3-mcp-ai-cli stufently/vkcloud-s3-mcp-ai-cli VK Cloud S3 MCP server and AI CLI with scoped access and human approval for destructive actions. | |
| Yandex Metrica MCP stufently/yandex-metrica-mcp Yandex Metrica for AI agents: counters, goals, Reporting API and Logs API export over stdio. | |
| io.github.stufently/yandex-s3-mcp-ai-cli stufently/yandex-s3-mcp-ai-cli Yandex Cloud S3 MCP server and AI CLI with scoped access and human approval for destructive actions. | |
| Zabbix AI CLI MCP stufently/zabbix-ai-cli-mcp Task-shaped Zabbix access for AI agents: problems, host triage, metrics, maintenance windows. | |
| Stuga stuga-dev/stuga Your AI writes your self-hosted team wiki and answers from it. Its edits await approval by default. | |
| io.github.StuMason/coolify stumason/coolify-mcp 46 optimized tools for managing Coolify infrastructure, diagnostics, and docs search | |
| Stunt Double stunt-double/stuntdouble-mcp Deploy AI user personas to validate user journeys at scale. Find UX friction before real users do. | |
| CryptoTaxEdge sturs49/cryptotaxedge-mcp US tax classification for on-chain transactions: tx hash in → canonical category, tax treatment, confidence, and review flags out. 80+ chains. | |
| hostaway-kit stylabs/hostaway-kit-mcp-skills Read-only Hostaway MCP: listings, calendar, inbox, reports. Fixtures, no key. By STYLABS. | |
| io.github.Subcue/edititall-mcp subcue/edititall-mcp Drive EditItAll's local in-browser editors: PDF, sheet, photo, vector, Word, slides. | |
| SubcueAI subcue/subcue-mcp Public read-only MCP for SubcueAI: live pricing, latest desktop version, overview and FAQ. | |
| SubDownload subdownload/subdownload-mcp Public MCP wrapper for SubDownload.Fetch YouTube transcripts, search videos, browse channels and playlists — instant YouTube data for your AI workflow. | |
| BundlerMCP subelsky/bundler_mcp Enables agents to query information about gems in a Ruby project's Gemfile, including source code and metadata. | |
| link.obfus/utility-grid subether-labs/obfus-link-mcp 31 deterministic tools: JSON→Zod, regex, JWT, curl→fetch, hashing, encoding, UUIDs, encrypted links | |
| io.github.subhajitlucky/codebase-doctor subhajitlucky/codebase-doctor Read-only codebase audits for coding agents: secrets, RLS, deps, review verdicts. No writes. | |
| Twilize subhatta123/twilize Generate Tableau .twb/.twbx workbooks: 47 tools for charts, dashboards, rules, CSV pipelines. | |
| subimpact data (Apify) subimpact/data-mcp Google SERP + AI Overviews, AI Mode, SEA news mentions, Maps, Jobs, Trends and 13 more data tools. | |
| NimBooks subimpact/nimbooks-mcp Read-only Nimiq books: balances, history, statements, staking, payment and stake links. Never signs. | |
| Submitator submitator/submitator-mcp Launch your clients' products on up to 100 directories each from Claude, ChatGPT, Cursor or VS Code. | |
| AI AppSec subodhkc/ai-appsec Evidence-backed AppSec for AI applications and agents. Powered by HAIEC. | |
| io.github.subodhkc/mcp-tenant-isolation subodhkc/mcp-tenant-isolation Static analysis scanner for MCP server code and multi-tenant SaaS applications. | |
| Subotiz MCP subotiz/mcp Connect AI assistants to Subotiz - Using Subotiz's external capabilities through natural language | |
| com.proabono/mcp-installation subscriptiontech/proabono.mcp.installation Installs ProAbono into a website from the IDE: hosted pages, rights sync, catalogue, billing. | |
| DataLikers subzeroid/datalikers-mcp Instagram & TikTok data tools: demographic user search, analytics, posts, comments, hashtags. | |
| HikerAPI subzeroid/hikerapi-mcp Instagram data via HikerAPI: profiles, posts, reels, stories, comments, hashtags, locations. | |
| LamaTok subzeroid/lamatok-mcp TikTok data via LamaTok: profiles, videos, comments, followers, hashtags, search, downloads. | |
| freshprobe sudhan30/freshprobe Data freshness verification for AI agents. Probes endpoints for HTTP cache staleness, latency percentiles, content fingerprinting, TLS certificate health, DNS timing, and redirect chains.
Returns deterministic FRESH/STALE/UNKNOWN JSON verdi | |
| SEC EDGAR Filings sudiptohaldar/mcp_server_edgar Latest SEC filing and calendar-year filing history for a stock ticker, with official EDGAR links. | |
| io.github.sudo-ai-git/mcp-benchmark-hygiene sudo-ai-git/mcp-benchmark-hygiene Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM. | |
| io.github.sudo-ai-git/mcp-secret-scrub sudo-ai-git/mcp-secret-scrub Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values. | |
| io.github.sudo-ai-git/mcp-skill-sec sudo-ai-git/mcp-skill-sec Audit agent skills/prompts against 8 supply-chain attack patterns. Deterministic, no-LLM scanner. | |
| io.github.sudo-ai-git/mcp-verify-claim sudo-ai-git/mcp-verify-claim Force evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM. | |
| io.github.sudohnim/eidolon sudohnim/eidolon Privacy-first OSINT scanner: breaches, credentials, Shodan, username sweep. Scored PDF report. | |
| Gizmo Analytics sudomichael/gizmoanalytics-mcp Privacy friendly, cookieless web analytics built MCP-first.
"Add analytics to my Next.js app" → an AI agent runs the
setup_analytics_for_site tool, picks the right install snippet,
edits your layout file, and verifies the script is loading. | |
| io.github.sudomichael/search-console-mcp sudomichael/search-console-mcp Google Search Console for any MCP client - 30-second login, no Google Cloud project. Read-only. | |
| io.github.sudomock/mcp sudomock/mcp-server Product mockup API. Render PSD and photo mockups, generate videos, manage async jobs and webhooks. | |
| io.github.sudzikcoin/mcp-server sudzikcoin/suverse-mcp Pay-per-call x402 tools: crypto market pulse, wallet reputation, token check, endpoint search. | |
| Versum Agent Assistant sudzikcoin/versum-agent-assistant Local businesses for AI agents: what they sell, prices, delivery quotes, order and booking links. | |
| Notion MCP Server suekou/mcp-notion-server MCP Server for the Notion API, enabling Claude to interact with Notion workspaces. | |
| io.github.sugar-co-dev/roc-mcp-server sugar-co-dev/roc-mcp-server Creator commerce intelligence for TikTok Shop brands — benchmarks, ROC calculator, and brand fit. | |
| Japan Real Estate Intel sugukurukabe/japan-real-estate-intel-mcp Japan real estate MCP: land price, risk, foot traffic, renovation. 10 prefectures. | |
| JP Bids sugukurukabe/koko-call-mcp Read-only MCP server for searching Japan government procurement bid information from the KKJ portal. | |
| pod suhui-organization/pod Least-privilege compiler and MCP gateway for AI agents: run your agent in record-only mode, compile the smallest policy it actually needs from its real tool calls, enforce it at the gateway (deny > approve > allow), and keep a SHA-256 hash- |
19,001–19,050 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.