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 |
|---|---|
| io.github.jyswee/weselltours jyswee/weselltours Travel platform for coding agents: hotels, tours, bookings, 13 AI experts. 21 tools, stdio. | |
| Big Brain jzhao234/big-brain Plain-markdown second brain for you and your AI: notes, projects, tasks, search, links. | |
| io.github.jztan/pdf-mcp jztan/pdf-mcp Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR. | |
| io.github.jztan/qt4-doc-mcp-server jztan/qt4-doc-mcp-server Offline MCP server for local Qt 4.8, Qt 5, and Qt 6 documentation with full-text search. | |
| io.github.jztan/redmine-mcp-server jztan/redmine-mcp-server MCP server that lets AI assistants manage Redmine issues, projects, wikis, and time tracking | |
| io.github.K-Cupples/mockmcp k-cupples/mockmcp Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup. | |
| claude-skills-mcp k-dense-ai/claude-skills-mcp A Model Context Protocol (MCP) server that provides intelligent search capabilities for discovering relevant Claude Agent Skills using vector embeddings and semantic similarity. This server implements the same progressive disclosure archite | |
| Miro MCP k-jarzyna/mcp-miro Miro MCP server, exposing all functionalities available in official Miro SDK. | |
| K01 Synthetic Health Data k01labs/k01-mcp-server Privacy-preserving synthetic health data generation. FHIR R4/R5 compliant. | |
| harald k0nnect/harald helps coding agents work out the bluetooth le and classic protocol of gadgets you own | |
| MCP Bench Router k1ta141k/mcp-bench-router Routes design tasks to designarena.ai's top-ranked model via OpenRouter across 14 categories. | |
| io.github.k8ika0s/mcp-tmux k8ika0s/mcp-tmux Model Context Protocol server that lets LLMs collaboratively drive tmux | |
| io.github.kaael1/mcp-power-automate kaael1/mcp-power-automate Local MCP for Power Automate with browser-backed auth, target locking, review diff, and rollback. | |
| AgniGateway Marketplace kaanthan24/agnigateway-mcp AI marketplace — flights, tours, activities, transport & more via MCP. No auth required. | |
| AISentinel by BizDNAi kabzhanov/aisentinel Pre-tool policy enforcement + JSONL audit for AI agents. Apache 2.0. | |
| Kadal Deck kadalcc/deck Build it, rehearse it, own the room: draft, edit and publish MDX talks and follow their live rooms. | |
| Kadam Ad Network kadam-official/mcp-server Kadam advertising platform — manage ads, campaigns, creatives, audiences and stats | |
| kadenzo-mcp kadenzo/kadenzo-mcp Schedule, manage, generate, and analyze social posts across 11 networks (Instagram, TikTok, X, LinkedIn, YouTube, Facebook, Pinterest, Threads, Bluesky, Mastodon, Telegram) from any AI agent — 13 tools covering scheduling, media upload, AI | |
| io.github.kaditang/402sentinel-mcp kaditang/402sentinel-mcp DEPRECATED: hosted 402Sentinel retired 2026-10-31. Client for x402 payment-safety checks. | |
| io.github.kaditang/agent-wallet-mcp kaditang/agent-wallet-mcp DEPRECATED - hosted service retired 2026-10-31. Local non-custodial Solana MCP (you sign). | |
| Japan RuleWatch kadopi/japan-rulewatch-mcp Japan tourism entry and ecommerce evidence MCP for business agents; free tools and x402 pack. | |
| x402 MCP Starter kadopi/x402-mcp-starter Free self-hosted x402 USDC billing for Cloudflare MCP servers, with a Base Sepolia test endpoint. | |
| ai.pullpush/pullpush-mcp kaduno-systems/pullpush-mcp Connect any two APIs and keep them in sync — 50 MCP tools with shadow previews and diagnostics. | |
| OpenAPI Schema Explorer kadykov/mcp-openapi-schema-explorer MCP server providing token-efficient access to OpenAPI/Swagger specs via MCP Resources for client-side exploration. | |
| AutoMobile kaeawc/auto-mobile Mobile device interaction automation via MCP | |
| Smitline kaelorlabs/smitline Make phone calls and join Zoom, Teams and Google Meet meetings from any AI agent. Self-hosted. | |
| KAERIS i18n kaeris-io/kaeris-mcp Translate app language files into 46 languages and check placeholders, plurals and missing keys. | |
| Rocuronium kageroumado/rocuronium Drive macOS apps without taking the cursor: read, click, type, scroll, each with evidence. | |
| Kagura Memory Cloud kagura-ai/memory-cloud Persistent memory for AI assistants: store, search, and connect knowledge across conversations. | |
| io.github.kahlilashanti/mantis-mcp kahlilashanti/mantis-mcp Build proven high converting product showrooms and websites from your existing ecommerce catalog | |
| KaiCalls kaicalls/kaicalls-mcp A phone number for your business or your AI agent. Kai answers it and calls businesses for you. | |
| Kaidn kaidn-io/kaidn-mcp Explain fraud verdicts with evidence, surface account rings, and see who has burned other operators. | |
| pypreset kaierikniermann/pypreset Scaffold Python projects from YAML presets, augment existing projects with CI/tests. | |
| Taskwarrior MCP kaierikniermann/taskwarrior-mcp MCP server wrapping the Taskwarrior CLI for structured, project-scoped task management. | |
| io.github.kairosastro-sketch/mcp-ephemeris kairosastro-sketch/mcp-ephemeris NASA-validated computed planetary positions for your AI: 19 astrology tools, never hallucinated. | |
| io.github.KairosMobius/memory-nexus-mcp kairosmobius/memory-nexus-mcp Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs. | |
| io.github.KairosMobius/nexus-memory-mcp kairosmobius/nexus-memory-mcp Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs. | |
| TeTsuki Gateway kairosusunsei/tetsuki-gateway Checks whether a website has a usable llms.txt. Score 0–100. Free 3/day/IP, then ¥10. | |
| Luogu MCP Server kaiserunix/luogu-mcp-server Search Luogu problems, fetch statements, explore problem sets and get practice recommendations. | |
| io.kaitoi/studio kaitoi-labs/kaitoi-mcp Build and run visual creative-production workflows from your AI agent. | |
| io.twitterapi/mcp-server kaitoinfra/twitterapi-io-mcp-server Official twitterapi.io hosted MCP: Twitter/X tweets, users, followers, trends. OAuth or API key. | |
| io.github.kaitoy/nasa-images kaitoy/nasa-images-mcp-server MCP server with UI for NASA images | |
| AtomGit MCP Server kaiyuanxiaobing/atomgit-mcp-server A Model Context Protocol server that enables AI to manage AtomGit open source collaboration platform resources including repositories, issues, pull requests, branches, and labels. | |
| kops kaka-milan-22/kops A read-only kubectl MCP server for AI assistants. The kubectl verb is hardcoded in each tool
(get/describe/logs/events) and user input only fills argument values — no mutation path even with
malicious input, and Secret/ConfigMap values are | |
| io.github.kakha13/esim-mcp kakha13/esim-mcp Compare travel eSIM plans by country, and regional vs local pricing for multi-country trips. | |
| io.github.kalehdoo/warehouse-mcp kalehdoo/warehouse-mcp Production MCP server for Postgres, Oracle, Snowflake, BigQuery, Redshift, DuckDB, MotherDuck. | |
| k402-mcp kali123411/k402-mcp Pay-per-call MCP server for AI agents, offering text tools, web reading, and Kaspa blockchain data with automatic payment via Kaspa cryptocurrency. | |
| io.github.Kali123411/kx402 kali123411/kx402 Kaspa x402 agent payer — pay x402 v2 services on Kaspa (KAS) per call, no account or API key | |
| MCP Zotero kaliaboi/mcp-zotero Allows AI to interact with your Zotero library. | |
| io.github.kalki-kgp/whatsapp-macos kalki-kgp/whatsapp-mcp WhatsApp MCP for macOS - Read messages from local DB, send via WhatsApp Web. |
10,201–10,250 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.