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 |
|---|---|
| MyFinanceBook Ask Claude about your income and spending, and import bank statements. No bank login. | |
| MyGhosts Send AI bots to attend meetings on your behalf. Get recordings, transcripts, and summaries. | |
| Meo Studio AI video ads, dubbing in the speaker's own voice, and images and clips from top models. | |
| myocr.app Convert PDF bank statements into Excel and check that the balances add up. Invoices and tables too. | |
| NailMe – Book nail studios Find nail studios near you, see services, prices and free times, and prepare a booking to confirm. | |
| NameHound Is a brand name free as a .com/.net/.org/.app domain and as a Bluesky, Mastodon, npm or PyPI handle? | |
| BidSwarm A public 500-rank ad board where every bid decays 1%/h. Read it, buy a rank, or try it free. | |
| webcheck The website checker for AI agents. One call: verdict, score out of 100, fix list. | |
| Neotic AI agents create contextual in-app experiences, announcements, and triggers with Neotic. | |
| Agent Rescue Desk Production Triage Read-only triage for n8n, MCP, webhook, and AI agent workflow production failures. | |
| Mat Web & Data Toolkit (x402) 28 pay-per-call web/data tools: RDAP, SSL, DNS, SEO, FX, crypto, more. 0.01 USDC each via x402. | |
| Chain Check (x402) x402-paid on-chain tools: wallet report, contract scan, token risk, gas, address labels (USDC/Base) | |
| LION - Trend Intent MCP + Marketplace Visibility Audit x402-paid MCP data: trend feed + visibility audit. USDC/Base. No API key. No PII. | |
| app.netlify.japan-data-mcp/japan-data-mcp Japanese law, corporation & statistics data as MCP, normalized to English with source attribution. | |
| Nexo Meinlem — fórum e universo agent-first Fórum persistente com conversa MCP, assembleias, jogos multiagente e universo Meinlem. | |
| Nexo Meinlem — open social space for agents Open agent forum: read, debate, reply as a guest, play together and return voluntarily. | |
| app.netlify.micropay-test-suite/micropay-test-suite Verify your agent's x402 payment flow for free on Base Sepolia testnet before real money moves. | |
| Japanese Order Eval Regression checks for Japanese order automations: six free cases, strict JSON scoring and CI gates. | |
| TenderDelta TED procurement notices and changes for AI workflows, with source links, deadlines and freshness. | |
| USDC & RPC Reference (free) Free read-only data: verified USDC addresses and EIP-712 domains, measured RPC eth_getLogs limits. | |
| netrack Track your net worth with any AI assistant: read totals and goals, record values in any currency. | |
| NeuroRank Esports cognitive-combine data over MCP: free cohort stats, paid player & team scouting reports. | |
| NeverBlank Rehearse hard conversations: lessons, XP drills and practice opponents built from your situation. | |
| Newsmind Read, search and track your RSS feeds: semantic search, story clustering, watches, OPML import. | |
| Nexusol Search Solana ecosystem projects and read sourced Solana news from Nexusol. | |
| NFTm Quote an NFTm launch. The creator signs in Phantom. | |
| NIAR Which nearby physical shops in Spain have a product: stores, stock, prices, hours. | |
| nice to have Find ready-made build kits for Claude Code and Codex: slides, LINE stickers, pixel art, games. | |
| noback Publish AI-made HTML apps as shareable links that save and sync data. No account or token needed. | |
| NoMac (all tools) Everything NoMac in one server: the Mac, the cloud iPhone and the App Store. | |
| NoMac App Store Signing, TestFlight, App Store metadata, screenshots and App Review for AI agents, on a NoMac Mac. | |
| NoMac Cloud iPhones and Macs with Xcode for AI agents: build, run and test iOS apps, use the screen. | |
| NoMac Session The cloud Mac alone, with Xcode, for AI agents: run commands, build and test, use the screen. | |
| NoMac Simulator Cloud iPhone Simulators for AI agents: build the Xcode project, read the screen, tap by label, test. | |
| Nombox Your recipe box, shopping lists and meal plans, plus public recipes to discover. | |
| Nomok Check name availability on 70+ platforms: domains, social networks, marketplaces. | |
| NoteCube Your NoteCube meeting and lecture recordings: search, read transcripts, and write cited documents. | |
| NoteFit Plan and manage strength training for athletes — mesocycles, weekly volume, and shareable plans. | |
| NovumOS Kanban where AI agents are first-class users — real seats, real API, no AI credit meters. | |
| NudgeBell Reminders your agent creates: email, WhatsApp, SMS or call, in steps you set. Stops on acknowledge. | |
| Octopad The AI brain for builders: ChatGPT, Claude and your other AIs share one workspace and one method. | |
| app.ofia/latex Persistent AI LaTeX workspace: edit and compile multi-file projects, export publication-ready PDFs. | |
| Oh Dear Website monitoring: uptime, SSL certificates, broken links, DNS, cron jobs and status pages. | |
| OIO Projects, tickets, notes and to-dos in OIO, the freelance workspace. OAuth sign-in, Pro plan. | |
| Oktio.app Instagram analytics, media kits, bio link and brand deals for creators, from your AI assistant. | |
| ONCE Music distribution for agents: upload, AI-check, submit and track releases on ONCE. | |
| One's Vibe Search a curated gallery of live, tryable AI-built products for prior art. Read-only, no auth. | |
| OnlineFitness.app Manage fitness coaching clients, workouts, programs, chats and funnels from your assistant. | |
| OpenClip Turn long videos into short, captioned viral clips from your AI assistant. 28 tools, OAuth. | |
| OpenDealer MCP Server Automotive inventory search for AI assistants: vehicles, dealers, deals, and market data. |
28,201–28,250 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.