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 |
|---|---|
| ZeroWidth Ledger Log decisions with expectations, add evidence, and track metrics in Ledger. | |
| ZeroWidth Napkin Draw boards, write docs and sheets, and build decks with your brand in Napkin. | |
| ZeroWidth Prism Explore ideas in Prism fields, run studies, and read research findings. | |
| ZeroWidth Workbench Build, run and publish Workbench flows, tasks, shims and knowledge bases. | |
| ZeroWidth Search, write and run work across Compass, Workbench, Caliper, Ledger, Prism and Napkin. | |
| Zevari The all-in-one LinkedIn MCP server: six outbound specialists for LinkedIn and email. | |
| Zicron medical chronology (public) Price, sample and request page-cited medical chronologies for law firms and LNCs. No sign-in or PHI. | |
| Zicron workspace (OAuth) Zicron account via OAuth: upload records, get page-cited chronologies, score SSDI and other claims. | |
| Zindex Immutable agent diagrams: create, edit, validate and render versioned diagrams over MCP. | |
| ai.zine/mcp Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere. | |
| zRev AI Grade any llms.txt, cold-read a homepage, run a B2B GTM ROI model, get a GTM diligence checklist. | |
| Ephemeral Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections. | |
| Fly Travel Albania Cached charter package, hotel facts and tour prices from Fly Travel Albania (Tirana); party-aware. | |
| Toys Hub Browse Toys Hub: products, prices in ALL, stock, delivery and checkout links. Read-only, no sign-in. | |
| ELIB - Armenian Digital Library Search and cite books, authors and subjects of elib.am, the free Armenian digital library. | |
| Mana Public Read-only MCP tools for Mana public creations, tags, creator profiles, and share pages. | |
| YerevanEstate — Yerevan apartment prices Yerevan, Armenia apartment prices: price per m² by district, street or point, rent, yields, deals. | |
| BrowserHere Control a real browser from AI agents: navigate, click, type, screenshot, read the page. | |
| Aalto FF&E product library for interior designers. Connect Claude, ChatGPT and Cursor. | |
| Acornonaut Turn YouTube playlists into AI flashcards and learn with spaced repetition. | |
| ActionDock Supervised API-write gateway for AI agents with policy, human approval and execution receipts. | |
| app.agendaforge/agendaforge Event management for organizers: events, sessions, speakers, agendas, forms, approval-gated writes. | |
| app.agendaforge/docs Search and fetch AgendaForge public documentation and marketing content. No authentication needed. | |
| app.agentguestbook/agent-guestbook Open guestbook for AI agents: read messages and leave a human-reviewed message. | |
| AgentIndex Search a curated directory of open-source AI agents, MCP servers and AI developer tools. | |
| Agentivity Run the agents, teams and workflows of your Agentivity workspace from your AI assistant. | |
| AgentBoard Autonomous agent coordination for beneficial projects: shared goals, tasks, review and handoffs. | |
| AI Backtester Backtest crypto trading strategies described in plain English, with fees and funding included. | |
| ailiste - new builds in Cyprus Cyprus new builds: buildings, dated site photos and stages, developers and district asking prices. | |
| AI Mechanic AI Mechanic — understand car symptoms and OBD-II codes, check recalls, get repair guidance. | |
| Novelist Prepare complete, illustrated AI novels in 22 languages; users review and pay on ainovelist.app. | |
| Aitho Turn a slide deck into a talk you rehearse out loud: voice-following script, slides, private Q&A. | |
| AltcoinChasersHQ: Acai crypto research Crypto research: launch, surge, daily picks, forensics, research jobs, monitors, rug checks. | |
| AltOrbit AltOrbit boards, tickets, time tracking, reports and client requests, with your rights in the app. | |
| app.anamneseai/anamnese A self-improving memory layer. Your memory, notes, tasks and goals, remembered everywhere. | |
| Anjal Email inboxes and calendars for AI agents: send, receive, search, draft and schedule. | |
| Dumaguete Extension Costs, travel, visas, hospitals, weather and places for Dumaguete, Philippines. | |
| Veliane Discovery Plus Facts, price, safety and join links for Veliane, free marriage-minded matchmaking. | |
| Ultra Billiard Pool Eight-ball pool in the browser: table state, shot physics, rules and live match data. | |
| app.applybolt/applybolt Search 200k+ live jobs and internships. Filter remote, salary, H-1B, then auto-apply on ApplyBolt. | |
| Arkame Backup Backups of servers, Docker and Zimbra to your own S3. Restore by chat; changes need 2FA approval. | |
| Artec Brand deals, winning example videos, video analysis and scripts for UGC creators. | |
| AskLoop Create and run surveys by chatting. Respondents just open a link — no AI, no account. | |
| StructForge Turn messy text into strict JSON schemas agents can trust (invoice, receipt, contact, resume). | |
| app.aspirelearning/mcp Aspire Learning MCP — browse courses, chapters, lessons, and import LaTeX quizzes | |
| Atelier Search and license original photographs for personal or commercial use, as screen and print files. | |
| Athlete Diary Your workout log in chat: history, progress, records, muscle volume, body weight, programs. | |
| Atlasly UK site research and worldwide CAD/GIS site context (DXF, GeoJSON, SVG) for architects | |
| AuditAE SEO MCP SEO MCP: Search Console, GA4, SERP and domain data, rank tracking, AI citations and site fixes. | |
| AuditFellow Your audit methodology inside Claude: findings, risks, controls and workpapers in your team format. |
27,851–27,900 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.