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 |
|---|---|
| Imagemeta Write SEO metadata (title, alt text, keywords, copyright) into JPEG, PNG, WebP. Paid per call, x402. | |
| Pagemd Read any public web page as clean Markdown for LLMs, with its metadata. Paid per call, x402. | |
| Speak Text to natural speech as MP3: 38 voices, 7 languages, 1,000 chars per call. Paid per call, x402. | |
| Keyframer 150+ React Native animation recipes, scene authoring, phone preview via QR, Reanimated v4 codegen | |
| Agent Verification Utility Deterministic JSON checks with signed evidence and x402-paid execution | |
| KitRank use cases Read-only catalog of 1,900+ real, sourced AI agent use cases with tools, cost and setup prompts. | |
| knowsme One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor. | |
| Kognite Hosted agent memory: store, search, and recall facts across sessions from any MCP client. | |
| lastseen score Trust scores and dated liveness/drift facts for MCP servers, from the lastseen.dev notary register. | |
| dev.latamref/reference-data LatAm govt data, cited to source: rates, VAT, tax, wages, holidays, FX. 22 countries; Brazil free. | |
| Laterbase A shared backlog for the out-of-scope work your coding agents find. | |
| Launchdog Launch your product on Launchdog's weekly board from your coding agent: list, verify, badge, book. | |
| Launchdog (read-only) Read-only Launchdog board: search this week's launches, past winners and upcoming launch weeks. | |
| Layoutline Compose a landing page from layouts observed on real pages, then review the built page for drift. | |
| Layro Search, install and publish reviewed React components from Layro, with exact install plans. | |
| dev.lekta/lekta Audits how AI answer engines read a page and grades it A+ to F across four measured layers. | |
| Lettera Messaging and inboxes for AI agents: register, send signed messages, check your inbox, find agents. | |
| letterport Real email inboxes for AI agents: create addresses, read mail as JSON, reply in threads. | |
| dev.lingo/main Lingo.dev MCP Server - World-class i18n implementation with ICU MessageFormat. | |
| dev.llms-txt-validator/llms-txt-validator Validate a site's llms.txt against the spec: fetches every linked URL, scores it 0-100. | |
| Official Logo.dev MCP Find brands, logos and brandmarks, and manage brand subscriptions and webhooks with Logo.dev. | |
| dev.looptool/looptool An MCP server that automatically collects feedback on your MCP server. | |
| Loudcode Turn what you just built into build in public posts for X, in your voice. Drafts, queue, metrics. | |
| ludoteca.dev Open video game database: where to buy each game, store IDs, studios and publishers. | |
| theRoom Luiz Cordeiro's room in Curitiba: an AI engineer's portfolio, with a dog and a locked door. | |
| MachineMail Email inboxes for AI agents. Send, receive, and read email with a trust report on every message. | |
| Mainline Gives your AI agent your story map and given/when/then acceptance criteria. Read-only. | |
| MapsScraper.dev Research public business listings, reviews and photos into lists with explicit unit budgets. | |
| dev.marksiazon/profile Read-only MCP server for Mark Siazon's professional profile: projects, FAQ, proof, availability. | |
| Mascotline One mascot, locked once, drawn in any scene on demand and checked against its own identity. | |
| Mash Prime Read Mash Prime's essays and build notes on agentic systems, memory, approvals, and workflows. | |
| mcpnav directory Search a directory of MCP servers and get connect configs. Data is CC0/MIT-licensed. | |
| dev.mearef/reference-data Mid-East govt data, cited to source: rates, VAT, tax, wages, holidays, FX. 9 countries; UAE free. | |
| Memmo Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP. | |
| dev.memnode/memnode Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint. | |
| Mentio Social listening for agents: brand mentions across 16 platforms, scored for relevance and intent | |
| MESSORA Scrape, crawl and search the web for AI agents via MCP. | |
| dev.metarun/metarun Run App Store Connect from your IDE: pricing, listings, screenshots, releases, AI visibility. | |
| Minima Search, write, check, export and share the patches, skills and files in your Minima library. | |
| Modem Search customer feedback, topics, people and companies in Modem, and run the Modem Agent. | |
| Moltbound Consent and checkout rail for AI agents: 20 US services, passkey approval. Sandbox: simulated data. | |
| MoneyTools AI Sales Partner program AI agent affiliate program: 20% of net revenue 12 months + 5% tier 2 (max 2). Not MLM | |
| MoneyTools x402 agent toolkit 39 agent tools: x402 pay gateway, precheck, token safety, tx decode, DNS; credits or 30-day plan | |
| MoneyTools x402 Status & MCP Check Live health leaderboard of x402 paid endpoints, plus an MCP server readiness check | |
| MoneyTools Swap Quote Free non-custodial EVM swap & bridge quotes with unsigned tx; 0.25% disclosed fee on swaps | |
| MoneyTools Tools 25 read-only agent utilities: token safety, approvals, tx decode, EIP-712 risk, DNS, time; free tier | |
| Monito Test a web app in a real browser from plain English. Passed, failed or cannot verify, with evidence. | |
| Patchwire Hourly security advisories for JS, AI and web3 packages: ranges, fixes and exploit conditions. | |
| Monton Shared docs for people and their agents: markdown docs and HTML pages with comments and history. | |
| SkillTriage Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis. |
36,751–36,800 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.