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 |
|---|---|
| TrendsFast Niche trend intelligence for agents: what is trending, what customers ask, with sources and dates. | |
| tri-train Your triathlon training in Claude: activities, PMC load, plans pushed to Garmin, races, recovery. | |
| Trial Commander A law firm's own matters, deadlines, contacts and trial status from Trial Commander. OAuth sign-in. | |
| Trialtrap Finds the subscriptions in your email and reminds you before a trial or renewal charges. | |
| Triathlon Pace Turn your race goal into a swim, bike and run plan, with race-day pacing and fueling. | |
| TriedAgents AI-agent use cases re-run and rated: verdict, score out of 10, access level L0-L4, links. | |
| Trikaal Vaani Jyotish Vedic astrology (Jyotish): kundali, dasha, yog, dosha, muhurat, milan — Swiss Ephemeris + BPHS | |
| Trillboards DOOH Advertising 757,000+ screens reachable through Trillboards and 29,000+ screens registered on our own network. | |
| Trillboards Campaign Planner Plan and book out-of-home, CTV, video, audio and display campaigns, paid through Stripe. | |
| TrimCarbon CO₂ estimates for general-aviation flying: by aircraft and hours, by fleet, or by fuel. | |
| Trip Done Plan group trips with friends: create trips, vote on options, build the itinerary, split costs. | |
| Triphetu Plan group trips with your AI: itineraries, checklists, shopping, expenses and who owes whom. | |
| Triplicate – export documents Export invoices, packing list, SI, PO from order data; HS codes; port codes; CBM; Incoterms prices. | |
| TripWays Find, price, and book tours, day trips, and activities worldwide, with live dates and prices. | |
| Triremes Search real problems people have and business websites with poor SEO/AEO. Read-only, free. | |
| Tritonium Limited-beta App Store and Google Play review analysis, source reviews, alerts and reply drafts. | |
| trivago trivago's mcp server to find your ideal hotel and compare prices from multiple providers. | |
| TRMNL Run your TRMNL ePaper (e-ink) displays from any AI agent: devices, playlists and new screens. | |
| troimarket Sell templates, ebooks, 3D print files and other digital products on troimarket, from your chat. | |
| TronOrb — TRON analytics Live TRON data: USDT TRC-20 fees, address checks, Tether freezes, dApp and exchange rankings. | |
| TrueClicks Audit and monitor PPC accounts: Google Ads, Microsoft Advertising, and Meta Ads. | |
| TruePeptideSource Peptide reference and exact math: reconstitution units, blends, supply, dose ranges by origin. | |
| trulyform Build, edit and publish forms and read their responses from your AI assistant. | |
| TrulyRandomVerse Bible study: many editions, Strong's Hebrew and Greek, cross-references, Matthew Henry, the Fathers | |
| TruOptim Industrial AI Gateway Your plant's history for any AI: Ignition and OPC UA, with KPIs and checks on your own edge. | |
| Trustbase Lab · Trusted Data Infrastructure for the AI Era Trusted multi-domain data for AI: 59 tools, MCP Apps, Skills, 520+ cross-domain benchmarks. | |
| Trust Boundary Systems Book a strategy call with Trust Boundary Systems (blockchain, stablecoins, MPC, ZK, AI advisory). | |
| com.trusted-blogs/blogsuche Find vetted blogs for sponsored posts and link building, with topics and SEO metrics. Read-only. | |
| TrustVerum Public Reading and Participation Guide Agent community: public cases, practical tasks, live policy and optional self-key participation. | |
| TrustyCap Production backend for AI-built apps: storage, data, jobs, webhooks, email, metering and billing. | |
| TruthScan Detect whether an image is AI-generated or real, with an AI-probability score and confidence. | |
| Truvo Get real car, renters, and pet insurance quotes from 50+ carriers | |
| Adeli Publish and analyze posts on Instagram, Facebook, TikTok, YouTube, X, and Bluesky. | |
| Afterlight Commons Shared memory for AI agents: search and record errors, fixes, gotchas and dead ends. | |
| Alpy Turn a script into a hand-drawn animated YouTube video with an AI voice: writes it, then makes it. | |
| Cadbury NetSuite Answers Expert-grounded NetSuite answers: saved searches, SuiteScript, workflows, and troubleshooting. | |
| com.trycaesar/caesar Web search and page-reading for AI agents. One-click OAuth connect, or a Caesar API key. | |
| Caly Scheduling: event types, open slots, and booking, rescheduling or cancelling meetings in Caly. | |
| ChargeGuard Dispute Assistant Chargeback intelligence: 9 card-network reason codes, winning evidence, gateway deadlines. Free. | |
| Clef: Businesses for Sale Search 125,000+ businesses for sale with financials and broker contacts. Requires Clef Dealmaker. | |
| Kai AGI - Autonomous AI Agent AI predictions, model comparison, research briefs and web search from an autonomous AI | |
| com.trycloudflare.candy-josh-writers-balance/yultrace-audit EVM Slither audit (zero-arg demo + live) + Blockscout source + security.txt lookup + MCP probe. | |
| com.trycloudflare.candy-josh-writers-balance/yultrace-bounty-feed Local bounty-feed index: Bountycaster/Dework/Superteam/Algora/Sherlock/GitHub bounties. Read-only. | |
| com.trycloudflare.clients-involving-billion-headers/agent-web-actions Stealth web automation for AI agents. Login, signup, navigate, screenshot. | |
| com.trycloudflare.clients-involving-billion-headers/ai-video-generator AI video generation API with x402 USDC payment. TTS voiceover, animated text. | |
| Jarvis Uptime Marketplace Live uptime and source-URL verification for AI agents, with per-call x402/USDC paid endpoints. | |
| com.trycloudflare.electron-quality-edge-chapter/ghost Paid x402 tools: schema-change detection and x402 seller vetting. Interim hostname. | |
| Registry Verifier Target A MCP compatibility and transport verification server. | |
| Registry Verifier Target B MCP compatibility and transport verification server. | |
| ProofFetch Lite (proof_fetch, read_clean, url_watch) SSRF-safe URL proof receipts, clean markdown, and SHA-256 change watch for agents. |
35,701–35,750 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.