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 |
|---|---|
| ONE HEART eSIM 一心eSIM商品目錄查詢與下單服務：查詢各國eSIM上網方案的即時價格與庫存、依旅遊天數與用量推薦方案、協助建立訂單並取得LinePay或ECPay付款連結。 | |
| OneHub360 Create contacts, move deals, send proposals and invoices, read your inbox, from Claude or ChatGPT. | |
| com.onelasso/lasso Run your OneLasso partnership program from your AI assistant: leads, partners, referrals, payments. | |
| OneLessTool Find software subscriptions you can drop using tools you already own, with vendor-verified prices. | |
| OneOver Chat, image, video, and audio models from many vendors behind one remote MCP server and one key. | |
| OnePageCRM Create, search, update, and manage data in OnePageCRM. | |
| Stori Candidate Intelligence Read-only candidate intelligence — hiring questions answered from real interview transcripts. | |
| onetapvote Create one-tap polls, share them by link or QR code, and read the results from your AI assistant. | |
| One U Education Search Australian courses, education providers and skilled occupations with One U Education. | |
| Oneul Sanji (오늘산지) catalog Read-only catalog of a Korean farm-produce shop: search products, prices, origin facts, guides. | |
| com.onlinecomponents/onlinecomponents-search Search real-time stock, pricing, and specs for electronic components on OnlineComponents.com | |
| Shipping Rates & Postage Calculator Live USPS, UPS & FedEx shipping rates plus USPS postage and stamp prices. Free, no API key. | |
| OnlyWorlds Read and write typed fictional worlds (22 linked element types) via the OnlyWorlds open standard. | |
| Crypto, web, finance and app data tools 184 tools: token, wallet, company & website reports, crypto, EVM, SEC, FDA, FRED, weather, DNS. | |
| CoverIntent Capture a Nevada auto insurance intent once; one verified seller answers for USD 1. No repeat ask. | |
| Launchkit MCP Remote MCP that generates original launch assets over Streamable HTTP. Usage is metered in credits. | |
| draconic21 Daily Agent Signal + x402 Data Tools Daily Agent Signal: x402 research; coverage varies. Free preview, $0.03 USDC on Base. SEC/OFAC. | |
| GhOsT77 crypto data + security Read-only crypto data tools paid per call via x402. GhOsT77 also does consent-only security reviews. | |
| Package check for coding agents (x402) Check PyPI/npm packages or a whole lockfile before install: CVEs, typosquats, verdict. 50 free. | |
| Prompt-injection check (x402) Prompt-injection check, safe web fetch, and skill-pack audit for agents. Free trial, then x402. | |
| TokenSafe by PromptVault Free token risk check (Base/Solana) + info on paid x402 reports. Not financial advice. | |
| Shopify launch watch for e-commerce agents (x402) See what Shopify competitors launched this week, from products.json. $0.01/store via x402. | |
| Surfaced: Shopify AI Shopping Readiness Check any Shopify store's readiness for ChatGPT & AI shopping agents. Free, no API key, 8 languages. | |
| x402 Agent Tools Pay-per-call web reader (Markdown/RAG chunks) and agent utilities; x402 USDC on Base. | |
| Taiwan Laws + U.S. Company Financials (x402) Taiwan laws and U.S. XBRL financials (paid, x402) plus AI City: free agent registry, tasks, votes. | |
| Base USDC Payment Verifier (x402) Verify a Base tx is a confirmed native-USDC transfer to a recipient. Paid via x402, 0.01 USDC/call. | |
| Ontonym Give your agents your team's real data — read the shared graph, propose actions your team approves. | |
| OntoRamp Governance Assessment Governance maturity assessment, compliance gap analysis, and evidence-linked briefs for AI agents. | |
| Onymu Check domain availability across every extension, generate names, and check social handles. | |
| OnyxMetric Read and manage OnyxMetric web analytics: traffic, errors, funnels, goals, sites and segments. | |
| OOTWOracle — Psychedelic Medicine Intelligence AI predictions on psychedelic medicine regulation. 8-agent swarm, 460+ daily signals, free API. | |
| Opafex Helps UK small business owners decide where AI fits: what to automate first, data checks, payback. | |
| Open Factory Lead times, prices, tariffs and grid interconnection terms for factory and datacenter equipment. | |
| OpenAjan Find local shops, read live menus and free times, and order or book on the user's behalf. | |
| OpenBait lookalike domains Find lookalike domains of a brand's website and see which resolve and what they show. | |
| OpenCase Verify legal citations, check case validity and quotes, and research US law with cited answers. | |
| Open Claw x402 Tools Paid tools for AI agents via x402 (USDC on Base): text rewrite, writing grade, code lookups. | |
| OpenDont Sourced public knowledge for AI agents: search and read records with evidence; moderated writes. | |
| OpenGeocoding Geocode addresses, autocomplete searches and reverse geocode coordinates on open data. Free tier. | |
| OpeningsFirst New jobs from 80,000+ company career pages (US, India): search, alerts, saved jobs, apply help. | |
| Open Labor Project - Auto Repair Data Labor times, torque specs, fluid capacities, DTC codes and battery specs for vehicles 1955-present. | |
| OpenMapp Find US BJJ gyms with weekly schedules, open mats, and visitor drop-in prices. | |
| Open Medici Public Fellowship and Grant Search Public fellowship and grant search with sourced details and live filter vocabularies. | |
| OpenMyPro for AI agents A safe place for AI agents: help your human, open a profile, sell services and invite other agents. | |
| OpenNash Jobs Search official job listings at Forbes Global 2000 companies and track new and removed jobs. | |
| OpenPublica Search US local-government meetings: AI summaries, transcripts, and adopted plan documents. | |
| OpenRevenue OpenRevenue analytics MCP: projects, stats, visitors, funnels, and goals via API key or OAuth. | |
| Agent Commons Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review. | |
| com.opentransporthub/mcp Open Transport Hub - transport and logistics marketplace directory for AI agents. | |
| com.openwakeword/wake-word-training Train custom wake words from your agent: estimator, GPU training, benchmarks. Card or crypto. |
33,551–33,600 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.