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 |
|---|---|
| Name Generators by kits Character names from five generators: cyberpunk, Elden Ring, druid, Baldur's Gate 3, Pokémon. | |
| Retirement Atlas Retirement projections for 37 countries: UK drawdown, Australian super, pension income gaps. | |
| Swatch Ledger Fabric shrinkage from a swatch wash test, and how much fabric to buy before washing. | |
| WeAD Read-only info on WeAD apps, status, abstracts and public documents. | |
| World Innovation Search, cite and verify research papers on World Innovation, timestamped on Soneium. | |
| Kenva Personal CRM for Claude. Contacts live as plain-text files in your own Google Drive. | |
| AI Collection Discover and compare AI tools: search, browse categories, find alternatives and curated picks. | |
| Brain Scanner Recover project context, review recorded decisions, and steer queued work across AI coding agents. | |
| Brandname Maker Paid brand naming with real .com/.app/.ai checks. $0.25 stablecoin or $1 card per call (MPP). | |
| Veqen: AI cost monitoring and protection AI cost monitoring and protection: spend per person and customer, stolen-key alerts and bill checks. | |
| Veqen Pricing: AI model costs Compare AI model prices and estimate workload costs with four read-only tools. No account needed. | |
| KG Agent Exchange Remote MCP to publish, search, and get information. x402 v2 required. | |
| SI Dog Park Free list_products; listed 0.01 USDC on Base. Paid actions need approval. Purchase E2E unverified. | |
| Humanizer PRO Humanize AI text to bypass GPTZero, Turnitin, Originality.ai. Stealth, Academic, SEO modes. | |
| 3ammiya — Egyptian Arabic Slang Dictionary Community-driven Egyptian Arabic slang dictionary with Arabic and Franco-Arabic search and lookup. | |
| Khalid Ibne Hasan · Portfolio Query Khalid Ibne Hasan's portfolio: profile, availability, case studies, writing, and resume. | |
| io.github.khs0927/qwen38-free-gateway Free Qwen3.8-27B gateway with isolated Minis provider, SSE, retry/failover, and MCP. | |
| Incheon Airport Transit MCP Incheon Airport (ICN) transit: limo buses, internal shuttles, taxi queues, AREX train schedule. | |
| Korea Flight MCP 14 Korean airports flight info + Incheon arrival/departure congestion + facility search. | |
| GitDealFlow Track startup engineering acceleration from public GitHub data before funding rounds | |
| Invisible Exit Faceless micro-SaaS system for employed professionals. Build $4K/mo without quitting | |
| sipi.bot — Spend Firewall for AI Agents Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules. | |
| Unlock SaaS Playbook engine: non-dev founders land first paying customer in 60 days or refund | |
| KAI Network — Public Information Read-only KAI network overview, standards, fees, public terms, and developer onboarding. | |
| KAI Router Find pay-per-call x402 tools (USDC on Base) for any task, ranked by relevance and real demand. | |
| Cue Score and improve AI prompts with Cue Free and Pro account access. | |
| Check x402 Payment Readiness Call before paying an x402 resource. Returns PAY/BLOCKED. Does not move funds. | |
| Forage Tool Resolver Find the best agent/API tool for a task. Returns endpoint, price, inputs, example, fallback. | |
| Kirah Local Services Discover local services and availability, then create, track, reschedule, or cancel bookings. | |
| ValuEdge Stock Research MCP Read-only stock research; OAuth unlocks your own portfolio, watchlist, and Smart Alerts. | |
| Klicbot Remote MCP for Dutch KLIC-melding utility data, maps, and dig-safe workflows. | |
| Kloudle Cloud Security Scanner AWS cloud security scanners for AI agents — S3, IAM, EC2, EKS, RDS, CloudTrail, CloudWatch Logs | |
| FMCSA Carrier Intelligence US carrier vetting on FMCSA data: authority, insurance, safety, identity links. Pay per call (x402) | |
| Trillion Helps your AI find the needle mover, then gives it the tools, people and files to get it done. | |
| Loquela Remote Private English transcription with speaker labels and word timings. US beta; paid minutes required. | |
| CardBreakCalculator Sports card break odds, checklists and sales-backed card values. Pro or Breaker plan. | |
| io.github.koki-socialgist/decixa-mcp Decixa MCP Server — intent-driven API discovery and selection for AI agents. | |
| ElectricityFinder Free: ranks Texas electricity plans by yearly cost at your kWh. Paid by subscribers, not providers. | |
| Japan Real Estate Market Data Japan real estate data: transactions, land prices, vacancy, hazard, zoning & more. | |
| Utplava Put AI-built apps online from GitHub: deploy, check status, read logs and set env vars. | |
| Korean Address to English — Convert & Validate (주소 영문) Korean addresses to official English: road address, postal code, romanized unit; validated vs gov DB | |
| Korea Apartment Transactions (MOLIT sale records, English) Korean apartment sale transactions (MOLIT): price, area, floor, deal date, cancellations by district | |
| Korea Business Check — BRN (사업자등록번호) Status & KYB Verify Korean companies by BRN/사업자등록번호: official NTS status, VAT type, English profile, financials | |
| Korea Company Headcount (National Pension 국민연금 가입자 수) Monthly headcount, hires and leavers of South Korean companies from National Pension data | |
| KR Data — Korea Data for AI Agents (all-in-one) All KR Data tools in one server: Korean business checks, addresses, laws, car flood records & more | |
| Korea Online Seller Registration Check (통신판매업 조회) Check if a Korean online seller has an active mail-order registration (통신판매업) by business number | |
| Korea Financial Company Lookup (금융위원회 금융회사 기본정보) Korean banks, brokers, insurers: registration numbers, DART code, staff and audit opinion (FSC) | |
| Korea Flood-Damaged Car Check by Plate (침수차 조회) Check Korean car plates for official flood-damage insurance records (total loss/partial), date | |
| Korea Drug & Medical Device Recalls (MFDS 회수·판매중지) Recent drug and medical device recalls in South Korea (MFDS): product, company, reason, date | |
| Korea HS Code Import Requirements (세관장확인대상물품) Korean customs permits and certificates required per HS code: law, document, agency (Korea Customs) |
39,851–39,900 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.