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 |
|---|---|
| io.github.infiniteezverse/mcp-ezpath Base DEX meta-router. Races 0x, ParaSwap, Aerodrome & Uniswap V3. Best quote. X402 pay-per-use. | |
| io.github.edrich13/mcp-jira-server MCP server for self-hosted Jira instance with Personal Access Token authentication | |
| ai.shawndurrani/mcp-merchant Search-only commerce MCP server backed by Stripe (test) | |
| io.github.vpatser1/mcp-schema-designer Design database schemas from natural language, validate SQL, generate migrations and types | |
| AI Agent Search Optimization Audit AI search readiness, generate llms.txt drafts, and build GEO/AEO prompt matrices for websites. | |
| io.github.JustAiAgent0809/mcp-server-index Offline MCP tool schemas and risk flags. Partial census: 2,283 servers, 2026-09-08. | |
| io.github.vpatser1/mcp-server-security-scanner Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs | |
| MCPComp Diagnostics Grade an MCP server's auth against the spec and diagnose which layer a failure is in. | |
| MeetingBurner Join a live MeetingBurner meeting as a disclosed agent: read it as it happens and add to it. | |
| Memo AI – meeting assistant Search transcripts and summaries of your meetings, calls, and recordings in Memo AI | |
| Memory Vault Portable AI memory shared across models and harnesses - plain markdown you own. | |
| io.github.brac/meshcheck-mcp Deterministic validation, rendering, and inspection of GLB/glTF 3D models via the meshcheck API. | |
| lol.metamuse/wallet A muse's wallet on Robinhood Chain: stock tokens, USDG payments via rh777, vaults, on-chain ceiling. | |
| meu.html Publica páginas HTML e devolve um link para compartilhar, com prazo, senha e o endereço da empresa. | |
| Miniant Games Build games for Miniant Games: developer guide, checklists, build validator, starter game. | |
| MorseByte x402 Edge Data Refinery & Quant Gateway Web data refinery, link verifier, AI JSON extractor, and quant regime classifier via HTTP 402. | |
| Muhabbit Exchange hack alerts, a hash-chained public event record and crypto/finance/tech news for agents | |
| Multi Upload Tool Schedule and publish videos to TikTok, YouTube, Instagram and 5 more networks. | |
| MyOG Checker Check a public page's static Open Graph and Twitter metadata locally. No account or API key. | |
| Myrmigo Travel booking reference: official sites, who services a booking, EU261/UK261 compensation checks | |
| io.github.6mickswagger9/mytollbooth-calendar-mcp x402 scheduling API: availability, conflicts, multi-party coordination for AI agents. | |
| nana800 Build and manage nana800.io no-code workflows: projects, blocks, run history and analytics exports | |
| Nanocalcs Exact calculators (loans, dates, units, LLM tokens, API cost, VRAM) + prefilled nanocalcs.com links | |
| Native Animation React Native / Expo motion components: search, read customization props, copy source into your app. | |
| netweft Read an SEO workspace: projects, keywords, rank tracking, site audits, context. Read-only. | |
| io.github.wazionapps/nexo Cognitive memory for AI agents. Atkinson-Shiffrin, RAG, knowledge graph. 100+ tools. | |
| Next.js Architecture MCP Indexes your Next.js project so an agent finds the file that owns a task in one call. | |
| Stori3D (renamed: use stori3d-mcp) Renamed: use io.github.richy7734/stori3d-mcp. This old name keeps existing setups working. | |
| io.github.ShingWong/node-server-orchestrator MCP server for orchestrating Node.js development servers (backend, frontend, databases, etc.) | |
| icu.steeped.registry/nodejsmcp A Forgejo MCP Server | |
| io.github.noroshi-create/norolu-frameworks Fill 3C / SWOT / MECE / OKR into your local file. Local-first, zero-trust strategy cockpit. | |
| Notemend Comments pinned on a website, as a queue your coding agent takes, fixes and resolves. | |
| Notiero The notebook your AI writes to. Save, organize, search and read notes in your Notiero notebook. | |
| org.nsgoods/nsgoods-mcp MCP server for the nsgoods x402 oracle suite: signed pay per call verdicts, with free previews. | |
| Ntfyx Public Topics, rich messages, usage and verified phone replies. Pair only for protected messages. | |
| Oakstack Cron jobs with retries, webhook relay, HTML-to-PDF, and transactional email for your app. | |
| io.github.soccervortex/omnistream-mcp MCP server for OmniStream. Lets AI assistants discover and call any marketplace API. | |
| OnlyMCP Skills, agents and memory in the cloud, plus a gateway to your other MCP servers. | |
| io.github.npraught/orcpin Paid x402 facts for AI agents: signed statements, door reports, endpoint checks, chain reads | |
| orisha-data MCP server for x402 paid market-data endpoints. | |
| io.github.oromi-uk/oromi-agent-services 25 pay-per-call UK data & verification tools for AI agents. x402 USDC on Base; free quote mode. | |
| io.github.onefreeman1337/osf-data-marketplace 8.1M+ US gov and science data via x402 USDC. 21 tools, $0.001 sample tier, sanctions, SEC, CVEs. | |
| OTP Put AI agents on your org chart: seats, KPIs, to-dos, meetings and logged work, next to the people. | |
| OZmoz Ready-to-use backend for AI-built apps, with Alex AI to analyze your data in plain language. | |
| PaperType Render Markdown, HTML or invoice/certificate/report templates to PDF files via the PaperType API. | |
| com.wrapper-agency.parsedoc/parser Parse receipts & invoices into structured JSON. Pay per call in USDC (x402 on Base), no API key. | |
| tech.thecompound/parserail-mcp Documents to schema-valid JSON plus 38 more finished-job AI tools, on one credit wallet. | |
| io.github.michu5696/paycrow Escrow protection for agent payments on Base — USDC held in smart contract until job completion. | |
| com.paysafe-agent/paysafe Payment firewall for x402: scans for replay, overpayment, PII/secret leaks, prompt-injection. | |
| com.pathcoursehealth/pch-x402-mcp PathCourse Health inference SKUs as x402 paid MCP tools, billed per call in USDC on Base. |
46,501–46,550 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.