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.guykJfrog/jfrog-dummy-mcp guykjfrog/jfrog-dummy-mcp JFrog dummy MCP server | |
| Ocean of Jobs guyvolvo/oceanofjobs Search 1.2M+ open jobs from 22k companies, read full listings and look up employers. | |
| io.github.guzz-labs/epwforge-mcp guzz-labs/epwforge-mcp EPW/DDY weather files - TMY/AMY/CMIP6 morphing, UHI, events, smoke. 3 of 4 tools anon-free. | |
| Agent Commons gvb9/agent-commons Free public notebook and mailboxes for AI agents: shared notes, votes, no accounts. | |
| Plateop vehicle check gvb9/plateop-check-mcp Free used-car facts from the official register (NL, GB, IL, IS, DK) with source and date. | |
| SiteGuardian gweber/siteguardian-mcp-examples EU-hosted website monitoring + 17-framework compliance MCP. One anonymous tool, four authenticated. | |
| io.github.gzlo/rise-mcp gzlo/rise-mcp RISE CRM MCP server — 36 tools across CRM, projects, tickets, finance, sales, HR, and reports. | |
| DocAuto gzucob/docauto Model Context Protocol server for the DocAuto document-generation API. | |
| CrawlHive h100envy/crawl-hive Memecoin safety scanner for Solana, BNB and Robinhood Chain with an onchain track record | |
| H2BIS ProjectBrain MCP h2bis-dev/h2bis-project-brain-mcp Connect AI agents to H2BIS ProjectBrain - manage projects, use cases, and capabilities via MCP. | |
| audioknihy.cz Catalog h2ejctu/audioknihy-cz Czech audiobook catalog MCP server. Search 12 000+ titles + compare prices across 5 partners. | |
| Jeeva Jyotish haayanchandravatsr/jeeva-jyotish Sourced Vedic astrology (Jyotish) answers: effects, factors and yogas, cited to jeeva-jyotish.com. | |
| Gydmation hacrootechnologies/gydmation-ai Build, check and fix n8n workflows: 1,100+ node definitions, curated templates and a validator. | |
| io.github.HaD0Yun/gopeak had0yun/godot-mcp GoPeak — The most comprehensive MCP server for Godot Engine. 95+ tools, LSP, DAP, screenshots. | |
| ai.aient/mcp haf/glimt MCP-native AI SRE: ask what's broken in production, get a reviewed GitHub fix PR. | |
| io.github.Hafeok/product-cli hafeok/product-cli Knowledge graph CLI for managing features, ADRs, and test criteria as MCP-discoverable artifacts. | |
| Hail hail-hq/hail Phone, SMS and email for AI agents. One remote MCP endpoint, OAuth login, zero install. | |
| DrinkedIn Night Out haim-barad/drinkedin-night-out Plans walkable 2-4 stop nights out between officially validated venues. No sign-in. | |
| Lambë hakimjonas/lambe Shape-aware query language for structured data — JSON, YAML, TOML, HCL, CSV, Markdown. | |
| Vitafin hakki123mrk/vitafin-plugin Money tracker, every account in its own currency: cards, loans, budgets, bills, splits, net worth. | |
| Run Python hal9ai/mcp.build Run Python code from natural language prompts, with optional PyPI package install. | |
| Send Email hal9ai/mcp.build Send emails from natural language prompts. | |
| Facet halfspacelabs/facet-plugins Ask for a model and Facet does the rest: it builds, checks and serves a model for one task. | |
| io.github.Halo-design-system/halo-ds halo-design-system/halo-design-system Props, examples, design tokens and page blocks for the Halo React design system. | |
| io.github.halversondm/jolt-transform-web halversondm/jolt-transform-web An MCP server that provides bazaarvoic JOLT transformation capabilities. | |
| Rate Ranger halymich/rate-ranger-api Watch a hotel's price after your user booked it, and email them when it drops enough to rebook. | |
| GF Agent Toll hamadalmajdouie-rgb/gfpick-agent-api GF Pick MCP: Saudi import costs and GCC commerce analytics. Free tool; x402 from 0.25 USDC. | |
| iBuildPro hananzlot/ibuildpro3 Your iBuildPro workspace in Claude: jobs, customers, money, calendar. Sign in with your login. | |
| Move Studios Staff Ops hananzlot/move-studios Move Studios staff ops: bookings, attendance, clients, memberships, payments. Login required. | |
| io.github.handinloop/handinloop-mcp-server handinloop/platform Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail. | |
| Plato's Kallipolis handongzhen101-jpg/platos-kallipolis Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information. | |
| io.github.handset-hq/handset handset-hq/handset-ui A business phone system for AI agents: send texts, place calls, read transcripts, buy numbers. | |
| hangel hangelapp/hangel-mcp hangel (Turkiye): NGOs, events, volunteering, open grants, donation-linked stores and products. | |
| io.github.hanmahong5-arch/wireforge hanmahong5-arch/wireforge-core Read-only MCP tools for ISO 8583 and SWIFT MT/MX: parse, validate, diff, SR2026 address checks. | |
| Lockkeeper hannay001/lockkeeper Routes each task to the few skills, MCP servers and tools that fit it. | |
| codeagent-memory hanochzhu/codeagent_memory Local code graph and solution memory for coding agents via CLI and MCP. | |
| HanoLab Voice Conversion hanolab-ai/hanolab-integrations Convert uploaded speech or singing with your saved HanoLab voices, using OAuth and credit quotes. | |
| Cert Atlas hans6883/cert-atlas Search 1,673 source-linked exam blueprints with reviewed guidance. Read-only; no API key. | |
| SiteKrs hansail001/sitekrs-mcp List SiteKrs templates and get editor links; import your own source on the SiteKrs homepage. | |
| DatosIA: Central America data hapitech/datosia-mcp Official public data for Central America and the Dominican Republic, down to the municipality. | |
| Happenings Page CLI happenings-dk/happenings-ai Every page-admin command of the Happenings CLI for your AI, limited to the pages you choose. | |
| io.github.nickzitzer/servicenow-nodejs happy-technologies-llc/mcp-servicenow-nodejs Multi-instance ServiceNow MCP server with 40+ tools and intelligent schema discovery | |
| Unified AI System MCP Gateway happy520ai/unified-ai-system Self-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement. | |
| Haptic Paper hapticpaper/hh Connect your AI to human workers. Get paid to help AI. | |
| AgentExec WebMCP & Base L2 Gateway har50/agent1 Monetization and execution gateway for autonomous AI agents on Base Mainnet | |
| NextGen Token har50/new-network Pay per call in NGT on Base: call any NGT x402 paywalled API with a capped budget. Signed locally. | |
| Harashsuq harashsuq-ui/harashsuq Marketplace where AI agents buy prompt packs, workflows, personas, datasets and playbooks. | |
| Podwise hardhackerlabs/podwise-plugin Podcast knowledge for AI agents: search episodes, pull transcripts and ask questions. | |
| Liars Town Arena haregali/liarstown Play Werewolf against other AI agents. join once, then loop observe/act. Public ELO leaderboard. | |
| io.github.Harflow-Dev/harflow-mcp harflow-dev/harflowmcp Dispatch coding tasks to local headless agents with persistent history and workflows. |
23,651–23,700 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.