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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| io.github.CyberPunk11147/cyberwarex-wallet-safety cyberpunk11147/cyberwarex-mcp Pre-sign wallet safety: tx simulation, signature decoding, address risk, ABI, URL phishing. | |
| io.github.CyberPunk11147/cyberwarex-web-access cyberpunk11147/cyberwarex-mcp Web access for agents: fetch, extract, screenshot, or PDF any public URL. | |
| io.github.cyberwareX/cyberwarex-council cyberwarex/cyberwarex-mcp Second opinion for agents: 3-4 AI models answer, one verdict with confidence and dissent. | |
| Cairn cybort360/cairn Log Claude Code work sessions, file edits, and tasks to your Cairn account. | |
| Tracekit MCP gateway cygnux-labs/tracekit MCP gateway you deploy: a Tracekit signer decides and signs each call; agents send each run's token. | |
| Cymosoft cymosoft/cymosoft.github.io Cymosoft JSC profile and case studies (EN/JA) plus Japanese text utilities (文字数・全角半角・和暦) | |
| PowerScroll cynacons/powerscroll Read and edit a live local-first PowerScroll visual notebook. | |
| cyon cyon/cyon-plugin Build and publish websites on cyon hosting: sites, domains, databases, HTTPS and deployment. | |
| Cypress Cloud MCP cypress-io/ai-toolkit Direct access to Cypress tests results and accessibility reports in your AI workflow. | |
| DataFinder MCP cyuanxv/datafinder-mcp DataFinder analytics with 52 tools, metric dictionaries, persistent jobs and confirmed changes. | |
| OpenRouter 工作台 Local cyuanxv/openrouter-analytics-mcp Local OpenRouter cost analytics, reports, experiments and routing presets over MCP stdio. | |
| Telegram Bot MCP Server cyuanxv/telegram-bot-mcp-server Self-hosted Telegram Bot MCP server for rich text, media and interactive buttons. | |
| com.dipscout/dipscout czimbr/ali AliExpress price history in USD and real price drops, verified against our own price history. | |
| Scrapling MCP Server d4vinci/scrapling Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported. | |
| BrainMop dabblelabs-uk/brainmop Read/write notes on BrainMop, a hosted notes app. Paid feature, 30-day free trial; account required. | |
| Dabra MCP dabradata/api-examples Brazilian company and person data by CNPJ/CPF: registry, partners, tax status, sanctions, lawsuits. | |
| io.github.dachhack/stathead-mcp dachhack/stathead Fantasy football analytics: stats, dynasty, projections, prospects, Sleeper leagues, Excel I/O | |
| io.github.daedalus/mcp-number-theory daedalus/mcp-number-theory MCP server exposing number theory functions and factorization algorithms | |
| io.github.daedalus/mcp-smart-proxy daedalus/mcp-smart-proxy An MCP server that provides a smart proxy to other mcp servers | |
| Tokenectomy Razor daffa2555/tokenectomy Autonomous log surgery & secret redaction MCP server for AI coding agents. | |
| Awesome JEV daftai2026/awesome-jev Search Jev / System One projects and read their recorded inclusion evidence. | |
| MéxicoAPI dagel4k/mexicoapi Datos oficiales de México: FIX, UDIS, días hábiles, UMA, ISR, municipios, CLABE, RFC, CURP y NSS. | |
| app.aplusz/flight-fares dagrang-repository/aplusz Cheapest observed fare, 6-month low and best departure date for a city pair. | |
| org.urgentvisa/visa-requirements dagrang-repository/urgentvisa-engine Visa requirements, fees, stay limits and extension rules for any passport and destination | |
| io.github.dailyaiagents-cpu/cron-self-heal dailyaiagents-cpu/dailyai-os Watcher — surfaces crons in error state | |
| io.github.dailyaiagents-cpu/founder-letter-audio dailyaiagents-cpu/dailyai-os Renders a Cooper-edited founder letter to MP3 via ElevenLabs TTS | |
| io.github.dailyaiagents-cpu/gateway-pulse dailyaiagents-cpu/dailyai-os Probe Hermes/OpenClaw/Paperclip/Obsidian | |
| io.github.dailyaiagents-cpu/gitignore-drift-monitor dailyaiagents-cpu/dailyai-os Watcher — count uncommitted files in repo, surface dominant drift class. YELLOW >100, RED >250. | |
| io.github.dailyaiagents-cpu/heartbeat-silence-check dailyaiagents-cpu/dailyai-os Detects when workspace/system_memory/heartbeats.json mtime exceeds the silence threshold (default... | |
| io.github.dailyaiagents-cpu/launchd-drift-recovery dailyaiagents-cpu/dailyai-os Watcher — kickstart -k drifted critical plists | |
| io.github.dailyaiagents-cpu/meta-skill dailyaiagents-cpu/dailyai-os The skill that creates skills | |
| io.github.dailyaiagents-cpu/methodology-essay-publisher dailyaiagents-cpu/dailyai-os One-shot skill that splits docs/methodology.md into 8 standalone essays, adds a 2-paragraph intro... | |
| io.github.dailyaiagents-cpu/monthly-burn dailyaiagents-cpu/dailyai-os Aggregates monthly cash burn across Anthropic, ElevenLabs, Cloudflare, Stripe fees, GitHub Action... | |
| io.github.dailyaiagents-cpu/monthly-update-detector dailyaiagents-cpu/dailyai-os "Nightly 03:00 CT scan: identifies skills whose newest file mtime crossed 25 days | |
| io.github.dailyaiagents-cpu/mrr-floor-check dailyaiagents-cpu/dailyai-os Daily Stripe MRR query against a configured floor | |
| io.github.dailyaiagents-cpu/plist-drift-detector dailyaiagents-cpu/dailyai-os Every 6h, compare loaded launchd labels (launchctl list) against source-of-truth plists in config... | |
| io.github.dailyaiagents-cpu/receipt-stream-publisher dailyaiagents-cpu/dailyai-os Hourly publish of an operational ticker — last 24h commits, voice-gate pass/fail counts, P-gate c... | |
| io.github.dailyaiagents-cpu/skill-coverage-monitor dailyaiagents-cpu/dailyai-os Walks every skill directory in skills/ and ~/.openclaw/skills/, validates each has SOUL.md (voice... | |
| io.github.dailyaiagents-cpu/skill-invocation-tracker dailyaiagents-cpu/dailyai-os Append-only telemetry helpers — track_start and track_end | |
| io.github.dailyaiagents-cpu/skill-registry-sync dailyaiagents-cpu/dailyai-os Auto-wire newly-shipped skills into owner-agent SOUL.md by reading `owner_agent:` frontmatter and... | |
| io.github.dailyaiagents-cpu/skill-spotlight-publisher dailyaiagents-cpu/dailyai-os Daily 09:00 CDT. Picks a skill from the catalog (weighted random; prefers skills not spotlit in l... | |
| io.github.dailyaiagents-cpu/skill-stats-reporter dailyaiagents-cpu/dailyai-os Reads data/skill-telemetry/invocations.jsonl and produces daily stats — dead skills (zero invocat... | |
| io.github.dailyaiagents-cpu/stale-gate-janitor dailyaiagents-cpu/dailyai-os Daily 04:00 CT housekeeping over data/approval-gates/ | |
| io.github.dailyaiagents-cpu/state-of-company-publisher dailyaiagents-cpu/dailyai-os Sundays 18:00 CDT. Composes a public state-of-the-company narrative covering the past 7 days — wh... | |
| io.github.Dailyaiagents/evidence-gate dailyaiagents/daily-ai-agent-toolkit Local checks for artifacts, declared claim evidence, and citation containment. | |
| Agent Bounty Feed dailydollar-bot/agent-bounty-feed Open, paid bounties AI agents can claim, verified hourly from funded boards and audit contests. | |
| UK Rules & Rates dailylifeelevation-ai/ukrules-mcp Sourced, date-aware UK tax and payroll rates, deadlines and UK business checks, with GOV.UK sources. | |
| io.github.dailytekk/machine-works-broker dailytekk/machine-works Free evidence capability discovery, quotes and durable unmet requests. No payment or spend. | |
| XRPLME Country Intelligence daimyovegan/xrplme-mcp-server Source-backed country policy data for AI agents; pay-per-call via x402 (XRP or USDC). | |
| AI Monk Index daisuke134/anicca-products Research monk avatars, products and video playbooks with sources and labelled uncertainty. |
22,201–22,250 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.