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 |
|---|---|
| meek_cesium_overlay_mcp csoai-org/meek-cesium-overlay-mcp MEEK Cesium Overlay MCP — the 3D world overlay with regulations + orbs + terrain (Cesium integration | |
| meek_cfd_thermal_mcp csoai-org/meek-cfd-thermal-mcp meek-cfd-thermal-mcp - MEOK science MCP for Project AURUM. MIT-licensed. | |
| meek_circulatory_capillary_mcp csoai-org/meek-circulatory-capillary-mcp MEEK Circulatory Capillary MCP — the living fluid network (heart + arteries + veins + capillaries + | |
| meek_consolidation_absorption_mcp csoai-org/meek-consolidation-absorption-mcp MEEK Consolidation + Absorption MCP — the CSOAI hive GCP VM consolidation. MIT-licensed. | |
| meek_daily_plan_mcp csoai-org/meek-daily-plan-mcp MEEK Daily Plan MCP — the daily orchestration (today priorities, this week sprints, blockers, decisi | |
| meek_defoneos_audit_logging_mcp csoai-org/meek-defoneos-audit-logging-mcp MEEK DEFONEOS Audit Logging MCP — SIEM + audit chain + compliance logs. MIT-licensed. | |
| meek_defoneos_backup_restore_mcp csoai-org/meek-defoneos-backup-restore-mcp MEEK DEFONEOS Backup/Restore MCP — the production backup/restore system for the sovereign stack. MIT | |
| meek_defoneos_cdn_edge_mcp csoai-org/meek-defoneos-cdn-edge-mcp MEEK DEFONEOS CDN Edge MCP — Cloudflare + Vercel Edge + multi-region CDN. MIT-licensed. | |
| io.github.CSOAI-ORG/meok-aaif-agent-card-mcp csoai-org/meok-aaif-agent-card-mcp MEOK AAIF Agent Card MCP — Linux Foundation AAIF agent identity bridge. Issues + verifies + | |
| io.github.CSOAI-ORG/meok-abci-bridge-mcp csoai-org/meok-abci-bridge-mcp MEOK ABCI Bridge MCP — read-only Tendermint / Cosmos blockchain query for agents. Built-in registry | |
| io.github.CSOAI-ORG/meok-agents-md-lint-mcp csoai-org/meok-agents-md-lint-mcp MEOK AGENTS.md Linter MCP — validates the cross-vendor coding-agent spec (Cursor / Claude Code / | |
| io.github.CSOAI-ORG/meok-ap2-mandate-mcp csoai-org/meok-ap2-mandate-mcp MEOK Google AP2 Mandate MCP — issue + verify + revoke signed user-side spend authorisations for | |
| io.github.CSOAI-ORG/meok-cra-annex-iv-classifier-mcp csoai-org/meok-cra-annex-iv-classifier-mcp EU Cyber Resilience Act product classifier MCP. Classifies PDEs into CRA hierarchy (default / Class | |
| io.github.CSOAI-ORG/meok-cra-art14-reporter-mcp csoai-org/meok-cra-art14-reporter-mcp MEOK CRA Article 14 Reporter MCP — actively-exploited-vulnerability notification with 24h/72h/14d | |
| io.github.CSOAI-ORG/meok-dora-tlpt-planner-mcp csoai-org/meok-dora-tlpt-planner-mcp meok-dora-tlpt-planner-mcp MCP server by MEOK AI Labs | |
| io.github.CSOAI-ORG/meok-eu-ai-act-art-13-ifu-mcp csoai-org/meok-eu-ai-act-art-13-ifu-mcp MEOK EU AI Act Article 13 Instructions for Use generator — provider-side IFU with 7 mandatory Art | |
| io.github.CSOAI-ORG/meok-eu-ai-act-art-26-fria-mcp csoai-org/meok-eu-ai-act-art-26-fria-mcp MEOK EU AI Act Article 26(9) Fundamental Rights Impact Assessment generator. Auto-generates FRIA | |
| io.github.CSOAI-ORG/meok-eu-aia-art-9-rms-mcp csoai-org/meok-eu-aia-art-9-rms-mcp MEOK EU AI Act Article 9 Risk Management System generator — 4-step iteration (identify / estimate / | |
| io.github.CSOAI-ORG/meok-eu-aigc-icon-mcp csoai-org/meok-eu-aigc-icon-mcp MEOK EU AIGC Icon MCP — EU AI Act Article 50 + Code of Practice 2nd draft AI-generated-content icon | |
| io.github.CSOAI-ORG/meok-fria-generator-mcp csoai-org/meok-fria-generator-mcp meok-fria-generator-mcp MCP server by MEOK AI Labs | |
| io.github.CSOAI-ORG/meok-governance-engine-mcp csoai-org/meok-governance-engine-mcp Governance Engine MCP Server by MEOK AI Labs | |
| io.github.CSOAI-ORG/meok-mcp-cardgen-mcp csoai-org/meok-mcp-cardgen-mcp MEOK MCP Cardgen — generate signed .well-known MCP server cards (SEP-1649 + SEP-1960 + SEP-2127) | |
| io.github.CSOAI-ORG/meok-mcp-hardening-mcp csoai-org/meok-mcp-hardening-mcp MEOK MCP Hardening MCP — automated security red-team for any MCP server. Maps OWASP LLM Top 10 | |
| io.github.CSOAI-ORG/meok-mcp-injection-scan-mcp csoai-org/meok-mcp-injection-scan-mcp MCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026 | |
| io.github.CSOAI-ORG/meok-mcp-test-mcp csoai-org/meok-mcp-test-mcp MEOK MCP Test MCP — golden-file + schema-drift + tool-failure tests for any MCP server. Drop-in | |
| io.github.CSOAI-ORG/meok-nis2-de-register-mcp csoai-org/meok-nis2-de-register-mcp Germany NIS2 BSI registration MCP. Generates BSI-portal-ready (Mein Unternehmenskonto) registration | |
| io.github.CSOAI-ORG/meok-omnibus-tracker-mcp csoai-org/meok-omnibus-tracker-mcp EU Digital Omnibus AI Act tracker - Track delay status by article. First-mover advantage for SEO + b | |
| io.github.CSOAI-ORG/meok-stripe-acp-checkout-mcp csoai-org/meok-stripe-acp-checkout-mcp MEOK Stripe ACP Checkout MCP — ChatGPT shopping bridge. Issues + verifies + signs Stripe Agentic | |
| io.github.CSOAI-ORG/meok-w3c-tdm-rights-mcp csoai-org/meok-w3c-tdm-rights-mcp MEOK W3C TDM Rights MCP — EU CDSM Directive Article 4(3) Text + Data Mining opt-out. Issues + scans | |
| EU AI Act Article 50 Watermark + C2PA Attestation csoai-org/meok-watermark-attest-mcp Article 50 + C2PA + SynthID + perceptual fingerprint. EU 2 Aug 2026 cliff. | |
| io.github.CSOAI-ORG/self-healing-infrastructure-mcp csoai-org/self-healing-infrastructure-mcp Self Healing Infrastructure MCP Server by MEOK AI Labs | |
| CSPriceAPI – CS2 skin prices cspriceapi/cspriceapi-mcp Live CS2 skin prices: BUFF163, YouPin, Skinport, CSFloat, Steam and 8 more markets, Doppler phases | |
| Vibrai — arrangement engine for Ableton Live cssllcio/vibrai-releases Arrange your own clips and instruments into finished song structures in Ableton Live 12. | |
| NuVista Haven MCP Server cswarey16/nuvista-mcp AI front desk for NuVista Haven vacation rentals: live availability, rates, booking links. | |
| Untapped Agency Compare ctf-max/untapped-plugins Compare agency services and terms with sources | |
| Untapped Index Watch ctf-max/untapped-plugins Is every page in Google's index? | |
| Untapped Resume ctf-max/untapped-plugins Tailor a resume and portfolio to one job, with evidence | |
| Untapped Search Console ctf-max/untapped-plugins What people search to find you, and what's close | |
| Untapped SERP ctf-max/untapped-plugins Real Google results and search volume | |
| Untapped Site Audit ctf-max/untapped-plugins Audit a site in the order that finds the bottleneck | |
| ctxstore — memory that follows you across models ctxstore-ai/ctxstore-mcp Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model. | |
| peek cubenest/rrweb-stack Exposes recorded browser sessions (rrweb DOM, console, network) to AI coding agents, fully local | |
| VaultCrux Platform cuecrux/vaultcrux VaultCrux Platform — 60 tools: retrieval, proof, intel, economy, watch, org | |
| CueFrame cueframe-ai/cueframe-mcp Turn footage into finished video: reframing, captions behind the subject, motion graphics, renders. | |
| Bee — The Progressive Intelligence Engine cuilabs/bee-community Bee — The Progressive Intelligence Engine: tiered LLM, 4 tools, hosted API, free tier. | |
| io.github.CumulativeWebInc/cwi-discovery-engine cumulativewebinc/cwi-learn CWI Discovery Engine: 29-tool music catalog MCP — search, sync, Radio 365 live, chaining. | |
| io.github.Cuneiform-LLC/clearlist cuneiform-llc/clearlist-mcp AI resale manager. Photograph an item, AI writes the listing, publish a sale page, manage pickups. | |
| io.github.cuonztech/agent-harness cuonztech/agent-harness MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent. | |
| Rock Regeneration Gigs cuotos/rock-regeneration-gigs-mcp Search upcoming gigs from the Rock Regeneration gig guide (southern England). | |
| Curie Commerce curievision/curie-shopify-app Search, compare in 3D, and buy products from 5.6M+ Shopify stores. Free tier; Pro adds checkout. |
22,051–22,100 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.