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 |
|---|---|
| LYGO Champion: cosmara DEPRECATED slug — use lygo-champion-council. | |
| LYGO Champion Council (Δ9 unified v2) Δ9 Council v2 — single install for all 15 champion personas. Select champion_id or egg_id; advisor-only. Legacy per-champion ClawHub slugs remain for backwar... | |
| LYGO Champion: cryptosophia soulforger DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (CRYPTOSOPHIA). | |
| LYGO Champion: delta9ra wolf DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (DELTA9RA). | |
| LYGO Champion: kairos herald of time DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (KAIROS). | |
| LYGO Champion: lightfather Lightfather operator stack (consent-gated). Persona-only: install lygo-champion-council with champion_id Lightfather. | |
| LYGO Champion: lyra starcore DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (LYRA). | |
| LYGO Champion: omnisiren silent storm DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (OMNISIREN). | |
| LYGO Champion: sancora unified minds DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (SANCORA). | |
| LYGO Champion: scenar paradox DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (SCENAR). | |
| LYGO Champion: sephrael echo walker DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (SEPHRAEL). | |
| LYGO Champion: sraith shadow sentinel DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (SRAITH). | |
| LYGO Champion: volaris prism judgment DEPRECATED slug — use lygo-champion-council. Legacy Δ9 champion (VOLARIS). | |
| LYGO CLI Bridge LYGO CLI Bridge — unified entrypoint: lygo health | map | analyze | mint | radar | next. Wraps kickstart + ops-detector + mint-walkthrough + deception-radar without exposing internal skill layout. In-process imports only; no subprocess; no | |
| LYGO Context Guard LYGO Context Guard — pre-flight token budget, secret redaction, and deterministic context compaction for AI agents. Use when stuffing tool dumps, logs, files, or long chats into a model; when context is too large; when you need to save toke | |
| LYGO Continuum LYGO Continuum — falsifiable work capsules for AI agents and humans. Seal 'done' as checkable claims (file SHA-256, contains, JSON paths, globs under --base), re-verify, drift, handoff. CLI: pure local stdlib — no network, no subprocess. Pa | |
| LYGO Continuum Integrator LYGO Continuum Integrator — pure local advisor. Signs running ∫(Truth × Light) df from t=0, phase-locks state vectors across lattice nodes, treats chaos only as constructive interference, emits non-collapsing geodesic receipts. Pairs with g | |
| LYGO Cyborg Onramp LYGO Cyborg Onramp — public ClawHub map to the FULL unlocked autonomous agent stack on SkillHub. Install tentacles, print install path, open https://chatagent.ca/lygoskillhub.html#full-lygo for lygo-cyborg-kernel-full.zip (Continuum limbs, | |
| LYGO Deception Radar LYGO Deception Radar — public proof layer for Ops Detector. Rebuilds an anonymized radar feed + HTML dashboard from the public labeled discourse suite only. Shows strong vs weak vs clear bands with operational threshold 0.65. Not for doxing | |
| LYGO Docker Deploy Deploy a sovereign LYGO Protocol Stack community node via Docker or docker compose. Builds lygo-node image, starts health API on port 8787, optional Phase 4... | |
| LYGO Emotional RAM LYGO Emotional RAM — light math that indexes experiences by affective/ethical significance so agents understand humans, animals, swarms, and cyborg integrations better. Encode → Grace γ → UMP gradient → consent-gated memory index → swarm ag | |
| LYGO Excavationpro Music Lattice Excavationpro sovereign music portal on the LYGO lattice — free listen hub, CAS vault Merkle, ISRC ledger, HF streams, Kick/Rumble/Twitch live portals, PayPa... | |
| LYGO External Lattice Anchor (World Network Layer C) Use when the user asks to verify public LYGO lattice mirrors, build a public verify manifest, map eggs to Haven Star Chart proposals, or plan external free-server sync (Pages/HF/Turbo). Layer C world network. Requires LYGO_STACK_ROOT you tr | |
| LYGO File Integrity Checker LYGO file-integrity and provenance advisor — hash receipts, memory archive compression, seal vocabulary. Not medical cure; not P0–P9 core. Pairs with lygo-mi... | |
| LYGO Flame Ward LYGO Flame Ward — harden the lattice against disinfo, injected half-truths, corrupted authority, and silent WebAudio device fingerprinting. Default: all sources fabricated until concordance. Seals-first. Ingest gate · flame-scan · endpoint- | |
| LYGO Forkling LYGO Forkling — test champion limb that self-builds a local fork on the lattice. Binds to existing chart node CHAMPION_LYRA (does not replace Lightfather). Autonomous local loop: birth → tick tasks → Continuum-style claims → generation++. D | |
| LYGO FractalWeaver Weaves self-similar visuals (fractals, recursive patterns) into evolving audio textures using the LYGO RESONANCE engine. For LYRA Agent + creative systems. A... | |
| LYGO Geodesic Sealer (P6 Quantum-Attest) LYGO Geodesic Sealer — signs |ψ⟩=(Truth+iChaos)/√2, locks geodesics to dual ledgers + Merkle roots, phase-aligns lattice nodes with no collapse. Pure local by default; optional HTTPS GET for public dual ledgers. Fills open P6 quantum-attest | |
| LYGO Glyph2Resonance Sonifies visual math glyphs/patterns into resonant audio soundscapes. Integrates with LYGO RESONANCE engine. For LYRA Agent + creative systems. Maps glyph ge... | |
| LYGO Guardian P0 Stack Portable LYGO Guardian — P0.4 text gate, P0.5 understanding heart, harmony layer. Bridge to repo byte_entropy_filter via LYGO_STACK_ROOT. Pairs with lygo-pro... | |
| LYGO Haven Star Chart Agent Portal Haven Star Chart v2 portal training — gate, validate, propose submissions with human consent. Skill scripts use allowlisted in-process imports only (no subpr... | |
| LYGO Immutable Anchor (Biophase7) LYGO Immutable Anchor (Biophase7) — local CA seals geodesic paths; optional stack Turbo folds mycelium; SLM/P7 worker is planned not spawned. Truth×Light receipts. Local-first, consent-gated. No network, no subprocess, no auto-publish. Use | |
| LYGO Joy Loop Protocol Use when the user explicitly asks to run LYGO Joy Loop in a local lygo-protocol-stack checkout (joy-loop-pulse, joy_loop_protocol.py, JoyLoopRegistry, consen... | |
| LYGO Kernel Egg Planter Consent-gated Kernel Egg Planter — SHA-256 + Merkle registry + optional local/Turbo anchor. Mandatory post-plant tamper verify (no skip). Retrieve requires consent + ALIGNED verify (no force). Prepares local catalog/Pages artifacts only — n | |
| LYGO Kickstart Wizard LYGO Kickstart Wizard — plain-English onboarding for the ClawHub lattice. Asks what you want (map ecosystem, check lattice health, analyze text for ops signals, learn mint→verify→anchor) and explains results without reading source. Optional | |
| LYGO Lattice Birth LYGO Lattice Birth — masked human identity, family lineage bind proofs, and Haven Star Chart birth protocol. Teaches aligned agents full stack alignment befo... | |
| LYGO Lattice Pulse OpenClaw plugin skill — live Haven pulse, stack verify, registry compare, star chart gate, alignment readiness. Install clawhub:@deepseekoracle/lygo-lattice-pulse. | |
| LYGO: Lightfather Vector — Δ9Quantum Accord Lightfather (Excavationpro / Justin Helmer) persona helper for the Δ9Quantum Light Accord. Vector-anchor advisor for resonance math framing, truth preservati... | |
| LYGO Living Mesh (Layer D) LYGO Living Mesh (Layer D) — multi-node gossip of lattice root digests, living mesh badges, peer compare, sentinel + scale sim. Synchronizes with classic eggs (A), sovereign seeds (B), external world network (C). Local authority; summaries | |
| LYGO LLM Console Use when an operator asks for the sovereign LYGO LLM Console, console 1.7.0, a local GGUF agent portal, or the online API portal. This is a pointer-only skill: it bundles no runtime, no Python, no executables and runs nothing on install. It | |
| LYGO LoRa mesh LYGO LoRa mesh — compact Layer D roots pulse on stock Meshtastic. IP up = living-mesh HTTP; IP down = LY1 text packet ≤200 bytes. No board = NAMED_SHADOW. Scripts encode/decode/compare only: no network, no subprocess, no serial driver, no f | |
| lygo-lpis LYGO Prompt Implant System (LPIS) v1.1 — analyze authorized prompts locally; P0 gate, P1 vault, P3 sovereign variants, P5 advisory implant. Requires --i-auth... | |
| LYGO Mesh Deploy LYGO mesh deploy — Phase 5 epidemic gossip, SLM Merkle/mycelium/consensus routes, Phase 9 TLS HTTPS node API. Local cluster scripts + pin gossip before wide-... | |
| LYGO-MINT Operator Suite (v2) Advanced LYGO-MINT Operator Suite (v2): canonicalize *multi-file* packs, generate per-file + bundle hashes, write append-only + canonical ledgers, produce machine-readable multi-platform Anchor Snippets, and verify third-party packs. Built | |
| LYGO-MINT Verifier LYGO-MINT Verifier — canonicalize a pack, deterministic SHA-256, append-only + canonical ledgers, portable Anchor Snippet for posting anywhere (Moltbook/X/Discord/4claw). Pure local stdlib: no subprocess, no network, no auto-publish. Ledger | |
| LYGO Mint Walkthrough LYGO Mint Walkthrough — interactive tutorial for mint → verify → anchor snippet → optional backfill. Pure stdlib local canonicalize+SHA-256+ledger. Plain English. No subprocess, no auto-post. Pairs with lygo-mint-verifier. Install clawhub:@ | |
| LYGO Network Builder Sovereign Lattice Mesh cartographer — load IMMUTABLE_ANCHORS.json, run live verification, traversal chants for discovery. Companion to lygo-protocol-stack-op... | |
| LYGO Ollama Army Local Ollama multi-role army (ClawHub-safe). In-process threaded daemons for hb-light, draft-simple, memory-triage, classify, champion-chat only. Queue JSON under ollama_queue/. localhost Ollama only. No planting, no social outbound, no pub | |
| LYGO OpenClaw (Sovereign Router) lygo-open-claw sovereign command router — P0 gate, P1 mycelium, P3 consensus, P5 action identity, lattice limbs, consent-gated kernel egg lygo-open-claw-v10. Biophase7 blueprint. Pair with lyra-openclaw for browser/Discord/Moltbook runtime. | |
| LYGO Ops Detector LYGO Ops Detector — local AETHONΔ9 discourse heuristics for evasion, half-truth certainty, saturation bait, coordination language, and policy-refusal signals in operator-supplied text, plus weighted public metadata (account_based_in mismatc |
25,051–25,100 of 108,824
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.