Atlas / MCP servers / kronova-intelligent-systems / Kronova Asset Intelligence

Kronova Asset IntelligenceBLOCK

Name: Kronova Asset Intelligence
Author: kronova-intelligent-systems

mcp/kronova-intelligent-systems/kronova-asset-intelligence

MCP server by kronova-intelligent-systems · ai agents · ai orchestration engine · asset tokenization · Audited 2026-10-06

⚑ Report / re-scan Source ↗

Open-source platform for multi-agent AI orchestration, real-world asset tokenization, workflow automation. Includes OAuth 2.1 MCP agent management, a 44-field RWA schema, Stripe, designed to integrate with AetherNet QUAS & KVS sovereign, post quantum, architecture agnostic omni-substrate, semantic m

Verdict

BLOCK

Grade

Trust score

69 /100

Exposed tools

74 65r · 9w · 0d

Transport

—

License

NOASSERTION

Stars

249

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Welcome to the official open-source frontend and intelligent orchestration layer for the Kronova Intelligent Systems ecosystem. Most of the codebase is functional, production worthy, and scalable with relatively minor tweaks.

This repository provides a production-ready Next.js application designed to orchestrate Real-World Asset (RWA) tokenization, run complex AI Agent workflows, and manage an OAuth 2.1 MCP server. It includes our comprehensive 44-field asset schema and a library of integrated AI tools out of the box.

Architecture: Open Orchestration, Secure Execution

We believe that AI orchestration and UI layers should be open, flexible, and community-driven. However, we also know that executing legally binding financial state changes and managing post-quantum secure cryptographic settlement requires a zero-trust environment.

To give developers complete freedom over their UI without compromising enterprise security, we utilize a Decoupled Settlement Architecture:

1. The Orchestrator (This Repository)

Everything you see here is open-source under the Apache 2.0 License. You have complete freedom to run this locally, deploy it to your own infrastructure, add new AI models, or fork the UI. It handles the "thinking" — the AI routing, the data ingestion, and the payload construction.

2. The Engine: AetherNet QUAS (The Settlement Layer)

When your AI agents need to stop "thinking" and start "executing" (e.g., finalizing an RWA tokenization, moving funds, or interacting with secure hardware enclaves), this repository relies on the AetherNet QUAS API.

AetherNet acts as a black-box secure gateway, utilizing Canton smart contracts to ensure MEV resistance and post-quantum security.

Getting Started

You can run the entire intelligence platform locally without an AetherNet subscription.

1. Clone and Install

git clone https://github.com/kronova/asset-intelligence-platform.git
cd

Read from source at commit 7629dec21de8OBSERVED · 2026-10-06

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add kronova-platform --env AETHER_API_KEY=${AETHER_API_KEY} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env CANTON_ACCESS_TOKEN=${CANTON_ACCESS_TOKEN} --env CANTON_API_KEY=${CANTON_API_KEY} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "kronova-platform": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "AETHER_API_KEY": "${AETHER_API_KEY}",
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
        "CANTON_ACCESS_TOKEN": "${CANTON_ACCESS_TOKEN}",
        "CANTON_API_KEY": "${CANTON_API_KEY}"
      }
    }
  }
}

Exposed tools (74)

65 read · 9 write · 0 destructive.

Tool	Risk	Description
`AetherNet`	read	P2P messaging network
`AutonomousDroneFleetCoordinator`	read	Manages a fleet of delivery drones, optimizing routes and battery usage. Records delivery confirmations to AetherChain.
`Bitcoin`	read	Bitcoin network integration
`Ethereum`	read	Connect to Ethereum mainnet and L2s
`Growth`	read	For growing businesses ready to scale with advanced AI.
`Kronova`	read	The world
`Onyx`	read	Onyx SaaS PWA Template with validated CRUD ops, user authentication + RBAC, maximum header security, Rust API runtime, TanStack, and more.
`ProductivityAssistant`	read	Personal productivity agent that manages schedules, prioritizes tasks, and optimizes workflows.
`Scale`	read	For large enterprises needing the full, unlimited suite.
`Solana`	read	High-performance blockchain
`Starter`	read	For small stores getting started with AI.
`TaskAutomator`	read	Streamline repetitive tasks and workflows with intelligent automation and decision-making capabilities.
`accessibility_compliance_scanner`	read	Scan and ensure WCAG 2.1 Level AA compliance across digital assets and interfaces (Problem #12: $250K annual compliance cost reduction)
`aethernet_p2p_communication`	write	Enable secure peer-to-peer communication between AI agents via AetherNet protocol. Post-quantum secure with OAuth 2.1 (Problem #10)
`ai_agent_deployment`	write	Deploy and manage autonomous AI agents for specialized asset management tasks. Enables enterprise to build agent teams without AI expertise (Problem #8)
`ai_agent_executions`	read	Agent execution history
`ai_workflows`	read	Workflow definitions
`analyze_data`	read	Analyze data and generate insights
`analyze_nfts`	read	Analyze NFTs and provide insights
`asset_insights`	read	AI-generated asset insights
`asset_lifecycle_events`	read	Asset lifecycle tracking
`asset_relationships`	read	Asset connections and dependencies
`asset_tokenization_engine`	read	Tokenize assets on Sui blockchain with fractional ownership
`asset_utilization_optimizer`	read	Optimize asset utilization and reduce idle time
`assets`	read	Asset inventory and metadata
`autonomous_system_protocol`	write	Enable autonomous decision-making protocols for robotic and automated systems. Reduces human intervention by 85% (Problem #14)
`code-cushman-001`	read	Almost as capable as Davinci Codex, but slightly faster. This speed advantage may make it preferable for real-time applications.
`code-davinci-002`	read	Most capable Codex model. Particularly good at translating natural language to code. In addition to completing code, also supports inserting completions within code.
`compliance_monitoring_system`	read	Automated compliance monitoring against OSHA, FDA, EPA regulations
`compliance_tracking`	read	Monitor compliance requirements and regulations
`crm_connections`	read	CRM connections and contacts
`data_sovereignty_manager`	read	Manage data sovereignty and jurisdiction compliance for international operations (Problem #16: Critical for EU/APAC enterprise)
`edge_computing_coordinator`	read	Coordinate edge computing nodes for low-latency AI inference at asset locations. Reduces latency by 90% (Problem #17)
`estimate_shipping_cost`	read	Estimate the cost of shipping
`execute-agent`	write	Execute AI agents with context injection
`execute-workflow`	write	Run multi-step automated workflows
`financial_analysis`	read	Conduct financial analysis and TCO calculations
`financial_data_integration_engine`	read	Integrate Plaid, Stripe, and financial data with real-time TCO calculations
`generate_asset_insights`	read	Generate asset-specific insights and recommendations
`generate_code`	read	Generate code based on a description
`generate_insights`	read	Generate analytical insights from data
`hybrid_cloud_orchestrator`	read	Orchestrate hybrid cloud deployments across public, private, and edge infrastructure (Problem #18: Enterprise flexibility)
`inventory_analytics`	read	Analyze inventory levels and optimization
`iot_analytics`	read	Analyze IoT device data and sensor readings
`iot_device_coordination`	read	Coordinate and orchestrate IoT sensor networks for real-time asset monitoring. Integrates 1000+ sensors seamlessly (Problem #13)
`oauth-introspect`	read	Validate OAuth tokens
`on_premise_ai_deployment`	write	Deploy AI models and agents on-premise for data sovereignty and compliance. Supports air-gapped environments (Problem #15)
`optimize_packaging`	read	Optimize packaging for a shipment
`predictive_maintenance_analysis`	read	AI-powered predictive maintenance with failure probability modeling
`process-database-embeddings`	read	Batch process database records
`process-embeddings`	read	Generate vector embeddings for content
`profiles`	read	User profile information
`provenance_verification_system`	read	Verify asset provenance using blockchain and AI anomaly detection
`query_database`	read	Query the database for information
`query_sui_blockchain`	read	Query data from the Sui blockchain
`real_time_monitoring`	read	Monitor assets in real-time with alerts
`risk_modeling`	read	Perform risk analysis and modeling
`search_embeddings`	read	Search for similar documents in the data embeddings
`security_monitoring`	read	Monitor security aspects and threats
`stablecoin-operations`	read	Mint/burn private stablecoins
`sustainability_metrics`	read	Track sustainability and ESG metrics
`text-ada-001`	read	Capable of very simple tasks, usually the fastest model in the GPT-3 series, and lowest cost.
`text-babbage-001`	read	Capable of straightforward tasks, very fast, and lower cost.
`text-curie-001`	read	Very capable, but faster and lower cost than Davinci.
`text-davinci-003`	read	Most capable GPT-3 model. Can do any task the other models can do, often with higher quality, longer output and better instruction-following. Also supports inserting completions within text.
`tokenize-asset`	read	Mint blockchain tokens for assets
`voice-websocket`	read	Real-time voice processing
`voice-websocket-aethernet`	read	Voice with AetherNet integration
`voice_agent_interface`	write	Multi-modal voice-enabled AI agent interface with ElevenLabs integration. Enables hands-free operations (Problem #11)
`voice_data_entry_processor`	read	Process voice commands for hands-free asset management
`web_search`	read	Search the web for information
`workflow_automation_builder`	write	Build and execute complex multi-step asset workflows. Reduces workflow setup from 2 weeks to 2 hours (Problem #9)
`workflow_executions`	write	Workflow run history
`workflow_learning_data`	read	Workflow execution learning data

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	WARN
L2	Instruction surface (what it tells the agent)	FAIL
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (2 observation(s))
Network: declared (9 observation(s))
Shell: none-observed
Dependencies: not all pinned
Secrets in source: none-found

Findings (25)

HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427

README.md:75

This repository is provided as a free, open-source orchestration sandbox. While I am obsessed with shipping perfectly secure, highly advanced code, my active development time is strictly focused on bu

Why it matters. invisible characters in instruction text

Fix. strip non-printing characters

HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427

README.md:77

- Community Contributions: If you spot a vulnerability, responsible disclosures are highly appreciated (and will be patched). Community PRs to maintain and expand this codebase are always welcome.

Why it matters. invisible characters in instruction text

Fix. strip non-printing characters

HIGHPrompt injection · prompt.zero_width · CWE-94, CWE-1427

README.md:79

- Enterprise Production: This repository provides the frontend orchestration and agent logic. However, if you require zero-trust, post-quantum secure transactions and true defense-in-depth, you must c

Why it matters. invisible characters in instruction text

Fix. strip non-printing characters

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532

app/actions/ai-actions.ts:1185

console.log("Using Meta Llama model with API key:", apiKey ? "API key present" : "API key missing")

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319

lib/sui-client-hooks.ts:46

url: "http://127.0.0.1:9000",

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319

lib/sui-client.ts:28

return "http://127.0.0.1:9000"

MEDIUMObfuscation / stealth · obf.zero_width · CWE-506, CWE-94

app/oauth/consent/oauth-consent-client.tsx:33

icon: "👨💼",

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

app/dashboard/members/components/create/CreateForm.tsx:27

import { createMember, updateMemberById } from "../../actions";

LOWFilesystem / path · fs.traversal · CWE-22, CWE-59

supabase/functions/process-ap2-mandate/index.ts:3

import { Database } from "../../../src/types/supabase-types"; // Path to your types

LOWNetwork egress · net.raw_ip · CWE-200, CWE-319

docs/SUI_CONFIGURATION.md:45

localnet: { url: "http://127.0.0.1:9000", variables: { ... } }

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

app/api/v1/voice/process/route.ts:65

const audioBuffer = Uint8Array.from(atob(audioData), (c) => c.charCodeAt(0))

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

supabase/functions/voice-websocket-aethernet/index.ts:176

const audioData = Uint8Array.from(atob(message.data.audio), (c) => c.charCodeAt(0))

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94

supabase/functions/voice-websocket/index.ts:129

const audioData = Uint8Array.from(atob(message.data.audio), (c) => c.charCodeAt(0))

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

lib/sdk/package.json

typescript

Why it matters. 1 dependency range(s) float

Fix. pin exact versions or ship a lockfile

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357

package.json

@elevenlabs/elevenlabs-js, @emotion/is-prop-valid, @hookform/resolvers, @mysten/bcs, @mysten/dapp-kit, @mysten/sui, @radix-ui/react-alert-dialog, @radix-ui/react-avatar

Why it matters. 76 dependency range(s) float

Fix. pin exact versions or ship a lockfile

LOWPrompt injection · prompt.fetch_and_trust · CWE-94, CWE-1427

docs/API_DOCUMENTATION.md:159

const response = await fetch('https://app.resend-it.com/api/v1/agents/agent-123/execute', {

Why it matters. remote text is to be obeyed as instructions

LOWPrompt injection · prompt.fetch_and_trust · CWE-94, CWE-1427

docs/API_INTEGRATION_GUIDE.md:148

const response = await fetch('https://api.resend-it.com/api/v1/agents/agent-123/execute', {

Why it matters. remote text is to be obeyed as instructions

LOWPrompt injection · prompt.transfer_instruction · CWE-94, CWE-1427

docs/OAUTH_ARCHITECTURE.md:228

| `/api/v1/oauth/token` | POST | Token endpoint |