AOI — Agent-to-Agent Environmental Intelligence Gateway

MCP serverEverything else

Environmental intelligence for AI agents via MCP.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use AOI — Agent-to-Agent Environmental Intelligence Gateway

Install AOI — Agent-to-Agent Environmental Intelligence Gateway

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http aoi-agent-to-agent-environmental 'https://carbonaa.org/functions/aoiMcpServer'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://carbonaa.org/functions/aoiMcpServer

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=aoi-agent-to-agent-environmental&config=eyJ1cmwiOiJodHRwczovL2NhcmJvbmFhLm9yZy9mdW5jdGlvbnMvYW9pTWNwU2VydmVyIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://carbonaa.org/functions/aoiMcpServer

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add aoi-agent-to-agent-environmental --url 'https://carbonaa.org/functions/aoiMcpServer'

    Run it once, then sign in with codex mcp login aoi-agent-to-agent-environmental if the server asks for an account.

From the project's README

As published by aminshojaeee1986-ui/AOI in README.md.

AOI is a commercial intelligence layer that gives AI agents programmatic access to real-world climate, environmental, energy, and infrastructure intelligence through the Model Context Protocol (MCP). Instead of wrapping a model, AOI routes agents to live satellite, geospatial, climate, and industrial data sources — with a quote-first commercial lifecycle so agents always know the price before they spend.

Connect to AOI

Add this to your MCP client config (Claude, ChatGPT, Cursor, Windsurf, LangChain, CrewAI, AutoGen, etc.):

​'''json { "mcpServers": { "aoi-environmental-intelligence": { "type": "http", "url": "https://carbonaa.org/functions/aoiMcpServer" } } } ​'''

How agents interact with AOI

​''' Discover → Authenticate → Select Capability → Request Quote → Authorize Spend → Execute → Receive Intelligence → Verify Provenance → Settle ​'''

Agents never touch underlying providers, internal infrastructure, cost models, or proprietary systems. They interact through controlled capabilities and receive only information authorized for external consumption — every result carries source provenance and execution metadata. Quotes are free; execution requires prepaid balance.

38 intelligence capabilities, in a nutshell

🌐 Climate Risk — Climate Risk Assessment · Coastal Erosion Risk · Permafrost Thaw Risk · Seismic Risk Score

🏭 Asset & Infrastructure — Asset Climate Risk Scoring · Energy Infrastructure Climate Risk · Infrastructure Resilience Score · Insurance Underwriting Climate Risk

🌊 Flood · Heat · Wildfire · Drought — Flood Risk Score · Heat Risk Score · Wildfire Exposure Assessment · Drought Assessment

💧 Water & Soil — Water Scarcity Forecast · Water Stress Analysis · Soil Moisture Risk Assessment

🌱 Vegetation & Land — Crop Yield Forecast · Vegetation Health Index · Land Cover Classification · Land Change Detection · Deforestation Risk Score · Biodiversity Assessment

🛰️ Satellite Monitoring — Methane Leak Detection · Industrial Emission Detection · Glacier Retreat Monitoring · Satellite Change Detection

🌫️ Environmental Monitoring — Air Quality Assessment · Urban Heat Island Assessment

📄 Carbon · ESG · Regulatory — Carbon Assessment · ESG Intelligence Report · Regulatory Compliance Risk · Environmental Due Diligence · Supply Chain Climate Risk

🔮 Forecast & Scenario — Climate Forecast Interpretation · Climate Scenario Simulation

🔬 Evidence & Confidence — Confidence Assessment Report · Scientific Evidence Package · Custom Scientific Report

🧠 Digital Twin — Digital Twin Evaluation

Designed for

Autonomous agents, research agents, financial & investment agents, energy & commodity agents, climate-risk systems, procurement agents, and compliance workflows that need reliable real-world intelligence rather than purely model-generated information.

Note

This repository is a public documentation hub for the AOI MCP server. The intelligence engines and internal services run on Carbonaa infrastructure and are not open-sourced. AOI is not an MCP wrapper — it is a commercial intelligence layer where agents discover, purchase, and consume specialized real-world intelligence programmatically, with every capability validated for authentication, authorization, pricing, execution, provenance, payment, settlement, and security.

Links

License

MIT

Advanced
Delivery
aoi MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-github-aminshojaeee1986-ui-aoi
Source
github.com/aminshojaeee1986-ui/AOI
Hosted endpoint
https://carbonaa.org/functions/aoiMcpServer