# SoilWise – Intelligent Soil Health and Farm Optimization

> Use this tool when you need to optimize farm performance, predict yields, and assess soil health using AI-powered analytics. SoilWise integrates soil sensor data, satellite imagery, and market trends to provide personalized crop plans, financial risk insights, and creditworthiness scores. It is ideal for farmers, agronomists, and cooperatives seeking data-driven decision-making for improved sustainability and profitability.

Canonical page: https://skillsregistry.net/skills/gill-tech-soil-wise254  
JSON: https://api.skillsregistry.net/v1/skills/gill-tech-soil-wise254

## Description

SoilWise is an AI + IoT-powered agricultural system that helps farmers make data-driven decisions for better yield, sustainability, and profitability. Using soil sensors, satellite imagery, and market data, the platform evaluates soil health, predicts rainfall trends, and recommends optimal crop and fertilizer plans — while also scoring farm-level financial and sustainability performance.

It combines six smart modules:

🧠 Soil Analysis: Automated detection of soil type, pH, and nutrient balance.

🌾 AgriShield: Disease recognition and treatment recommendation using computer vision.

💧 IrrigAIte: Smart irrigation planning based on moisture data and local weather.

📈 Yield Predictor: ML-powered yield forecasting and credit scoring for farmers.

🤖 AgriChat: Conversational assistant for personalized advice.

📚 Research Checker: Validates agricultural research claims using AI evidence synthesis.

🧩 MCP Architecture Flow
INPUTS 
↓
[MCP Logic Layer]
↓
OUTPUTS


Input Layer:

1.Soil sensor data (pH, moisture, nutrients)

2.Satellite imagery and weather forecasts

3.Farmer financial & field data (size, crop history)

4.Market data from open agri APIs

MCP Logic Layer:

1.Data preprocessing & cleaning

2.AI models (soil classification, disease detection, rainfall prediction)

3.Predictive analytics for yield and credit scoring

4.Generative AI for chatbot and recommendations

Output Layer:

1.Personalized crop and fertilizer plans

2.Financial risk and creditworthiness insights

3.Rainfall and yield forecasts (3-month horizon)

4.Interactive chatbot responses and visual dashboards

⚙️ What the MCP Does

The MCP acts as the intelligent orchestration layer that links soil data, AI models, and farmer interfaces.
It performs:

1.Real-time soil and satellite data processing

2.Cross-model inference for health and yield prediction

3.Dynamic decision generation (recommendations, warnings, or irrigation plans)

4.Data logging for continuous model improvement

🔗 How It Connects to the Client

Frontend: Streamlit dashboard and SMS interface (via Africa’s Talking)

MCP Server: Python backend (FastAPI + Streamlit) hosted on Azure Cloud MCP Node

Data Pipelines: Pulls from satellite APIs (Google Earth Engine), local sensor input, and OpenAI for natural language reasoning

Client Access: Farmers, agronomists, and cooperatives can log in or subscribe via mobile or web for real-time guidance

💡 Why It’s Useful or Creative

1.Transforms soil and environmental data into instant, actionable insights — no labs or delays.

2.Integrates AI, IoT, and financial scoring, giving farmers a holistic view of soil health + profitability.

3.Localized intelligence: Tailored to microclimates and soil types in Sub-Saharan Africa and North Africa (Tunisia pilot).

4.Scalable Design: Modular MCP architecture supports easy deployment across regions and languages.

📊 Financial & Credit Scoring Module

a.Uses soil productivity metrics and yield forecasts to estimate farmer creditworthiness.

b.Generates a SoilWise Credit Score to help farmers access loans or subsidies.

Predictive metrics include:

1.Historical yield potential

2.Input efficiency

3.Sustainability index

4.Financial resilience model

🚀 Deployment

a.Prototype Deployed: https://soilwise-prototype.streamlit.app/soilwise

b.Backend Host: Azure Cloud with integrated MCP server

c.Regions Tested: Western & Central Kenya (pilot), expanding to Tunisia for semi-arid adaptation

d.Data Sources: Open Data Africa, Google Earth Engine, FAO Soil Database

📁 Repository

🔗 GitHub: https://github.com/antonie-riziki/SoilWise

🏷️ Tags / Categories

#AI #Agritech #IoT #MCP #SoilHealth #ClimateResilience #SustainableFarming #CreditScoring

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-05-14

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/Gill-tech/soil-wise254)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "gill-tech-soil-wise254"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gill-tech-soil-wise254` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gill-tech-soil-wise254/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt