Leafengines

io.github.QWarranto由 GitHub 帳號 QWarranto 發布v2.0.8更新於 Oct 24, 2026

🌱 Agricultural AI: Soil analysis, crop recommendations, weather forecasts. FREE TurboQuant.

已驗證STDIO僅桌面位置與生活資料與分析

概覽

AI 產生的概覽

為助理提供農業智慧工具，用於土壤分析、作物推薦、天氣預報與環境影響評估。

可以做什麼
LeafEngines 提供多項農業分析工具：USDA 土壤成分與 pH、氮磷鉀建議，EPA 水質，NOAA 氣候與天氣預報，作物推薦，病蟲害辨識，灌溉排程，產量預測，農產品市場價格，以及碳權與永續性評分。其中 turbo_quant_capabilities 是免費的硬體最佳化檢查工具。此伺服器透過 stdio 在本機執行，文件以 Claude Desktop 等 MCP 用戶端為主。
適用情境
當助理需要運用土壤、水質、氣候與作物資料回答農業、農藝或土地管理問題，或需要提出永續性與碳權估算時，適合安裝。與農業無關的一般任務則用不到。
執行需求
需要本機 Node.js 執行環境；安裝 npm 套件 @ancientwhispers54/leafengines-mcp-server，並以 stdio 方式執行。付費工具需要 LEAFENGINES_API_KEY 環境變數，免費的 turbo_quant_capabilities 工具則可不填。僅支援桌面用戶端，無法在網頁中執行。
安裝前請注意
付費工具按請求計費，另有月租方案，助理的一次呼叫可能產生費用。LEAFENGINES_API_KEY 是密鑰，透過環境變數傳入，不要寫進共用設定。分析請求會送往服務商的 API，田區或位置資訊會離開本機。README 中關於專利、認證與使用者數量的說法出自廠商，此處未經查證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Leafengines，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

LeafEngines - Agricultural AI Intelligence Platform

🌱 TurboQuant-Powered Environmental Intelligence - Soil analysis, crop recommendations, weather forecasts, and environmental impact assessment for sustainable agriculture. The only patent-protected agricultural intellgence platform in the MCP ecosystem.

[GitHub MCP Registry] [MCP Registry]

Overview

LeafEngines provides agricultural intelligence through multiple integration channels:

  • MCP Server for Claude Desktop and MCP-compatible clients
  • ClawHub Skill for OpenClaw agents
  • Claude Skill for Claude.ai users
  • Composio Integration for enterprise AI agents
  • Direct API for developers and applications

Repository Structure

leafengines-claude-mcp/├── leafengines-mcp-server/          # MCP Server (npm package)│   ├── README.md                    # Installation & usage│   ├── src/                         # TypeScript source│   └── dist/                        # Compiled JavaScript├── leafengines-clawhub-skill/       # OpenClaw skill│   ├── README.md                    # OpenClaw integration│   ├── SKILL.md                     # Skill definition│   ├── references/                  # Reference materials│   └── scripts/                     # Helper scripts├── leafengines-claude-skill/        # Claude.ai skill│   ├── README.md                    # Claude integration│   └── SKILL.md                     # Skill definition├── leafengines-agricultural-intelligence/ # Core intelligence├── leafengines-opportunity-scanner/ # Market opportunity tools├── leafengines-arbitrage-skill/     # Agricultural arbitrage└── leafengines-workspace-skill/     # Workspace management

🌾 Core Capabilities

USDA, EPA & NOAA Data Integration

  • USDA Soil Analysis - Comprehensive soil composition, pH, N/P/K recommendations from SSURGO database
  • EPA Water Quality - National water quality monitoring and contamination risk assessment
  • NOAA Climate Insights - Historical weather data, climate trends, and agricultural forecasting

Offline-First for Deep Canopy & GPS-Denied Operations

  • Works anywhere - No internet required for core functionality
  • Deep canopy compatible - Designed for remote agricultural environments with limited connectivity
  • GPS-denied ready - Military-grade positioning algorithms for contested environments
  • Offline-first architecture - Local processing without cloud dependency

Environmental Intelligence & Carbon Credit Calculations

  • Carbon Credit Calculations - Accurate emissions tracking for regulatory compliance
  • Sustainability Scoring - Environmental impact assessment and reporting
  • Environmental compatibility - Patent-pending algorithms for ecosystem analysis

🛡️ Enterprise-Grade Governance (New!)

Built-in production readiness from day one:

  • ✅ Complete audit logging - Every tool call tracked with attribution
  • ✅ Operations dashboard - Real-time monitoring and anomaly detection
  • ✅ PII protection - Automatic sanitization of sensitive data
  • ✅ Compliance ready - SOC 2 alignment, export capabilities
  • ✅ Session correlation - Trace multi-step agent reasoning

Why this matters: Most MCP servers lack governance until enterprises demand it (painful retrofit). We built it in from the start.

TurboQuant Performance

  • 6x memory reduction with Google TurboQuant optimization
  • 8x faster inference for agricultural analysis
  • Gemma 7B on 4GB devices (previously required 8GB+)
  • Cloud-equivalent performance on edge devices

Agricultural Intelligence Tools

  1. Soil Analysis - USDA soil data, satellite intelligence, environmental factors
  2. Crop Recommendations - Optimal crop selection based on soil and climate
  3. Weather Forecasts - Agricultural weather data for planning
  4. Environmental Impact - Carbon footprint, water usage, sustainability analysis
  5. TurboQuant Capabilities - FREE hardware optimization check (no API key required)
  6. Pest Detection - Identify common agricultural pests
  7. Irrigation Scheduling - Water optimization based on weather
  8. Yield Prediction - Crop yield estimates
  9. Market Prices - Agricultural commodity prices
  10. Sustainability Score - Environmental impact assessment

Quick Start

Option 1: MCP Server (Claude Desktop)

bash
# Install globally
## 🎯 QGIS Plugin Officially Approved!
**Plugin ID:** 4987 (LeafEngines Agricultural Intelligence)  **Version:** 1.0.2 Experimental  **Status:** ✅ **PUBLICLY AVAILABLE**  **Download:** https://plugins.qgis.org/plugins/qgis_leafengines/version/1.0.2/download/
### Key Features:- **USDA soil data** - Soil composition, pH, N/P/K recommendations- **EPA water quality** - Water quality metrics and analysis- **NOAA climate data** - Historical weather patterns and agricultural forecasting- **Satellite vegetation indices** - NDVI, water-stress overlays from NASA MODIS- **AI-powered crop recommendations** - Tailored to exact field polygons- **Carbon credit calculations** - Environmental impact scoring for regulatory compliance- **Offline-first architecture** - Works in remote/"deep canopy" areas- **GPS-denied capabilities** - Military-proven algorithms for contested environments
### Strategic Advantages for Partners:1. **Pre-vetted, low-risk integration** - Officially approved by QGIS after rigorous review2. **Seamless future-proofing** - Aligns with QGIS release cycles (QGIS 4.0.0+ ready)3. **Instant credibility** - Discoverable by 500,000+ QGIS users in agriculture sector4. **Regulatory advantage** - Preferred for government/EPA/USDA-related procurements5. **Ecosystem power** - Integrates with thousands of complementary QGIS plugins
### For OEM Partners:Embed LeafEngines agricultural intelligence directly into your hardware or software platforms with confidence. The official QGIS approval eliminates weeks of custom validation, security audits, and compatibility testing.
*Approved: April 14, 2026*
npm install -g @ancientwhispers54/leafengines-mcp-server
# Run the serverleafengines-mcp-server

MCP Registry: io.github.QWarranto/leafengines version 1.1.5
GitHub MCP Registry: ✅ Approved July 6, 2026 — listed at github.com/mcp

Option 2: OpenClaw Skill

bash
# Install via ClawHub (available now)clawhub install leafengines
# Or manually add to skills directory

Option 3: Direct API

bash
# Working API now available!# URL: https://leafengines-agricultural-intelligence.onrender.com# Access: Comment on GitHub Issue #NUMBER
# Test FREE toolcurl -X POST https://app.soilsidekickpro.com/turbo-quant-capabilities

Pricing

FREE Tier

  • turbo_quant_capabilities tool - No API key required
  • Hardware optimization check
  • TurboQuant compatibility verification

Paid Tiers (per 1,000 requests)

  • Commoditized: $0.001 (Basic soil/weather data)
  • Enhanced: $0.003 (Environmental impact, crop suitability)
  • Proprietary: $0.01 (Planting optimization, carbon credits)
  • EXCLUSIVE: $0.02 (Patent-pending environmental compatibility)

Monthly Plans

  • Starter: $149/month (5k commoditized + 3k enhanced + 1.5k proprietary + 500 exclusive)
  • Pro: $499/month (20k commoditized + 10k enhanced + 5k proprietary + 2k exclusive)
  • Enterprise: $1,999/month (100k commoditized + 50k enhanced + 25k proprietary + 10k exclusive)

🔗 Integration Guides

Claude Desktop Configuration

Add to mcp.json:

json
{  "mcpServers": {    "leafengines": {      "command": "leafengines-mcp-server",      "env": {        "LEAFENGINES_API_KEY": "your_api_key_here"      }    }  }}

OpenClaw Configuration

Add to OpenClaw config:

yaml
skills:  leafengines:    enabled: true    config:      api_key: YOUR_API_KEY_HERE      base_url: https://app.soilsidekickpro.com/api-docs

Composio Integration

LeafEngines is available on Composio platform as custom tools for enterprise AI agents.

Documentation

API Documentation

MCP Server

Skills & Integrations

  • ClawHub Skill: For OpenClaw agents
  • Claude Skill: For Claude.ai users
  • Composio Tools: For enterprise AI agents

Contributing

Contributions are welcome! Please see individual directory CONTRIBUTING.md files for guidelines.

Project Philosophy

This repository contains integration adapters only. All proprietary intelligence (TurboQuant, AlphaEarth embeddings, phenology models) remains in the backend API.

What to Contribute

  • Bug fixes and improvements
  • Documentation enhancements
  • Integration examples
  • Test cases

What NOT to Contribute

  • Proprietary algorithms
  • Hardcoded business logic
  • IP-sensitive code

📄 License

Integration Code

Apache 2.0 License - See individual directory LICENSE files.

API Service

Commercial terms with FREE tier available. See pricing section or https://app.soilsidekickpro.com/mcp for details.

TurboQuant Technology

Based on Google's TurboQuant research (6x memory compression for LLMs).

👥 Join Our Community

750+ developers are already using LeafEngines MCP Server!

  • 💬 GitHub Discussions: Share your use cases & get help
  • 🎥 Upcoming Videos: Agricultural AI MCP tutorials (subscribe for updates)
  • 🐦 Twitter/X: @LeafEnginesAI for updates
  • 📧 Newsletter: Monthly MCP tips & agricultural AI insights

🌐 Links

🆓 Try It Free!

The turbo_quant_capabilities tool is completely free - no API key or payment required. Perfect for testing and demonstrations!

bash
# Test the FREE toolleafengines-mcp-server# Then in Claude Desktop, ask: "Check TurboQuant capabilities"

📞 Support

🌱 Happy farming with AI! Powered by TurboQuant technology.

來源：README.md，提交 b74a26f

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包，因此其工具未知。

版本歷史

1
  1. v2.0.8最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手；SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭，或保持端點能夠回應探測，以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分