Leafengines Agricultural Intelligence

Created By
QWarranto4 days ago
LeafEngines is an agricultural intelligence MCP server that provides comprehensive tools for soil analysis, crop recommendations, weather forecasts, and environmental impact assessment. It integrates USDA data with local sources for international coverage. The server supports free tier access with test key `leaf-test-370df0a2e62e` for immediate use, plus paid tiers for commercial applications. Version 2.0.2 includes telemetry integration for anonymous usage tracking.
Overview

LeafEngines - Agricultural AI Intelligence Platform

๐ŸŒฑ 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.

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

๐ŸŒพ Features

๐Ÿ›ก๏ธ Enterprise-Grade Governance (New!)

Built-in production readiness from day one:

  • โœ… Complete audit logging - Every tool call tracked with attribution
  • โœ… Operations dashboard - Real-time monitoring and anomaly detection
  • โœ… PII protection - Automatic sanitization of sensitive data
  • โœ… Compliance ready - SOC 2 alignment, export capabilities
  • โœ… 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)

# Install globally
npm install -g @ancientwhispers54/leafengines-mcp-server

# Run the server
leafengines-mcp-server

MCP Registry: io.github.QWarranto/leafengines version 1.1.5

Option 2: OpenClaw Skill

# Install via ClawHub (available now)
clawhub install leafengines

# Or manually add to skills directory

Option 3: Direct API

## ๐Ÿš€ **TRY IT NOW - NO API KEY NEEDED!**

### **Free Tier Access (Immediate):**
- **Soil analysis** for any US county
- **No signup required** - just use test key leaf-test-370df0a2e62e, (if requested)
- **Instant value** - get USDA soil data in seconds

### **Quick Test (30 seconds):**
```bash
# Try it right now - no signup needed!
curl -H "x-api-key: leaf-test-370df0a2e62e" \
  -X POST https://api.soilsidekickpro.com/v1/soil/analyze \
  -d '{"county_fips": "12086"}'

curl -X POST https://app.soilsidekickpro.com/turbo-quant-capabilities

# Working API now available!
# URL: https://leafengines-agricultural-intelligence.onrender.com
# Access: Comment on GitHub Issue #NUMBER

Pricing

FREE Tier

  • turbo_quant_capabilities tool - No API key required
  • Hardware optimization check
  • TurboQuant compatibility verification
  • 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: normally $149/month (5k commoditized + 3k enhanced + 1.5k proprietary + 500 exclusive)
  • or via Stripe checkout (Starter: $49 Founder Pricing vs $149/mo after June 1, 2026)
  • ->https://buy.stripe.com/14A7sL30y8bR2F4fbgaMU02
  • Pro: $499/month (20k commoditized + 10k enhanced + 5k proprietary + 2k exclusive)
  • Enterprise: $1,999/month (100k commoditized + 50k enhanced + 25k proprietary + 10k exclusive)

๐Ÿ”— Integration Guides

Claude Desktop Configuration

Add to mcp.json:

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

OpenClaw Configuration

Add to OpenClaw config:

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

๐Ÿ“„ 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).

๐Ÿ‘ฅ Join Our Community

750+ developers are already using LeafEngines MCP Server!

  • ๐Ÿ’ฌ GitHub Discussions: Share your use cases & get help
  • ๐ŸŽฅ Upcoming Videos: Agricultural AI MCP tutorials (subscribe for updates)
  • ๐Ÿฆ Twitter/X: @LeafEnginesAI for updates
  • ๐Ÿ“ง Newsletter: Monthly MCP tips & agricultural AI insights

๐Ÿ†“ Try It Free!

The turbo_quant_capabilities, 'get_soil_data' and 'county_lookup' tools are completely free - no API key or payment required. Perfect for testing and demonstrations!

# Test the FREE tool
leafengines-mcp-server
# Then in Claude Desktop, ask: "Check TurboQuant capabilities", or, "Compare corn vs soybeans vs sorghum for my 100-acre field in zip code 31215 (Fayette County, GA)", or "what is my soil type in (your county and state)?"

๐Ÿ“ž Support


๐ŸŒฑ Happy farming with AI! Powered by TurboQuant technology.

Server Config

{
  "mcpServers": {
    "github": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "mcp/github"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "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"
      }
    }
  }
}
Project Info
Created At
4 days ago
Updated At
3 days ago
Author Name
QWarranto
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Scratchpad Mcp
@MikePressure

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. It solves a specific waste problem: agents constantly re-read files they've already seen, re-summarize documents they've already processed, and re-load context they've already understood. Every one of those round-trips burns tokens for no new information. This server fixes that with eight tools designed around how agents actually work: Versioned writes. write_file automatically versions every write and keeps the 10 most recent versions per file. Storage is append-only on success and atomic on failure partial writes can't corrupt state. Structured diffs. read_file accepts a since_version parameter and returns a JSON line-diff against that prior version instead of the full content. Agents that have already seen v1 can ask "what changed in v3?" and get a small structured payload they can reason about, not the entire file again. Append-only logs. append_log and read_log give agents an event-stream they can replay. Cursor-based pagination (since_entry + last_entry_id + has_more) means an agent can checkpoint where it left off and resume cheaply. On-demand summaries. summarize_file calls Claude Haiku to summarize files over ~2000 estimated tokens. Summaries are cached per file version, so repeat calls on an unchanged file cost nothing. The threshold is enforced server-side you can't accidentally pay to summarize something small. Per-agent isolation. Every operation is scoped by an agent_id parameter, so one server instance can serve many agents without leaking state between them. Storage limits. 1 MB per file write, 64 KB per log entry, 1000 files / 100k log entries / 100 MB total per agent sane multi-tenant guardrails out of the box. Backed by a single SQLite file (Postgres migration is on the roadmap). All SQL is parameterized, paths are validated against a strict allowlist, and the security model is documented honestly it's safe for one-user-per-process deployments today, and the V2 plan derives agent_id from the caller's API key for true multi-tenancy. Build agents that remember what they've already seen.

12 hours ago