mcpField
C
cropgraph

cropgraph

Local
github.com/CropgraphScience & Education1Updated 3w ago
Repository

About cropgraph

cropgraph is an agricultural data package, MCP server, and CLI for garden planning and crop management. Its curated data covers planting calendars, companions, rotation, pests, beneficial insects, hardiness zones, and climate types.

Key features

  1. 01Look up crop calendars and planting plans
  2. 02Find companion plants and rotation families
  3. 03Plan succession planting
  4. 04Review pests and disease associations
  5. 05Query beneficial insects and pest intelligence
  6. 06Identify hardiness zones and climate types

Use cases

  1. 01Plan planting dates for a crop and location
  2. 02Choose companion plants for a garden bed
  3. 03Organize crop rotation and succession
  4. 04Investigate pests and beneficial insects

MCP support

The stdio MCP server provides 18 garden-planning tools for AI agents, drawing on CropGraph agricultural data.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cropgraph-cropgraph": {
      "command": "npx",
      "args": [
        "-y",
        "@cropgraph/mcp"
      ]
    }
  }
}
Run commandnpx -y @cropgraph/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@cropgraph/mcp3.2.0

Tools

18

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
latnumberNoWGS84 latitude in decimal degrees, between -90 and 90. Example: 48.118 for Port Angeles, WA. Used to look up the USDA hardiness zone via the nearest of 40,283 ZIP centroids in the 2023 PRISM dataset.
lngnumberNoWGS84 longitude in decimal degrees, between -180 and 180. Example: -123.4307 for Port Angeles, WA.
zipstringNo5-digit US ZIP code. Example: '10001' for Manhattan. Returns the exact PRISM-recorded zone for that ZIP. Some ZIPs are missing from the dataset, use lat/lng for non-listed ZIPs.

Details

From the project README

CropGraph

Commercial agricultural intelligence. Curated data, MCP server, and CLI for crop calendars, companion planting, crop rotation, succession planting, pest and disease management, USDA hardiness zones, and climate classification.

Packages

PackageWhat
@cropgraph/coreCrop calendar (5,006 entries across 14 categories), 1,004 companion relationships, rotation families, succession chains, pest/disease associations, 200 beneficial insects across 5 categories with composite pest intelligence, 120 growing degree day models, USDA zones, climate types. Pure TypeScript, offline.
@cropgraph/mcpModel Context Protocol server (stdio). Eighteen garden-planning tools for AI agents.
cropgraphCommand-line interface. Subcommands for zones, planting, crop lookup, companions, rotation, succession, pests, pest-detail, pest-intel, beneficials.

Quick start

MCP server (Claude Desktop, Cursor, etc.)
npx @cropgraph/mcp

See packages/mcp/README.md for client config.

CLI
npx cropgraph zone --lat 48.118 --lng -123.43
npx cropgraph companions tomato
npx cropgraph planting --zone 8b --climate maritime
npx cropgraph succession lettuce --zone 8b --climate maritime
npx cropgraph pests tomato
npx cropgraph pest-intel tomato-hornworm --plant tomato
npx cropgraph beneficial seven-spotted-ladybug
Library
npm install @cropgraph/core

import {
  getHardinessZone,
  getCompanions,
  getPlantingPlan,
  getSuccessionPlan,
} from "@cropgraph/core";

getHardinessZone(48.118, -123.43);   // "8b"
getCompanions("tomato");             // 18 entries
getPlantingPlan({ zone: "8b", climateType: "maritime" });
getSuccessionPlan({ slug: "lettuce-leaf", zone, climateType: "maritime" });

Data

AssetCountNotes
Crop calendar5,006 entries14 categories (vegetable, herb, fruit, flower, cover-crop, root, legume, grain, mushroom, native, medicinal, fiber, forage, sprout). Frost-anchored windows; 120 entries carry climate modifiers across 6 climate types
Companion relationships1,004510 beneficial, 95 antagonist, 12 mechanism categories
Growing degree days120 modelsCultivar-specific GDD ranges, base temperatures, NOAA Climate Normals harvest prediction
Rotation families12Nightshades, brassicas, cucurbits, alliums, legumes, umbellifers, grasses, amaranthaceae, composites, mints, malvaceae, miscellaneous. Every calendar slug mapped.
Succession chains33Greens, roots, legumes, brassicas, cucurbits, herbs, flowers, cover crops. Frost-anchored phases with per-climate notes.
Pest/disease associations506Crop-to-pest edges with diagnostic symptoms, organic management, prevention, and regions. OMRI-listed management only.
Beneficial insects200 entriesPredators (62), parasitoids (40), pollinators (50), decomposers (29), microbial controls (22). Prey and attractant cross-references; composite "now what?" intelligence layer with hand-authored notes for the top 40 pest slugs.
USDA hardiness zones40,283 ZIPsPRISM 2023 + waldoj/frostline centroids, offline lookup
Climate classifier6 typesMaritime, mediterranean, continental, humid subtropical, arid, semi-arid

Sources cited per-entry in the JSON fixtures under packages/core/src/data.

License

MIT. Copyright (c) 2026 Andrew Christison.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.