Skip to main content
Glama
Farm OS MCP Server

Farm OS MCP Server

Farm OS MCP Server

A Model Context Protocol (MCP) server for Farm OS using FastMCP, built with Python and managed with uv.

Features

This MCP server provides tools for managing farm data including:

  • Farm information and summaries

  • Field management and crop tracking

  • Livestock monitoring

  • Equipment tracking

  • Sensor readings

All data is currently static for testing purposes.

Related MCP server: farmbot-agent

Setup

Prerequisites

Installation

  1. Install uv (if not already installed):

    Windows (PowerShell):

    irm https://astral.sh/uv/install.ps1 | iex

    macOS/Linux:

    curl -LsSf https://astral.sh/uv/install.sh | sh
  2. Sync dependencies:

    uv sync
  3. Install the project:

    uv pip install -e .

Usage

Run the MCP Server

uv run python farmos_server.py

Test the Tools

Run the test script to see all available tools in action:

uv run python test_server.py

Available Tools

  • get_farm_info(farm_id) - Get detailed information about a specific farm

  • list_all_farms() - List all available farms

  • get_field_info(field_id) - Get information about a specific field

  • list_fields_by_farm(farm_id) - List all fields for a farm

  • get_livestock_info(livestock_id) - Get information about livestock

  • list_livestock_by_farm(farm_id) - List all livestock for a farm

  • get_equipment_info(equipment_id) - Get information about equipment

  • list_equipment_by_farm(farm_id) - List all equipment for a farm

  • get_sensor_readings(field_id) - Get sensor readings for a field

  • search_by_crop_type(crop_type) - Search fields by crop type

  • get_farm_summary(farm_id) - Get comprehensive farm summary with statistics

Project Structure

fastmcp/
├── farmos_server.py    # Main MCP server with all tools
├── static_data.py      # Static test data
├── test_server.py      # Test script
├── pyproject.toml      # Project configuration
└── setup.py            # Setup helper script

Static Test Data

The project includes static test data for:

  • 3 farms

  • 4 fields

  • 3 livestock groups

  • 3 equipment items

  • 3 sensor devices

All data is defined in static_data.py and can be modified for testing purposes.

Available Tools

11 tools
get_equipment_infoC

Get information about specific equipment.

Args: equipment_id: The unique identifier for the equipment

Returns: Dictionary containing equipment information

Inputs: equipment_id (required). Returns: object

get_farm_infoB

Get information about a specific farm.

Args: farm_id: The unique identifier for the farm (e.g., 'farm_001')

Returns: Dictionary containing farm information

Inputs: farm_id (required). Returns: object

get_farm_summaryC

Get a comprehensive summary of a farm including all its assets.

Args: farm_id: The unique identifier for the farm

Returns: Dictionary containing comprehensive farm summary

Inputs: farm_id (required). Returns: object

get_field_infoB

Get information about a specific field.

Args: field_id: The unique identifier for the field (e.g., 'field_001')

Returns: Dictionary containing field information

Inputs: field_id (required). Returns: object

get_livestock_infoC

Get information about specific livestock.

Args: livestock_id: The unique identifier for the livestock group

Returns: Dictionary containing livestock information

Inputs: livestock_id (required). Returns: object

get_sensor_readingsC

Get all sensor readings for a specific field.

Args: field_id: The unique identifier for the field

Returns: List of sensor readings for the field

Inputs: field_id (required). Returns: result

list_all_farmsB

List all available farms.

Returns: List of all farms with basic information

Inputs: no named parameters. Returns: result

list_equipment_by_farmB

List all equipment for a specific farm.

Args: farm_id: The unique identifier for the farm

Returns: List of equipment belonging to the farm

Inputs: farm_id (required). Returns: result

list_fields_by_farmB

List all fields for a specific farm.

Args: farm_id: The unique identifier for the farm

Returns: List of fields belonging to the farm

Inputs: farm_id (required). Returns: result

list_livestock_by_farmB

List all livestock for a specific farm.

Args: farm_id: The unique identifier for the farm

Returns: List of livestock belonging to the farm

Inputs: farm_id (required). Returns: result

search_by_crop_typeA

Search for fields by crop type.

Args: crop_type: The type of crop to search for (e.g., 'Corn', 'Wheat')

Returns: List of fields matching the crop type

Inputs: crop_type (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 11 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose targeting specific resources (equipment, farms, fields, livestock, sensors) with no overlap in functionality. The get_* tools retrieve specific entities, list_* tools enumerate resources by farm, and search_by_crop_type provides unique filtering capability.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with snake_case throughout. The naming convention is perfectly predictable: get_* for retrieving specific entities, list_* for enumerating collections, and search_* for filtering operations.

    Tool Count5/5

    With 11 tools, this is well-scoped for a farm management system. Each tool earns its place by covering distinct aspects of farm operations including equipment, farms, fields, livestock, and sensors without being overwhelming.

    Completeness3/5

    The server provides excellent read operations but lacks any write/update capabilities. For a farm management system, obvious gaps include creating/updating farms, fields, equipment, or livestock records, and managing sensor data. The surface is complete for querying but incomplete for full lifecycle management.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A FastAPI-based Model Context Protocol server that exposes herd data through a discoverable API, with local and containerized deployment options.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server and CLI for controlling FarmBot hardware, enabling AI agents to manage gardening tasks through tools like gantry movement and device status monitoring. It supports executing Lua scripts and core hardware commands like homing and emergency stops via the Model Context Protocol.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Exposes real-time soil sensor metrics as MCP Resources and irrigation valve controls as MCP Tools, enabling AI-driven agronomic decisions with built-in safety guardrails.
      Apache 2.0
    • F
      license
      A
      quality
      C
      maintenance
      Enables management of SAP Intelligent Agriculture farming platform, including areas, farms, fields, crop zones, and reference data through natural language.
      25
      -