mcp-horticulture-agent
A local-first MCP server for tracking indoor horticulture metrics, enabling cold-stratification timelines, ericaceous soil pH validation, and transplant-shock recovery through a LangGraph agent with a local LLM.
README
Local Agentic Horticulture Tracker 🌿
An autonomous, local-first AI agent designed to track indoor horticulture metrics, including cold-stratification timelines, ericaceous soil pH validation, and transplant-shock recovery.
This project demonstrates the implementation of a cyclic LangGraph reasoning engine communicating with a FastMCP tool server, powered entirely by a local offline LLM.
🧠 System Architecture & Workflow
The agent operates on a continuous reasoning loop, evaluating user input to determine if external tool execution is required before generating a final response.
Workflow Breakdown:
- Receive User Input: The human query is passed to the LangGraph state machine.
- LLM Reasoning (The Brain): The local model (Qwen2.5) evaluates the context against the system prompt.
- Tool Call Execution: If the LLM determines a tool is needed (e.g., logging stratification), it pauses generation, triggers the FastMCP server, and waits for structured data.
- Context Update: The tool's output is fed back into the reasoning loop.
- Generate Final Response: Once all necessary data is gathered, the LLM synthesizes a final, human-readable response.
🛠️ Tech Stack
- Framework: LangGraph (State Machine / Agent Loop)
- Tooling Protocol: FastMCP (Model Context Protocol)
- Local LLM: Ollama (qwen2.5)
- Language: Python 3.11+
- Validation: Pydantic (Strict schema enforcement)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.