> For the complete documentation index, see [llms.txt](https://docs.geopard.tech/geopard-tutorials/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.geopard.tech/geopard-tutorials/product-tour-web-app/geopard-mcp.md).

# GeoPard MCP

An intelligent two-way bridge connecting farm data with AI agents and LLM-driven agronomic reasoning.

GeoPard MCP is an AI bridge for data-driven farming. It connects GeoPard farm data with MCP-compatible assistants, enabling agronomists, farmers, and growers to work with agronomic and geospatial context in a structured way. Instead of relying on generic AI prompts, teams can use GeoPard MCP to interpret field conditions, retrieve dataset statistics, explain variability, and turn insights into practical actions such as recommendation maps and variable-rate strategies.

## Vision

GeoPard MCP is designed to work with your farm data in a controlled environment, with GeoPard’s broader policy that customer data remains theirs and is securely managed by GeoPard.

GeoPard MCP formats and streamlines farm data so AI agents and LLM-powered assistants can process it efficiently while preserving agronomic and geospatial context.

GeoPard MCP also converts AI-generated insights back into actionable outputs, including recommendation maps and variable-rate strategies.

{% @arcade/embed url="<https://app.arcade.software/share/rc1JfabDJ6Fge2X9CZSw>" flowId="rc1JfabDJ6Fge2X9CZSw" %}

## Capabilities

* Connect your GeoPard farm data to MCP-compatible AI agents and assistants.
* Preserve agronomic and geospatial context so AI can reason on field data more accurately.
* Retrieve field data and dataset statistics for analysis and recommendations.
* Turn AI-generated insights into actionable outputs, including recommendation maps and variable-rate strategies.

See [GeoPard MCP Capabilities](/geopard-tutorials/product-tour-web-app/geopard-mcp/geopard-mcp-capabilities.md) for the full capability reference.

## Who It Is For

* Agronomists who want faster, more consistent digital agronomy workflows.
* Farmers and growers who want quicker interpretation of field conditions and clearer next actions.
* Agricultural teams that want to scale expertise across more fields with AI-assisted analysis.

## Use Cases

1. Analyze soil compaction and define [Optimal Tillage Depth](/geopard-tutorials/product-tour-web-app/geopard-mcp/optimal-tillage-depth.md).
2. [Explain Vegetation Patterns](/geopard-tutorials/product-tour-web-app/geopard-mcp/explain-vegetation-patterns.md) across fields.
3. [Detect anomalies in yield datasets and trigger cleaning and calibration actions](/geopard-tutorials/product-tour-web-app/geopard-mcp/clean-and-calibrate-yield-data.md).

## Business Value

* Reduces manual interpretation of field and dataset information.
* Speeds up agronomic decision-making.
* Helps teams move from raw data to operational recommendations more consistently.

## Get Started

1. [Connect GeoPard MCP](/geopard-tutorials/product-tour-web-app/geopard-mcp/connect-geopard-mcp.md) to Claude, ChatGPT, Cursor, and other MCP clients.
2. [Ensure the GeoPard MCP connection is active](/geopard-tutorials/product-tour-web-app/geopard-mcp/verify-geopard-mcp-connection.md) before running any actions.
3. Once connected, you can run field-level workflows.

Start with connection and verification, then explore field-ready AI workflows. More GeoPard MCP workflows and integrations will be added over time.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.geopard.tech/geopard-tutorials/product-tour-web-app/geopard-mcp.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.