# Horizontal Well Productivity Engine AI Agent Connect

> Horizontal Well Productivity Engine is a specialized engineering MCP that brings Joshi and Economides models directly into your AI client. It handles the heavy lifting for horizontal well design, allowing your agent to calculate productivity indices, find optimal well lengths, and assess how eccentricity or placement affects reservoir performance.

## Overview
- **Category:** engineering
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_7LCwLtVgZDaJEgOo21gPlx7fE9h8RpqGb8MVgihs/ai-agent-connect
- **Tags:** reservoir, petroleum, productivity, horizontal-well, engineering-tools

## Description

You can now run complex reservoir engineering computations without leaving your chat interface. This MCP gives your AI client the mathematical tools needed to design and evaluate horizontal wells. Instead of manually running models, you can ask your agent to compare horizontal performance against vertical baselines or determine where you hit diminishing returns on well length. It handles the math for penetration effects, helping you understand how much productivity you lose when a well isn't perfectly centered or doesn't cover the full thickness of the reservoir. Whether you are checking the impact of eccentricity or looking for the most efficient length for a specific configuration, this MCP provides the specific engineering logic required for accurate well design assessments.

## Tools

### analyze_penetration_effects
This tool evaluates productivity losses caused by well eccentricity or incomplete coverage of the reservoir thickness.

### calculate_horizontal_productivity
Use this to compute the productivity index of a horizontal well and compare it directly to a vertical baseline.

### compare_well_types
This tool provides a high-level summary comparing a proposed horizontal well design against a standard vertical well.

### optimize_well_length
This tool finds the most efficient horizontal length based on your specific reservoir configuration.

## Prompt Examples

**Prompt:** 
```
Calculate the productivity index for a horizontal well with 500m length, 20 mD vertical permeability, 100 mD horizontal permeability, 15m thickness, 10 anisotropy, 1000m depth, 7.5m position, and 50 psi drawdown.
```

**Response:** 
```
The calculated productivity index is 12.45, with a vertical baseline PI of 2.10, resulting in an improvement factor of 5.93.
```

**Prompt:** 
```
What is the optimal length for a reservoir with 30 mD vertical permeability, 150 mD horizontal permeability, 20m thickness, and 5 anisotropy if I want a target PI of 15?
```

**Response:** 
```
The optimal length to achieve a target PI of 15 is 850 meters, with an estimated efficiency loss of 0.04.
```

**Prompt:** 
```
Evaluate the impact of a well positioned 2 meters from the top in a 10 meter thick reservoir with 15 mD vertical permeability and 100m length.
```

**Response:** 
```
The penetration efficiency is 0.82, resulting in a loss factor of 0.82 applied to the total productivity.
```

## Capabilities

### Productivity Index Comparison
Your agent uses this to measure how much better a horizontal well performs compared to a vertical one.

### Length Optimization
The AI calculates the specific point where increasing well length no longer provides efficient returns.

### Penetration Analysis
Your agent assesses productivity losses resulting from well placement and eccentricity.

### Design Summaries
The AI generates high-level comparisons between different well architectures.

## Use Cases

### Well Length Optimization
Determine the most efficient horizontal length for a specific reservoir to avoid unnecessary drilling costs.

### Placement Sensitivity
Check how much production you lose if the well is not perfectly centered in the reservoir thickness.

### Design Validation
Compare a proposed horizontal design against a vertical baseline to justify the project.

### Rapid Prototyping
Test different reservoir parameters like permeability and anisotropy to see how they affect the PI.

## Benefits

- Runs Joshi and Economides models through your existing AI client.
- Identifies the point of diminishing returns for well length.
- Quantifies productivity losses from poor well centering.
- Compares horizontal and vertical well performance instantly.

## How It Works

You connect the MCP to your AI client and start running engineering queries immediately.

1. Connect your AI client to the Vinkius hosted MCP.
2. Provide reservoir parameters like permeability, thickness, and anisotropy.
3. Ask your agent to perform a specific calculation or optimization.
4. Receive the calculated productivity index or optimal length directly in the chat.

## Frequently Asked Questions

**What models does this MCP use for calculations?**
The MCP uses Joshi and Economides models to perform reservoir engineering computations.

**Can I use this with any AI client?**
Yes, it works with any MCP-compatible client like Claude, Cursor, or Windsurf.

**Do I need to host the MCP myself?**
No, Vinkius hosts and manages the MCP for you, so it is ready to use once you connect.

**What kind of reservoir data do I need to provide?**
You typically need to provide parameters such as permeability (vertical and horizontal), thickness, anisotropy, depth, and well length.

**How does it handle well eccentricity?**
The analyze_penetration_effects tool specifically calculates the productivity loss caused by the well not being centered or covering the full thickness.