quoteBuilderMCP

MCP server for generating SVL equipment quote documents (.docx). Works with Claude Code, Claude Desktop, or any MCP-compatible client.

What it does

• list_equipment — Search the built-in equipment library (21 templates) by manufacturer, type, or model

• generate_quote — Generate a formatted .docx quote document from structured data

The server includes a Word template with SVL branding/styles and an equipment library with pre-built specs for common HVAC equipment (Aaon, Daikin, Cook, Reznor, etc.).

Install

Requires Python 3.10+.

pip install git+https://github.com/jacobe603/quoteBuilderMCP.git

Or clone and install locally:

git clone https://github.com/jacobe603/quoteBuilderMCP.git
cd quoteBuilderMCP
pip install .

Quick Start (Claude Code)

This repo includes a .mcp.json, so Claude Code will automatically detect the MCP server after install:

git clone https://github.com/jacobe603/quoteBuilderMCP.git
cd quoteBuilderMCP
pip install -e .

Then open the project in Claude Code — the server is ready to use.

To customize the output directory, set the QUOTE_OUTPUT_DIR env var in .mcp.json:

{
  "mcpServers": {
    "quoteBuilderMCP": {
      "command": "quote-builder-mcp",
      "env": {
        "QUOTE_OUTPUT_DIR": "C:/Users/you/Documents/SVL Quotes"
      }
    }
  }
}

If QUOTE_OUTPUT_DIR is not set, quotes save to the package's output/ directory.

Gemini API Key (optional — for schedule image OCR)

The analyze_schedule_image tool uses Google Gemini Flash to extract structured text from equipment schedule images, reducing Claude's vision token usage. To enable it:

1. Get a Gemini API key from Google AI Studio

2. Add it to .mcp.json:

{
  "mcpServers": {
    "quoteBuilderMCP": {
      "command": "quote-builder-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Without the key, all other tools work normally — Claude will just analyze schedule images directly via vision instead.

Configure in Claude Desktop

Add to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "quoteBuilderMCP": {
      "command": "quote-builder-mcp",
      "env": {
        "QUOTE_OUTPUT_DIR": "C:/Users/you/Documents/SVL Quotes"
      }
    }
  }
}

Usage

Once configured, ask Claude to build a quote:

"Build an SVL quote for 3 Aaon RN rooftop units for the Maple Grove project"

Claude will:

1. Look up the equipment template from the library

2. Ask you for pricing and salesman info

3. Generate a formatted .docx quote

Equipment Library

The built-in library includes templates for:

Development

pip install -e .
quote-builder-mcp