Revenue Engine MCP
# Revenue Engine MCP
A Model Context Protocol (MCP) server that connects Claude AI to Google Sheets, Gmail, and Calendar for comprehensive revenue tracking and business management.
## Features
- 📊 **Revenue Dashboard** - Real-time tracking of leads, revenue, and metrics
- 🔄 **Lead Pipeline Management** - Track leads from contact to close
- 📧 **Gmail Integration** - Search, read, and send emails
- 📅 **Calendar Integration** - Manage meetings and schedules
- ✅ **Task Management** - Track tasks and time
- 📝 **Knowledge Matrix** - Structured documentation with automated analysis
- 🐛 **Bug Tracking** - UID-based bug tracking system
- 📂 **File Operations** - Read, write, and edit local files
## Installation
### Prerequisites
- Node.js >= 18.0.0
- Google Account with access to Sheets, Gmail, and Calendar
- Claude Desktop app
### Setup
1. **Clone the repository**
```bash
git clone https://github.com/YOUR_USERNAME/revenue-engine-mcp.git
cd revenue-engine-mcp
```
2. **Install dependencies**
```bash
npm install
```
3. **Configure Claude Desktop**
Add to your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"revenue-engine": {
"command": "node",
"args": ["C:\\path\\to\\revenue-engine-mcp\\index.js"]
}
}
}
```
4. **Deploy Google Apps Script**
- Set up your Google Apps Script web app
- Update the `API_URL` in `index.js` with your deployment URL
5. **Restart Claude Desktop**
## Tools Available
### Revenue & Pipeline
- `get_dashboard` - Get current revenue metrics
- `get_pipeline` - View all leads
- `add_lead` - Add new lead
- `update_lead` - Update lead status
- `add_revenue` - Log closed deal
### Email & Calendar
- `search_gmail` - Search inbox
- `get_email_content` - Read full email
- `send_email` - Send email
- `get_upcoming_meetings` - View calendar
### Knowledge Matrix
- `setup_matrix_sheet` - Initialize Matrix
- `write_matrix_entry` - Log work
- `matrix_daily_summary` - Generate daily summary
- `matrix_time_analysis` - Analyze time spent
### Task Management
- `add_task` - Create task
- `get_tasks` - View all tasks
- `update_task` - Update task status
### File Operations
- `read_file` - Read file contents
- `edit_file` - Surgical file editing
- `write_file` - Write/update files
- `run_command` - Execute shell commands
## Documentation
See [Full Specification](docs/SPECIFICATION.md) for complete documentation.
## Version
Current version: 1.7.0
## License
MIT
TDQS
Scored across 29 tools
Most tools have distinct purposes, but there is some overlap that could cause confusion. For example, 'get_matrix_row' and 'read_matrix_snapshot' both retrieve matrix data with subtle differences in scope, and 'edit_file' vs 'write_file' have overlapping file modification functions. The descriptions help clarify, but agents might misselect between similar tools.
Naming is mostly consistent with a verb_noun pattern (e.g., 'add_lead', 'get_dashboard', 'update_task'), but there are minor deviations like 'check_new_leads' (verb_adjective_noun) and 'matrix_daily_summary' (noun_adjective_noun). These inconsistencies are minor and do not severely impact readability, as the overall pattern remains clear.
With 29 tools, the count is borderline high for a revenue engine server, which typically handles sales, tasks, and metrics. While many tools are justified for diverse operations (e.g., matrix management, file editing, email handling), the set feels heavy and could be streamlined, potentially overwhelming agents with too many options.
The tool set covers a broad domain including lead management, task tracking, metrics logging, email operations, file handling, and matrix knowledge management. There are minor gaps, such as no tool for deleting leads or tasks, and limited meeting management beyond retrieval. However, core workflows are well-supported, and agents can work around these omissions.