Executive Copilot

An MCP (Model Context Protocol) server that provides AI assistants with access to an executive's digital workspace. Aggregates data from email, calendar, tasks, and documents to enable intelligent assistance.

Features

• MCP Interface: Works with Claude Desktop, ChatGPT, Cursor, and any MCP-compatible client
• Multi-Provider Architecture: Pluggable providers for Outlook, Gmail, Google Calendar, Asana, and more
• Context Engine: Intelligently determines which information sources to consult
• Memory Layer: Persistent knowledge base for organizations, people, and decisions
• Automation Engine: Scheduled jobs for synchronization and briefings

Quick Start

Prerequisites

• Python 3.12+
• uv (Python package manager)

Installation

# Clone the repository
git clone https://github.com/gppsys/personalcopilot.git
cd personalcopilot

# Install dependencies
uv sync

# Copy and configure your settings
cp config/organizations.example.yaml config/organizations.yaml
# Edit config/organizations.yaml with your accounts

# Initialize database
uv run copilot db init

# Run MCP server
uv run copilot mcp

Connect to Claude Desktop

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "executive-copilot": {
      "command": "uv",
      "args": ["--directory", "/path/to/personalcopilot", "run", "copilot-mcp"]
    }
  }
}

Architecture

┌─────────────────────────────────────────────────────────────────┐
│                         MCP Layer                                │
│              (FastMCP server with tool definitions)              │
├─────────────────────────────────────────────────────────────────┤
│                       Service Layer                              │
│    (EmailService, CalendarService, ContextService, etc.)         │
├─────────────────────────────────────────────────────────────────┤
│                       Domain Layer                               │
│         (Models, Business Rules, Value Objects)                  │
├─────────────────────────────────────────────────────────────────┤
│                    Infrastructure Layer                          │
│       (Providers, Repositories, Database, Config)                │
└─────────────────────────────────────────────────────────────────┘

Available MCP Tools

Tool	Description
get_inbox	Get recent inbox emails
search_emails	Search emails with query
today_schedule	Get today's calendar events
upcoming_events	Get upcoming events
my_tasks	Get assigned tasks
overdue_tasks	Get overdue tasks
daily_summary	Combined daily briefing
organization_context	Get organization information
search_everything	Unified search across sources
recall_memory	Search knowledge base

Configuration

Configuration is managed through YAML files in the config/ directory:

• config.yaml - Base configuration
• organizations.yaml - Organization definitions (create from .example.yaml)
• context_rules.yaml - Context engine rules
• automation.yaml - Scheduled job configuration

See Configuration Guide for details.

Development

# Install dev dependencies
uv sync --dev

# Run tests
uv run pytest

# Run linter
uv run ruff check .

# Type checking
uv run mypy src

See Development Guide for detailed instructions.

Documentation

• Architecture
• Development Guide
• Configuration
• Provider Guide
• MCP Guide
• Roadmap

License

MIT