Timesheet Data MCP

MCP server that provides work checkpoint querying and timesheet report storage for AI assistants. Part of a personal AI-powered time tracking system — reads checkpoints logged via the Work Checkpoints Raycast extension and stores finalized timesheet reports in a local SQLite database.

How it fits together

┌─────────────────────┐
│  Raycast Extension  │  ← work-checkpoints
│  (logs checkpoints) │
└────────┬────────────┘
         │ writes
         ▼
   checkpoints.json     ← flat file, local only
         │
         │ reads
         ▼
┌─────────────────────┐
│   MCP Server        │  ← this repo
│   (this repo)       │
└────────┬────────────┘
         │ exposes tools to
         ▼
   Claude Desktop       ← generates timesheet from checkpoints
         │
         │ saves finalized reports
         ▼
     timesheet.db       ← SQLite database

Related MCP server: timedoctor-mcp

Tools

Checkpoint tools (read from JSON)

Timesheet tools (read/write SQLite)

Categories

Entries are classified as: client_project, client_maintenance, internal_dev, or non_billable.

Setup

npm install
npm run build

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

{
  "mcpServers": {
    "timesheet-data": {
      "command": "node",
      "args": ["/path/to/timesheet-data-mcp/dist/index.js"],
      "env": {
        "CHECKPOINTS_PATH": "/path/to/checkpoints.json"
      }
    }
  }
}

• CHECKPOINTS_PATH (required) — path to the checkpoints.json file synced by the Raycast extension

• TIMESHEET_DB_PATH (optional) — defaults to ~/Library/Application Support/timesheet-assistant/timesheet.db

The database and table are created automatically on first run.

Scripts

Related

• work-checkpoints — Raycast extension that logs the checkpoints