This guide walks you through connecting your AI tool to BookYourPTO using the Model Context Protocol (MCP). Once connected, your AI assistant can manage leaves, time tracking, expenses, and more.
https://mcp.bookyourpto.com/sse.Run this command in your terminal:
claude mcp add --transport sse bookyourpto https://mcp.bookyourpto.com/sse
Use the --scope flag to control where the server is available:
--scope local (default) — Available only to you in the current project--scope project — Shared with your team via .mcp.json file--scope user — Available to you across all projectsUse the /mcp command inside Claude Code to list and manage your MCP servers.
{
"mcpServers": {
"bookyourpto": {
"url": "https://mcp.bookyourpto.com/sse"
}
}
}
To share the configuration with your team, create a .cursor/mcp.json file in your project root with the same configuration.
.vscode/mcp.json file in your workspace:{
"servers": {
"bookyourpto": {
"type": "sse",
"url": "https://mcp.bookyourpto.com/sse"
}
}
}
Cmd+Shift+P / Ctrl+Shift+P) and run MCP: List ServersFor user-level configuration (all workspaces), run MCP: Open User Configuration from the Command Palette and add the server configuration there.
Claude Desktop uses local stdio transport. You'll need Docker installed to run the MCP server locally.
claude_desktop_config.json:{
"mcpServers": {
"bookyourpto": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "BYPTO_EMAIL=your-email@company.com",
"-e", "BYPTO_PASSWORD=your-password",
"bookyourpto/mcp-server:latest"
]
}
}
}
your-email@company.com and your-password with your BookYourPTO credentialsCmd+, on Mac) → search for MCPmcp_config.json{
"mcpServers": {
"bookyourpto": {
"serverUrl": "https://mcp.bookyourpto.com/sse"
}
}
}
https://mcp.bookyourpto.com/sse
BookYourPTO and saveAfter connecting, try asking your AI assistant:
"What's my leave balance?"
Your browser will open a BookYourPTO login page. Sign in with your email and password (2FA supported). Once authenticated, the browser will close and your AI client will be connected. The AI will then call the appropriate tools and return results from your workspace.
You can run the MCP server yourself using the public Docker image. This is useful for teams that want full control or need to run the server on their own infrastructure.
docker pull bookyourpto/mcp-server:latest
docker run -d \
--name bookyourpto-mcp \
-e BYPTO_EMAIL=your-email@company.com \
-e BYPTO_PASSWORD=your-password \
-e MCP_TRANSPORT=http \
-p 8000:8000 \
bookyourpto/mcp-server:latest
Verify it's running:
curl http://localhost:8000/health
Then connect your AI client to http://localhost:8000/sse instead of the hosted URL.
https://mcp.bookyourpto.com/ssecurl https://mcp.bookyourpto.com/healthOverview
Connect AI assistants to your BookYourPTO workspace using the Model Context Protocol (MCP). Manage leaves, time tracking, expenses, schedules, and more from any MCP-compatible client.
Tools Reference
Complete reference for all BookYourPTO MCP tools — parameters, descriptions, required roles, and usage examples.