Temporal Cortex MCP
@billylui
About Temporal Cortex MCP
Temporal Cortex is a Model Context Protocol server that gives AI agents deterministic calendar capabilities — temporal context, datetime resolution, multi-calendar availability merging across Google Calendar, Microsoft Outlook, and CalDAV, and conflict-free booking with Two-Phase
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"temporal-cortex": {
"command": "npx",
"args": [
"-y",
"@temporal-cortex/[email protected]"
],
"env": {
"GOOGLE_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
"GOOGLE_CLIENT_SECRET": "your-client-secret",
"TIMEZONE": "America/New_York"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Temporal Cortex MCP?
Temporal Cortex MCP gives any AI agent autonomous scheduling capabilities. It is open scheduling infrastructure that integrates with Google Calendar, Microsoft Outlook, and CalDAV, providing temporal awareness, cross-provider availability, and atomic booking. It is accessible via MCP, A2A, REST, and browser, powered by the Truth Engine.
How to use Temporal Cortex MCP?
Install via npx @temporal-cortex/cortex-mcp and run npx @temporal-cortex/cortex-mcp setup for an interactive wizard. For manual setup, configure environment variables like GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, and TIMEZONE in your MCP client's config file. Alternatively, use the managed Platform at app.temporal-cortex.com with an API key.
Key features of Temporal Cortex MCP
- 18 tools across 5 layers for scheduling.
- Temporal awareness with
get_temporal_contextandresolve_datetime. - Atomic booking with Two-Phase Commit to prevent double-booking.
- Computed availability that merges free/busy across multiple calendars.
- Deterministic RRULE expansion handling DST, BYSETPOS, EXDATE, and leap years.
- TOON format for token-efficient calendar data output.
Use cases of Temporal Cortex MCP
- AI agent scheduling meetings across Google Calendar and Outlook without double-booking.
- Developers integrating scheduling into their own AI products via MCP, A2A, REST, or browser.
- Automating complex recurrence rule handling for recurring events.
- Resolving ambiguous natural language time expressions like "next Tuesday at 2pm" into precise timestamps.
- Managed platform usage for individuals who want scheduling without local Node.js setup.
FAQ from Temporal Cortex MCP
What runtime dependencies does Temporal Cortex MCP require?
Node.js 18+ (for npx) or Docker. At least one calendar provider: Google Calendar (needs OAuth credentials), Microsoft Outlook (needs Azure AD app registration), or CalDAV (needs app-specific password).
How does Temporal Cortex MCP prevent double-bookings?
Atomic booking uses Two-Phase Commit: lock the time slot, verify no conflicts exist, then write. If two agents try to book the same slot, exactly one succeeds.
Where are credentials stored?
Credentials are saved to ~/.config/temporal-cortex/credentials.json and provider config to ~/.config/temporal-cortex/config.json after authentication.
What transports and authentication methods are supported?
The server supports MCP (stdio), A2A, REST, and browser protocols. Authentication is per-provider OAuth (Google, Outlook) or app-specific password (CalDAV). The managed Platform uses API key auth.
How is installation verified?
SHA256 checksums are published with each GitHub release and embedded in the npm package. On mismatch, installation fails with an error. Docker can be used for maximum isolation.
More Other MCP servers
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
🪟 Windows-MCP
CursorTouchMCP Server for Computer Use in Windows

EverArt
modelcontextprotocolModel Context Protocol Servers
Comments