chronos-protocol

Chronos Protocol is an MCP server that adds time intelligence, persistent memory, and complete traceability to AI coding agents. It exposes a suite of tools designed to give agents accurate system time context, manage long-running tasks, and preserve session continuity across sessions. Core capabilities include time awareness through get_current_time and convert_time, persistent activity logging with start_activity_log, end_activity_log, get_elapsed_time, and get_activity_logs, as well as intelligent reminders via create_time_reminder and check_time_reminders. These tools enable autonomous agents to schedule, track, and document their work with timestamps and metadata, while maintaining continuity across separate runs or projects. The server can be configured for centralized storage or per-project storage, allowing you to tailor memory scope to your development workflow.

Prerequisites:

• Python 3.10 or newer
• Internet access to fetch packages

Step-by-step installation:

1. Create and activate a virtual environment (optional but recommended):

   • python -m venv venv
   • source venv/bin/activate (Unix/macOS) or .\venv\Scripts\activate (Windows)

2. Install the Chronos Protocol MCP server package from PyPI:

   • pip install chronos-protocol

3. Run the MCP server:

   • python -m chronos_protocol

4. (Optional) Configure environment variables for storage and API settings:

   • CHRONOS_STORAGE_MODE: 'centralized' (default) or 'per-project'
   • CHRONOS_API_PORT: specify a custom port for the HTTP API if exposed

5. If you need a persistent background service, wrap the command in your system’s service manager (systemd, Windows Service, etc.).

Notes and tips:

• By default Chronos Protocol uses centralized storage for persistent memory. Set CHRONOS_STORAGE_MODE=per-project to enable per-project storage, which stores data under {project-root}/chronos-data/time_server_data.json.
• The MCP API/tools listed (get_current_time, convert_time, start_activity_log, end_activity_log, get_elapsed_time, get_activity_logs, update_activity_log, create_time_reminder, check_time_reminders) can be invoked by MCP clients that integrate with this server. Refer to theChronos Protocol API reference in the docs for exact parameter schemas and response formats.
• If you’re behind a firewall or using a proxy, ensure the API port is accessible to MCP clients and that any required TLS/authentication is configured as per your deployment needs.
• When upgrading, verify compatibility with your AI agents’ prompts and ensure the storage location paths remain writable by the process user.