temporal-mcp
Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"temporal-mcp": {
"command": "uvx",
"args": [
"temporal-mcp"
]
}
}
}Runnable packages
0.2.0stdioRemote endpoints
https://temporal-mcp.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (2)
⚪temporal_tick(thread_key, client_id, tz_offset_minutes, tz_name)
Advance the temporal clock for a thread and return a snapshot (now / prev / gap / day_rollover / fresh_thread). Call once per user turn. Pass a stable `thread_key` (e.g. the conversation ID) so gap deltas remain meaningful across page reloads.
Input Schema
{
"type": "object",
"properties": {
"thread_key": {
"type": "string",
"description": "Stable thread identifier within this client. For claude.ai web use the conversation ID; for other MCP clients any caller-stable string. If omitted, falls back to the Mcp-Session-Id header."
},
"client_id": {
"type": "string",
"description": "Namespace tag (e.g. 'caweb', 'cursor'). Defaults to 'mcp'."
},
"tz_offset_minutes": {
"type": "integer",
"description": "Caller's UTC offset in minutes (e.g. -360 for MDT). Used for day_rollover detection and header formatting. Defaults to 0 (UTC) so day rollover is always honest even if the caller forgets to pass one."
},
"tz_name": {
"type": "string",
"description": "Display name for the timezone (e.g. 'MDT'). Cosmetic; appears in the rendered header."
}
}
}🟢temporal_peek(thread_key, client_id, tz_offset_minutes, tz_name)
Read the current temporal snapshot for a thread WITHOUT advancing state. Use this when you want the gap delta but the call is not the canonical per-turn event.
Input Schema
{
"type": "object",
"properties": {
"thread_key": {
"type": "string"
},
"client_id": {
"type": "string"
},
"tz_offset_minutes": {
"type": "integer"
},
"tz_name": {
"type": "string"
}
}
}Community
Evidence