constructionclock-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
ConstructionClock MCP Server
A local Model Context Protocol server that gives Claude Desktop two ConstructionClock time-entry tools. It talks to the ConstructionClock REST API directly with fetch — no browser automation.
Tools
Tool | Required arguments | Hits |
|
|
|
|
|
|
Times are ISO-8601 local, with no timezone suffix, e.g. 2026-08-12T08:00:00
(that's the format ConstructionClock itself sends). employeeId is sent to the
API as userId. cc_edit_time needs the projectId too — the edit endpoint
requires it, not just the entry id.
Setup
Node.js 18+ is required (fetch is built in). Installed on this machine on
2026-08-13 via winget (OpenJS.NodeJS.LTS, Node v24.19.0) and dependencies are
already installed. To reinstall deps after a checkout:
cd "C:\Users\15049\OneDrive\Desktop\Claude\Tools\ConstructionClock-MCP"
npm installThe server loads .env relative to its own file, so it works no matter what
working directory Claude Desktop launches it from.
Then put your token in .env (copy from .env.example):
CC_API_TOKEN=your-real-tokenGet the token from the Authorization header of a captured ConstructionClock request in DevTools.
Register with Claude Desktop
Add this to your claude_desktop_config.json (%APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"constructionclock": {
"command": "node",
"args": ["C:\\Users\\15049\\OneDrive\\Desktop\\Claude\\Tools\\ConstructionClock-MCP\\src\\server.js"]
}
}
}Restart Claude Desktop. The two cc_* tools should appear.
Endpoints (verified)
Captured live from app.constructionclock.com on 2026-08-12:
ADD POST /api/punches
{ "punches": [ { userId, projectId, uuid, clockedInAt, clockedOutAt } ] }
EDIT PATCH /api/punch/edit/time
{ id, projectId, date: { dateFrom, dateTo }, uuid }uuid is generated per call by the server. If ConstructionClock ever changes
these, everything you'd need to edit lives in the CONFIG block at the top of
src/server.js.
Budget guardrail
See BUDGET_GUARDRAILS.md — a standing instruction for Claude Desktop sessions to check JobTread budgeted-vs-actual hours before adding or editing time.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read your tracked time and projects, pause tracking or add a note, from Claude or ChatGPT.
ClockShark MCP server for ChatGPT, Claude and any AI agent: list time entries, approve timesheet, create job, schedule shift and export payroll hours in your own ClockShark account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to ClockShark yourself; Cotlet does not store your password and you need no ClockShark API key. About the official ClockShark API: ClockShark has no public developer API or API docs (checked 10 Oct 2026). Admins can only generate a Zapier API key, which Zapier uses for 6 triggers and 2 actions: Create Job and Create Task. Setup and FAQ: https://cotlet.dev/integrations/clockshark-api-mcp-server
Hubstaff MCP server for ChatGPT, Claude and any AI agent: list timesheets, approve timesheet, review manual time request, add time entry, create project and create task in your own Hubstaff account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Hubstaff yourself; Cotlet does not store your password and you need no Hubstaff API key. About the official Hubstaff API: Hubstaff has a full REST API, API v2, with read and write scopes, and an official MCP server that is read-only (checked 17 Oct 2026). The MCP server reads organizations, members, projects, tasks and time and activity data for owners and managers, cannot create or change anything, and is switched on per organization after an email to Hubstaff support. Setup and FAQ: https://cotlet.dev/integrations/hubstaff-api-mcp-server
Connects AI assistants to TrackingTime for querying time entries, projects, tasks, customers, and team data using natural language.