What is MCP (Model Context Protocol)?
MCP, the Model Context Protocol, is an open standard for connecting AI assistants such as Claude to external tools and data. An MCP server describes the actions it offers, and the assistant can call them on the user's behalf.
How MCP works
Before MCP, every AI integration was custom work. MCP defines a common way for a server to list its tools, with names, descriptions and input fields, and for an assistant to call them and read the results. One MCP server works with every assistant that supports the protocol.
The assistant acts within the permissions of the credentials it is given. A read-only key can answer questions; a key with write access can also change data, so scope keys carefully.
The TimeTracking MCP server
TimeTracking has an MCP server with 18 tools on top of the REST API. With it, an assistant like Claude can answer questions such as which hours are still waiting for client approval this week, or enter hours for a worker, using an API key you control. Every action is recorded in the audit log like any other API call.
Related pages
Claude (MCP and Skill)
Ask Claude about hours and approvals through the TimeTracking MCP server and Claude Skill. Live.
API and integrations
Open REST API, webhooks, CLI and an MCP server for Claude, live today. Your data stays open.
Webhook
An automatic HTTP message one system sends to another when an event happens, such as hours being approved.
See pricing
Free for up to 5 users. Core from €1 per user per month, everything included.
Try TimeTracking free
Free for up to 5 users. Core from €1 per user per month, everything included.