mite
This server provides read-only access to mite time-tracking data for reporting and lookup.
Identify the account, API user/role, server mode, and enabled tools via
mite_whoami.Generate aggregated reports: hours/revenue per project and month, custom 1–3 level groupings, project budgets, and billable/non-billable ratios.
Browse time entries: list entries with period filters and paging, fetch one entry by id, and check tracker status.
Look up master data: customers, projects, services, and users, including active or archived records.
No write or admin tools are exposed in this schema; all listed tools are read-only.
mite-mcp-server
English · Deutsch
Ask Claude about your mite time tracking — "How many hours did we spend on each project per month this year, and what did that earn?" — and get the answer from a report mite computes itself, not from hundreds of entries the model has to add up.

Unofficial. Not affiliated with or endorsed by mite GmbH.
Why this server
Ready-made reports. mite groups on the server (
group_by), so a whole year is one request and one small answer.Safe by default. Starts read-only. Write tools only exist when you switch the mode on, and an allowlist narrows it further. Tools outside mode and allowlist are not even shown to the agent.
Your key stays yours. API key from the environment only, sent as header, removed from every error message, never logged.
Related MCP server: KIMAI MCP Server
Tools
Tool | Mode | What it does |
| read-only | Account, your user and role, server mode and enabled tools |
| read-only | Hours and revenue per project and month for a period; filters for customer, project, service, user, billable |
| read-only | Hours, revenue and share per 1–3 groupings (customer, project, service, user, day, week, month, year); same filters |
| read-only | Budget, consumption, remaining and percent used per project over its whole life; minutes in hours, cents in currency units |
| read-only | Billable and non-billable hours and billable share in percent for a period, optionally per customer, project, user or month |
| read-only | Single time entries for a period, newest first; filters, |
| read-only | One time entry by id |
| read-only | Whether the tracker is running, and on which entry |
| read-only | Customers, active or archived ( |
| read-only | Projects with customer and budget, active or archived |
| read-only | Services, active or archived |
| read-only | Users and roles (no email, no rates), active or archived |
| write | Creates a time entry; |
| write | Changes fields of a time entry (locked ones: see below); |
| write | Starts the tracker on a time entry |
| write | Stops the tracker on a time entry |
| write | Deletes a time entry in two steps with a confirmation token (see below); locked entries: see "Locked entries" |
| admin | Creates a customer, project or service; |
| admin | Changes fields; |
| admin | Deletes in two steps with a confirmation token (see below); mite's refusal, e.g. while time entries exist, is returned as an error |
Deleting with a confirmation token
mite_delete_time_entry and the three master data delete tools never delete on the first call:
Call it with the
id(or withdry_run: true). It returns a preview of the entry and aconfirm_token; nothing is deleted.Call it again with the same
idand theconfirm_token. Only then is it deleted.
The token is bound to the tool and its arguments, valid for 5 minutes, usable once, and only known to the running server process (a restart invalidates it).
If the MCP client supports elicitation, the second call (and any call with force: true and a token) additionally asks the human with a short summary of what will be deleted or forced. Only if the human accepts is anything executed. If they decline or cancel, nothing is sent to mite and the token stays unused until it expires. Clients without elicitation are not asked; the token alone applies.
Client support (checked 28.10.2026): Claude Desktop does not offer elicitation yet, so it shows no dialog; deleting there uses the token flow only. Once a client announces elicitation, the extra question applies without a new release of this server.
Locked entries
Locked time entries cannot be changed or deleted by default; mite answers with 423 and the tool returns a "locked" error. force is never set automatically, not even after a 423.
In mode admin only, mite_update_time_entry and mite_delete_time_entry additionally accept force: true. A call with force: true always needs a confirm_token, also on update: the first call (or dry_run: true) returns a preview stating that the entry is locked, plus a token; only a second call with the same arguments, force: true and the token executes. In modes read-only and write the parameter is not part of the input schema.
More tools (more reports) are planned — see the architecture decision.
Install without technical knowledge (Claude Desktop)
Download
mite-mcp-server.mcpbfrom the latest release.Double-click the file. Claude Desktop opens and offers to install the extension.
Fill in the settings and enable the extension:

Setting | Meaning |
mite-Account | The name in your mite address: for |
API-Key | Your personal mite API key; Claude Desktop stores it securely and shows it masked |
Zeiteinträge schreiben erlauben | Off (default): read only. On: create, change and delete time entries, start and stop the tracker |
Stammdaten verwalten | Off (default). On: manage customers, projects and services; includes writing time entries |
Erlaubte Werkzeuge | Optional, comma-separated tool names; empty means every tool the switches allow |
No JSON, no environment variables, no Node.js installation: Claude Desktop runs the bundle with its built-in Node.js. You need a mite account with API access enabled (in your mite user settings) and your API key from there. The settings are in German because mite's users mostly are.
Changing a setting later: Claude Desktop → Settings → Extensions → mite. A changed setting only takes effect after you switch the extension off and on again or restart Claude Desktop — until then the running server keeps the old switches. Ask Claude to call mite_whoami to see the mode the server is actually running in. In the same place you can also switch single tools on and off — on top of the switches above, which decide which tools exist at all.
Manual setup (Claude Desktop, for developers)
Requirements: Node.js 22 or newer, a mite account with API access enabled (enable it in your mite user settings), and your API key from there.
Add the server to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/), then restart Claude Desktop:
{
"mcpServers": {
"mite": {
"command": "npx",
"args": ["-y", "mite-mcp-server"],
"env": {
"MITE_ACCOUNT": "your-account",
"MITE_API_KEY": "your-api-key"
}
}
}
}Then ask, for example: "Show me hours and revenue per project and month for this year."
Configuration
Variable | Required | Meaning |
| yes | Account name — the subdomain of |
| yes | Your personal mite API key |
| no |
|
| no |
|
| no |
|
| no | Comma-separated allowlist, e.g. |
Use either MITE_MODE or the two switches; the server refuses MITE_MODE together with a switch set to true. Values true/false (also 1/0, yes/no, on/off).
mite still checks every call against the role of your key. The server can only restrict that, never extend it.
Development
npm ci
npm run check # lint, format, typecheck, tests with coverage, buildSee CONTRIBUTING.md and the architecture decision.
License
MIT © Stefan Jacomeit — www.jacomeit.de
Available Tools
12 toolsmite_get_time_entryGet one time entryARead-only
Fetches one time entry from mite by its id; use it when the id is known, otherwise find entries with mite_list_time_entries. Returns date, hours, revenue in currency units (null if none), billable and locked flags, customer, project, service, user and note. Fails with "not found" if no time entry has this id.
Inputs: id (required).
mite_list_customersList customersARead-only
Lists customers from mite, active ones or with archived: true the archived ones; use it to look up customer ids for filters such as customer_id in mite_list_time_entries. Returns id, name, archived flag and note per customer. The whole list is returned at once without paging.
Inputs: archived.
mite_list_projectsList projectsARead-only
Lists projects from mite, active ones or with archived: true the archived ones; use it to look up project ids for filters such as project_id in mite_list_time_entries, for budget usage use mite_report_budget. Returns id, name, customer, archived flag, note, budget and budget_type; budget is in the unit given by budget_type (minutes or cents), not hours or currency units. The whole list is returned at once without paging.
Inputs: archived.
mite_list_servicesList servicesARead-only
Lists services (activity types) from mite, active ones or with archived: true the archived ones; use it to look up service ids for filters such as service_id in mite_list_time_entries. Returns id, name, billable flag, archived flag and note per service. The whole list is returned at once without paging.
Inputs: archived.
mite_list_time_entriesList time entriesARead-only
Lists single time entries from mite for a period, newest first, optionally filtered by customer, project, service, user, billable or locked. Use it to find individual entries or their ids; for totals use mite_report, for one known entry use mite_get_time_entry. Each row has hours, revenue in currency units (null if none), the locked flag and the note. Returns at most limit entries per page (default 100, max 1000) and has_more when further pages exist; the period defaults to this_year.
Inputs: to, from, page, limit, +6 more.
mite_list_usersList usersARead-only
Lists users from mite, active ones or with archived: true the archived ones; use it to look up user ids for user_id in mite_list_time_entries, and mite_whoami for the current user. Returns id, name, role and archived flag per user; email addresses and hourly rates are not returned. The whole list is returned at once without paging.
Inputs: archived.
mite_reportHours and revenue grouped by up to three levelsARead-only
Aggregated report from mite: hours, revenue and share of hours, grouped by 1 to 3 of customer, project, service, user, day, week, month, year for a period, on the mite server so whole years work. For the fixed project-by-month view use mite_report_projects_by_month, for billable share use mite_report_billable_ratio, for budgets use mite_report_budget. Returns rows with hours, revenue in currency units (null without rates) and share of hours in percent, plus a total. Read-only, no paging, default period is this year.
Inputs: group_by (required), to, from, user_id, +4 more.
mite_report_billable_ratioBillable and non-billable hours with billable shareARead-only
Billable hours, non-billable hours and the billable share in percent for a period, optionally per customer, project, user, month, aggregated on the mite server. For revenue or other groupings use mite_report. Returns hours and a ratio in percent with one decimal, per group and as a total. Read-only, no paging, default period is this year.
Inputs: to, from, group_by.
mite_report_budgetProject budgets and their consumptionARead-only
Budget, consumption, remaining budget and percent used per project over the whole project life, not for a period; for hours or revenue in a period use mite_report. Minute budgets are in hours, cent budgets in currency units (consumption = revenue); budget, remaining and percent are null for projects without a budget. Without project_id: all active projects with a budget. Read-only, no paging.
Inputs: project_id.
mite_report_projects_by_monthHours and revenue per project and monthARead-only
Aggregated report from mite: hours and revenue per project and month for a period, grouped on the mite server so whole years work without reading single entries. For other groupings or totals use mite_report; for single entries use mite_list_time_entries. Returns rows of month (YYYY-MM), project, hours and revenue in currency units plus a total; revenue is null without rates. Read-only, no paging, default period is this year.
Inputs: to, from, user_id, billable, +3 more.
mite_tracker_statusTracker statusARead-only
Tells whether the mite time tracker is currently running for the key's user and, if so, on which time entry. Returns running and, when it runs, time_entry_id, the start time since and minutes, the entry's total so far in minutes. Read-only and takes no input; to look at that entry in full use mite_get_time_entry.
Inputs: no named parameters.
mite_whoamiWho am I in miteARead-only
Shows the mite account, the user behind the API key and its role, plus the mode and tools this server offers. Call it first to learn what you are allowed to do; for projects use mite_list_projects, for customers mite_list_customers. Returns account name, title and currency, the user id, name and role, and the server mode with the names of all enabled tools. Takes no input and is available in every mode.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Most tools target distinct operations; the main ambiguity is among the four report tools, but descriptions explicitly route between them (fixed project-by-month, flexible grouping, budget, billable ratio). `mite_list_projects` also exposes budget fields while `mite_report_budget` handles budget usage, but the boundary is stated.
Names use a consistent `mite_` prefix and snake_case, mostly following a verb_noun pattern such as `list_time_entries`, `get_time_entry`, and `report_budget`. Minor deviations are `whoami`, bare `report`, and `tracker_status`, but they remain readable and predictable.
Twelve tools is well within the ideal range and each supports a clear part of the read/report workflow: identity, reference lists, time entries, tracker status, and aggregations. No obvious redundant filler.
The surface covers read-only lookups and reporting well, including time entries, reference data, budgets, and billable ratios. However, there are no create/update/delete operations for time entries and no start/stop tracker controls, so lifecycle coverage is notably incomplete if the server is meant to support time tracking rather than only reporting.
Maintenance
Related MCP Connectors
Read time entries, projects, clients, tasks and invoices; log and update tracked time.
Time tracking, tasks and team chat for humans and AI agents.
MCP server for MOCO business software: time tracking, projects, budgets, and invoicing via API
timesheet.io MCP server - manage timers, projects, tasks and reports
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceModel Context Protocol server for the mite time tracking API, enabling time entries, stopwatch, customers, projects, and services management through natural language.15 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to interact with KIMAI 2 time tracking for managing timesheets, projects, activities, customers, and generating reports.MIT
- AlicenseAqualityBmaintenanceA read-only MCP server for querying Timely time tracking data, providing tools for project overviews, time spent summaries, and work log entries.3MIT
- AlicenseNot gradedqualityCmaintenanceRead-only MCP server for Clockify time tracking, exposing 60 raw read tools and five workflows for status, workspace overview, and review of days/weeks.MIT