A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Track Your Time is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
15
downloads a day
local
runs on your machine
152
downloads in 30d
What it does
Track time, manage entries and catalog, and summarize hours on hosted or self-hosted accounts.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'TRACKYOURTIME_API_TOKEN=${TRACKYOURTIME_API_TOKEN}' --transport stdio track-your-time-mcp '--' npx -y trackyourtime-mcp
# 2 — ask your agent for something these tools do
# get_token_info, get_running_timer, start_timer and 12 more
It needs TRACKYOURTIME_API_TOKEN: this reads it from your environment, so export it first.
Track Your Time costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TRAll 2 servers
trebeljahr2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Track Your Time as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads TRACKYOURTIME_API_TOKEN (A workspace API token created in Settings → Integrations) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx TRACKYOURTIME_API_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'TRACKYOURTIME_API_TOKEN=${TRACKYOURTIME_API_TOKEN}' --transport stdio track-your-time-mcp '--' npx -y trackyourtime-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: TRACKYOURTIME_API_TOKEN — A workspace API token created in Settings → Integrations.. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Confirm the MCP server can reach Track Your Time, and show the token's workspace, scopes and whether it may see other members' time and money. Call this first when another tool fails with an authentication error.
No parameter schema on file.
Return the timer currently running in this token's workspace, with how long it has run, or say that none is running.
No parameter schema on file.
Start a timer now (or at start). A timer already running in this workspace is stopped first. Use list_projects, list_tasks and list_tags to find ids; pass none of them to track unfiled time. Answers 409 when a timer runs in another workspace this token cannot stop.
No parameter schema on file.
Stop the timer running in this workspace, now or at end. Pass id to stop a specific entry; stopping an entry that is already stopped returns it unchanged.
No parameter schema on file.
Create a finished time entry with an explicit start and end, for work that was not timed. start and end are ISO-8601 timestamps with an offset or Z, and end must be after start.
No parameter schema on file.
List time entries that overlap a date range, newest first, with project, client and task names. Filter by project, client, task, tag, billable flag, or a text search over descriptions. Returns up to limit entries (default 100, max 500); pass nextCursor back as cursor for the next page.
No parameter schema on file.
List the workspace's clients. Archived clients are left out unless includeArchived is true.
No parameter schema on file.
List projects with their client, hourly rate, total tracked time and budget progress. Narrow to one client with clientId. Archived projects are left out unless includeArchived is true.
No parameter schema on file.
List tasks. A task is a workspace-wide kind of work (for example "Design review"), not part of a project: an entry carries a project and a task independently.
No parameter schema on file.
List tags with usage totals. Automation-only hidden tags are excluded unless includeHidden is true.
No parameter schema on file.
Create a client. A colour is assigned when none is given.
No parameter schema on file.
Create a project, optionally under a client (clientId from list_clients), with an hourly rate, a billable default, estimated hours or a budget.
No parameter schema on file.
Create a workspace-wide task, a name for a kind of work that any project's entries can use. Task names are unique per workspace.
No parameter schema on file.
Create a tag. Entries can carry several tags, and reports can group by them.
No parameter schema on file.
Total, billable time and amount for a date range, broken down by project, client, task or tag (or by day, week or month), plus a daily series. Grouped by tag, each entry counts fully toward every tag it carries, so tag rows can add up to more than the total. Refused when the token's owner may not…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under AGPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Track Your Time or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.3.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest23b0cf58f95a6e6a5b96458e6474d02ce09593b7fc933ba0b204516cef0ba4e5
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (13 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
13 of the 13 recovered tools are registered only when scopes && tool.scope && !scopes.has(tool.scope) is false (dist/index.js:1804) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
No tool is registered unconditionally · 13 only when scopes && tool.scope && !scopes.has(tool.scope) is false (dist/index.js:1804) — typically when a key or option is configured. All 13 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_token_info conditional | sensitive-sourceuntrusted-input | sensitive-source: keyword "get_token"; untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_running_timer conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| start_timer conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| stop_timer conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| log_time_entry conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_entries conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_projects conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_tasks conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_tags conditional | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| create_client conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_project conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_task conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_tag conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
get_running_timer → get_token_info → create_client
A cross-tool exfiltration chain exists: get_running_timer → get_token_info → create_client.
Supply chain and provenance
Integrityfirst-seen
Surface digest23b0cf58f95a6e6a
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.3.0. Pin a release below and the command asks for exactly that one.
0.3.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Track Your Time can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.