Interact with Microsoft 365 and Office services through the Microsoft Graph API.
Deputy 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.
What it does
Deputy workforce data for AI agents: rosters, timesheets and shifts; read-only by default
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user augbastos-deputy-mcp '--' uvx deputy-mcp
# 2 — ask your agent for something these tools do
# deputy_whoami, deputy_get_my_calendar_url, deputy_get_my_roster and 13 more
Deputy costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 Deputy 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.
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user augbastos-deputy-mcp '--' uvx deputy-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take DEPUTY_API_TOKEN (API token mode (all tools): a Deputy API token, created with an admin access level. Pair with DEPUTY_BASE_URL. Configure exactly one of the three authentication modes: API token, OAuth, or iCal feed.), DEPUTY_BASE_URL (API token mode: your Deputy install origin, e.g. https://your-company.eu.deputy.com.), DEPUTY_OAUTH_CLIENT_ID (OAuth mode (all tools, no admin needed): client id of a personal app registered at https://once.deputy.com/my/oauth_clients with redirect URI http://localhost:8823/callback. Run 'deputy-mcp login' once.), DEPUTY_OAUTH_CLIENT_SECRET (OAuth mode: client secret of the same app.), DEPUTY_CALENDAR_URL (iCal feed mode (your own roster only, read-only): your personal Deputy calendar link. It contains a private token.), DEPUTY_ALLOW_WRITES (Set to true to register the write tools (API token and OAuth modes). Read-only by default.), DEPUTY_TOKEN_STORE (OAuth mode: file path for a plaintext token store, only where no OS keychain is available. Default: the OS keychain.) if you want to set them.
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.
16 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.
Verify the Deputy connection and confirm which identity the token uses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| response_format | no | — |
Return the signed-in user's personal Deputy calendar (iCal) subscription URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| response_format | no | — |
List the signed-in user's own upcoming shifts in a date range.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start_date | string | no | Start date (ISO). |
| end_date | string | no | End date (ISO). |
| response_format | no | — |
Return the single next upcoming shift for an employee (name or id).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| employee | string | no | Employee name or id. |
| response_format | no | — |
List every scheduled shift in a date range, optionally scoped to one area.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | string | no | Single day (ISO); overrides range. |
| start_date | string | no | Range start (ISO). |
| end_date | string | no | Range end (ISO). |
| area_id | integer | no | OperationalUnit id filter. |
| response_format | no | — |
Show who is working at an instant: physically clocked in vs scheduled on.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| at | string | no | Instant to evaluate (ISO datetime). |
| response_format | no | — |
Look up one or more employees by name (substring) or numeric id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name_or_id | string | yes | Employee name (substring) or numeric id. |
| response_format | no | — |
Search shifts by employee (name or id), area, date range, and open status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| employee | string | no | Employee name or id. |
| area_id | integer | no | OperationalUnit id filter. |
| start_date | string | no | Range start (ISO). |
| end_date | string | no | Range end (ISO). |
| open_only | boolean | no | Only unassigned open shifts. |
| limit | integer | no | Max shifts (<=500). |
| offset | integer | no | Records to skip (pagination). |
| response_format | no | — |
List areas (operational units / work locations) with their ids.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| response_format | no | — |
List the signed-in user's own timesheets (actual worked time) in a range.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start_date | string | no | Start date (ISO). |
| end_date | string | no | End date (ISO). |
| response_format | no | — |
List the people you work with (self-service colleague directory).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| same_workplace_only | boolean | no | Only colleagues at your own workplace/location. |
| response_format | no | — |
Sign the user in to Deputy with OAuth by opening their browser.
Takes no parameters.
Assign the signed-in user to an open shift, after the user confirms it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| shift_id | integer | yes | Roster.Id of the open (unassigned) shift to take. |
| response_format | no | — |
Record an unavailability window for the signed-in user.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | string | yes | Window start, ISO 8601, e.g. 2026-07-20T09:00:00 or with offset. |
| end | string | yes | Window end, ISO 8601; must be after start. |
| reason | string | no | Optional comment stored with the record. |
| repeat | string | no | Optional iCal RRULE for a recurring block, e.g. 'FREQ=WEEKLY;INTERVAL=1;BYDAY=MO' or 'FREQ=MONTHLY;BYMONTHDAY=6'. FREQ must be WEEKLY or MONTHLY. Omit for a one-off block. |
| response_format | no | `markdown (default) or json`. |
Clock the signed-in user in, starting a live timesheet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| area_id | integer | no | OperationalUnit.Id (the area/location) to clock into. Omit only if the install has a single rosterable area; otherwise required. |
| response_format | no | `markdown (default) or json`. |
Clock the signed-in user out, ending their live timesheet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mealbreak_minutes | integer | no | Optional unpaid meal-break length, in minutes, to record. |
| response_format | no | `markdown (default) or json`. |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- 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 Deputy or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tools were statically extracted from the published source (16 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>".
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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| deputy_login | no tags | |
| deputy_whoami | no tags | |
| deputy_get_my_calendar_url | no tags | |
| deputy_get_my_roster | no tags | |
| deputy_next_shift | no tags | |
| deputy_get_team_roster | no tags | |
| deputy_who_is_working | no tags | |
| deputy_get_employee_info | no tags | |
| deputy_search_shifts | no tags | |
| deputy_get_areas | no tags | |
| deputy_get_my_timesheets | no tags | |
| deputy_get_my_colleagues | no tags | |
| deputy_claim_open_shift | no tags | |
| deputy_set_unavailability | no tags | |
| deputy_clock_in | no tags | |
| deputy_clock_out | no tags |
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
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 0.4.2. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
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.
Any signed-in account that does not publish Deputy can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.