See rosters, timesheets, leave and staff in Deputy, and create shifts, leave and memos. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"deputy": {
"url": "https://deputy.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"deputy": {
"type": "http",
"url": "https://deputy.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Deputy install host and Permanent access token.
Create one in Deputy → Integrations → API (developer portal): in your install open /exec/devapp/oauth_clients, choose New OAuth Client, then Get an Access Token. The token acts with its owner's Deputy permissions — supervisor tools (timesheet approval, publishing shifts) need a manager-level user. Your credentials are used only to call the API on your behalf and to derive a private account id; they are never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Deputy install host and Permanent access token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Deputy connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
deputy_whoami | read | Who am I Return the Deputy user the token belongs to — name, employee id, company and permissions. A cheap way to confirm DEPUTY_INSTALL and the token are right. Deputy: GET /api/v1/me. |
deputy_list_locations | read | List locations List the install's locations (workplaces). Deputy calls a location a Company; its Id is what other tools take as location_id. Deputy: GET /api/v1/resource/Company. |
deputy_list_areas | read | List areas List areas (Deputy OperationalUnits — the rosterable sections of a location, e.g. Kitchen, Front of house). Shifts and timesheets belong to an area. Optionally only one location's areas. Deputy: GET /api/v1/resource/OperationalUnit, or POST .../OperationalUnit/QUERY when filtered. |
deputy_list_employees | read | List employees Search employees by name, location or active status. Returns Id, DisplayName, Company (main location), Active, StartDate, Role and more. Deputy: POST /api/v1/resource/Employee/QUERY. |
deputy_get_employee | read | Get one employee Fetch one employee's details as a supervisor sees them — contact, locations, role and employment. Deputy: GET /api/v1/supervise/employee/{id}. |
deputy_list_shifts | read | List shifts Search the roster (scheduled shifts) by time window, employee, area, and published/open state. Each record has StartTime/EndTime (unix), StartTimeLocalized, Employee (0 or null when open), OperationalUnit (area), Published, Open, Cost and _DPMetaData with names. Deputy: POST /api/v1/resource/Roster/QUERY. |
deputy_get_shift | read | Get one shift Fetch one shift (Roster record) by id. Deputy: GET /api/v1/resource/Roster/{id}. |
deputy_list_timesheets | read | List timesheets Search timesheets (actual worked time) by time window, employee, area and approval state. Each record has StartTime/EndTime (unix; EndTime null while in progress), TotalTime (hours), Cost, TimeApproved, PayRuleApproved, IsInProgress, IsLeave, Roster (linked shift) and Exported. Deputy: POST /api/v1/resource/Timesheet/QUERY. |
deputy_get_timesheet | read | Get one timesheet Fetch one timesheet's full details, including breaks and approval state. Deputy: GET /api/v1/supervise/timesheet/{id}/details. |
deputy_list_leave | read | List leave requests Search leave requests by employee, location, status and time window. Status: 0 awaiting approval, 1 approved, 2 declined, 3 cancelled, 4 date approved without pay, 5 pay approved without date. Start/End are unix; LeaveRule is the leave type id. Deputy: POST /api/v1/resource/Leave/QUERY. |
deputy_get_employee_unavailability | read | Get an employee's unavailability List the times one employee has marked themselves (or been marked) unavailable to work — check before rostering them. Deputy: GET /api/v1/supervise/unavail/{employeeId}. |
deputy_query_resource | read | Query any Deputy resource Run a Resource API search on any business object (leave types, pay rules, public holidays, memos, events, shift templates, pay lines, availability, sales data, …). `search` is Deputy's clause map, e.g. {"s1":{"field":"Employee","data":12,"type":"eq"}}; operators: eq ne gt lt ge le is 'is not' in 'not in' starts contains. Use deputy_describe_resource to see an object's fields and joins. Read-only. Deputy: POST /api/v1/resource/{Object}/QUERY. |
deputy_describe_resource | read | Describe a Deputy resource Return a Resource API object's field list, field types and joinable associations — what deputy_query_resource can filter, sort and join on. Deputy: GET /api/v1/resource/{Object}/INFO. |
deputy_create_shift | write | Create a shift Add a shift to the roster, assigned to an employee or left open. Created as a DRAFT unless publish is true (publishing can notify the employee). Deputy returns an empty 200 on success — use deputy_list_shifts to find the new shift's id. Deputy: POST /api/v1/supervise/roster. |
deputy_update_shift | write | Update a shift Change an existing shift's times, area, employee, break or comment. Send the full intended shift (same fields as create) — Deputy's update is the add call with the shift id. Deputy: POST /api/v1/supervise/roster with intRosterId. |
deputy_publish_shifts | write | Publish shifts Publish draft shifts so employees see them, choosing how they are notified: 1 SMS and email, 2 SMS, 3 email, 4 no notification, 5 confirmation required. Only the listed shift ids are published. Deputy: POST /api/v1/supervise/roster/publish. |
deputy_create_leave_request | write | Create a leave request Add a leave request for an employee. By default it waits for manager approval (status 0); pass status 1 only when your system is the source of truth and the leave is already approved. Deputy tracks leave in hours, so give exact start and end times. Find leave type ids with deputy_query_resource on LeaveRules. Deputy: POST /api/v1/resource/Leave. |
deputy_add_unavailability | write | Add unavailability for an employee Record a time an employee cannot work (one-off, or recurring with an RFC 5545-style rule such as FREQ WEEKLY, INTERVAL 1, BYDAY MO). Auto-scheduling then skips them. Deputy: POST /api/v1/supervise/unavail. |
deputy_create_memo | write | Post a memo Post a memo to a location's news feed, optionally requiring staff to confirm they read it, or targeted to specific locations or users. Visible to staff immediately. Deputy: PUT /api/v1/supervise/memo. |
deputy_update_timesheet | write | Update a timesheet Correct an existing timesheet's start/end time, area, meal break or supervisor comment. Times cannot be in the future. Deputy: POST /api/v1/supervise/timesheet/update. |
deputy_approve_timesheet | write | Approve a timesheet Approve one timesheet's times as a supervisor. Approved timesheets flow toward payroll export, so check it first with deputy_get_timesheet. Deputy: POST /api/v1/supervise/timesheet/approve. |
deputy_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
deputy_request_feature | Request a missing feature Tell usefulapi that the user needs something the Deputy tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
deputy_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Deputy (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $19/month or $190/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
deputy_cancel_subscription | Cancel the Pro subscription Cancel the caller's Deputy Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run deputy_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Deputy server only. Subscribe with deputy_upgrade (it returns a Stripe Checkout link). Cancel any time with deputy_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running deputy_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Deputy. The server calls the Deputy API with your own Deputy access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Deputy install host and Permanent access token. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Deputy install host and Permanent access token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Deputy API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Deputy.
Yes, if you approve it. 8 of the 21 Deputy tools can create or change data. The other 13 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Deputy server only. Cancel any time: Pro then runs to the end of the paid period. Run deputy_usage_status to see how many calls you used.
Ask the AI to run deputy_upgrade: it returns a Stripe Checkout link. To cancel, run deputy_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with deputy_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.