Read Papershift absences, vacation, time tracking and shifts; request and review absences. 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": {
"papershift": {
"url": "https://papershift.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"papershift": {
"type": "http",
"url": "https://papershift.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 Papershift API key.
Create it in Papershift → gear icon → Account settings → API (Account Admin only; the paid Papershift API add-on must be active). New keys can read and write; edit the key's permissions to make it read-only if you only want to look things up. Your key is used only to call the Papershift API on your behalf; it is 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 Papershift API key. 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 Papershift connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
papershift_get_account | read | Get account The Papershift account this API key belongs to (id and name). A quick way to check the connection. GET /accounts. |
papershift_list_locations | read | List locations List all locations (sites/companies inside the account) with id, name and status. Most other tools need a location id from here. GET /locations. |
papershift_get_location | read | Get location One location by id. GET /locations?id=. |
papershift_list_working_areas | read | List working areas List working areas (departments/stations shifts are planned in), optionally for one location. Use the ids for shifts and time trackings. GET /working_areas. |
papershift_list_users | read | List employees List employees (users) with name, email, status, contract basics and their location, working-area and tag ids. Filter by location, working area or tag. 25 per page. GET /users. |
papershift_get_user | read | Get employee One employee by id: contact data, status, locations, working areas, tags and profile fields. GET /users?id=. |
papershift_list_tags | read | List tags List the tags of a location (labels on shifts, time trackings and employees). GET /filters. |
papershift_list_absence_types | read | List absence types List the absence types of a location (vacation, sick leave, ...) with id, title and rules. Use the ids to create absences. GET /absence_types. |
papershift_list_absences | read | List absences List absences (vacation, sick leave, ...) that fall between two dates, optionally for one employee or location. Shows type title, times, hours, vacation days and whether it is confirmed. 25 per page. GET /absences. |
papershift_get_absence | read | Get absence One absence by id, with its status, confirmation, hours and vacation days. GET /absences?id=. |
papershift_list_vacation_entitlements | read | List vacation entitlements An employee's vacation entitlements (planned days, spent days, expiry, carry-over) for the given period. Use it to answer 'how many vacation days does X have left'. 25 per page. GET /vacation_entitlements. |
papershift_list_time_trackings | read | List time trackings List worked-time entries (clock-ins) from a start date, optionally to an end date and for one employee. Shows start, end, break time, location, employee and whether confirmed. 25 per page. GET /working_sessions. |
papershift_get_time_tracking | read | Get time tracking One worked-time entry by id, with its breaks, tags and break total. GET /working_sessions?id=. |
papershift_list_evaluations | read | List evaluations (daily hours) An employee's daily evaluations: target, planned and actual hours, vacation and compensation per day. Use it for overtime and balance questions. 25 per page. GET /evaluations. |
papershift_list_target_hours | read | List target hours An employee's contractual target hours (weekly/monthly rhythm and hours per weekday) over time. 25 per page. GET /target_hours. |
papershift_list_payrolls | read | List payrolls An employee's payroll entries (paid hours, salary, bonus, time-account start/end per period). Sensitive pay data. 25 per page. GET /payrolls. |
papershift_list_shifts | read | List shifts List planned shifts of a location between two dates, optionally for one working area or tags. Shows start, end, number of employees needed, note and visibility. Assigned employees: papershift_list_shift_assignments. 25 per page. GET /shifts. |
papershift_get_shift | read | Get shift One shift by id. GET /shifts?id=. |
papershift_list_shift_assignments | read | List shift assignments Who is assigned to a shift and who has applied for it (user id and name). GET /assignments?shift_id=. |
papershift_list_availabilities | read | List availabilities The times an employee has marked as available between two dates. 25 per page. GET /availabilities. |
papershift_create_absence | write | Create absence WRITE: record an absence (vacation, sick leave, ...) for an employee. Get the absence type id from papershift_list_absence_types and the user id from papershift_list_users. Whether it counts immediately or waits for approval depends on the absence type and the account's approval rules; the employee may be notified. Papershift calculates the paid hours and vacation days. POST /absences. |
papershift_review_absence | write | Confirm, reject or reset an absence WRITE: decide on an absence request. action 'confirm' approves it (it then counts against vacation days and the plan), 'reject' declines it, 'reset' puts a decided absence back to pending. The employee is typically notified of the decision. Find ids with papershift_list_absences. PUT /absences/{confirm|reject|reset}. |
papershift_create_time_tracking | write | Create time tracking WRITE: add a worked-time entry for an employee after the fact (start, end and break minutes) in a location and working area. It changes the employee's recorded hours and balance. Ids from papershift_list_locations, papershift_list_working_areas and papershift_list_users. POST /working_sessions. |
papershift_confirm_time_tracking | write | Confirm time tracking WRITE: confirm (approve) a worked-time entry so it counts as final for payroll and balances. Find ids with papershift_list_time_trackings. PUT /working_sessions/confirm. |
papershift_create_shift | write | Create shift WRITE: plan a new shift in a location and working area for a number of employees. Set visible to true only if employees should see it right away (default: left to the account's setting). Assign people afterwards with papershift_assign_user_to_shift. POST /shifts. |
papershift_assign_user_to_shift | write | Assign employee to shift WRITE: put an employee on a shift (or, with application true, record them as having applied for it). The employee is typically notified of the assignment. An already assigned user is re-assigned. Returns the shift's assigned and applied users. POST /assignments. |
papershift_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. | |
papershift_request_feature | Request a missing feature Tell usefulapi that the user needs something the Papershift 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. | |
papershift_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Papershift (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. 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. | |
papershift_cancel_subscription | Cancel the Pro subscription Cancel the caller's Papershift 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 papershift_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 Papershift server only. Subscribe with papershift_upgrade (it returns a Stripe Checkout link). Cancel any time with papershift_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running papershift_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 Papershift. The server calls the Papershift API with your own Papershift 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 Papershift API key. See Before you connect for where to find it.
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 Papershift API key. 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 Papershift 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 Papershift.
Yes, if you approve it. 6 of the 26 Papershift tools can create or change data. The other 20 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 Papershift server only. Cancel any time: Pro then runs to the end of the paid period. Run papershift_usage_status to see how many calls you used.
Ask the AI to run papershift_upgrade: it returns a Stripe Checkout link. To cancel, run papershift_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 papershift_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.