Deputy MCP Server

Approve timesheets and leave, and roster shifts in Deputy.

Serveur MCP hébergé

npx add-mcp 'https://cotlet.dev/mcp/v1/deputy'

S’installe dans Claude Code, Codex, Cursor et plus

Documentation

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

Deputy API and MCP server

Yes, Deputy has a full REST API, but no official MCP server (checked 20 Oct 2026). Deputy says its API covers nearly all objects and actions and is included in all plans, so an agent needs your own code, an OAuth client and a token for your install.

Approve timesheets and leave, and roster shifts in Deputy. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by Deputy. Deputy is a trademark of its owner. If Deputy's own integrations cover what you need, use them first.

Workforce management app for shift businesses: rosters, timesheets, leave and team communication in one place for each location.

What is the Deputy API?

Cotlet's Deputy API exposes 12 endpoints for your own Deputy account: list locations, list employees, list shifts, list timesheets, get a timesheet, list leave requests, create a draft shift, publish draft shifts, approve a timesheet, discard a timesheet, approve a leave request and decline a leave request. The list_locations endpoint returns locations of your Deputy install with their IDs. Each endpoint takes simple JSON inputs like location_id, date_from or date_to and works both as an operation of the deputy_read or deputy_write MCP tool for agents and as a REST call for scripts.

  • Category: HR & recruiting
  • Endpoints: 12 (6 read, 6 write)
  • Updated: 2026-11-15

Yes, Deputy has a full REST API, but no official MCP server (checked 20 Oct 2026). Cotlet is a hosted MCP server and REST API for Deputy with 12 endpoints (6 read, 6 write): you sign in once in your own cloud browser, your AI agent does the work.

Does Deputy have an official API?

Yes, Deputy has a full REST API, but no official MCP server (checked 20 Oct 2026). Deputy says its API covers nearly all objects and actions and is included in all plans, so an agent needs your own code, an OAuth client and a token for your install.

TaskDeputy officialCotlet
List timesheets and read oneYes: Resource API, TimesheetYes
Approve or discard a timesheetYes: Timesheet management callsYes
List leave requestsYes: Resource API, LeaveYes
Approve or decline a leave requestYes: Update on the Leave resource; you work out the hours of each day yourselfYes
List shifts and employeesYesYes
Create a draft shift and publish rostersYes: Shifts can be draft, open or publishedYes
Use Deputy from an AI agent without codeNo: No official MCP serverYes

Sources: Deputy Developer: Getting Started with the Deputy API, Deputy Developer: Integration and Data Availability Options, Deputy Developer: Using OAuth 2.0, Deputy Developer: Timesheet Management Calls

Quick reference

Yes, Deputy has a full REST API, but no official MCP server (checked 20 Oct 2026). Deputy says its API covers nearly all objects and actions and is included in all plans, so an agent needs your own code, an OAuth client and a token for your install.
Cotlet provides a hosted MCP server and REST API for Deputy: 12 tools (6 read, 6 write).
Access       Sign up at https://cotlet.dev/app/signup?app=deputy and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    deputy_read, deputy_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/deputy, each operation at its own route, e.g. POST /api/v1/deputy/timesheets/{timesheet_id}/approve
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   list_locations, list_employees, list_shifts, list_timesheets, get_timesheet, list_leave_requests, create_shift, publish_shifts, approve_timesheet, discard_timesheet, approve_leave_request, decline_leave_request
Confirm      create_shift, publish_shifts, approve_timesheet, discard_timesheet, approve_leave_request, decline_leave_request (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/deputy-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=deputy and requests Deputy in the Cotlet console.
2. The user signs in to Deputy once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Deputy for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Deputy server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Deputy MCP server instead.

Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Deputy in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Deputy only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Deputy login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Deputy's terms; Cotlet is not affiliated with Deputy.

What can an AI agent do in Deputy?

Cotlet is best for Deputy managers who want their AI agent to approve timesheets, decide leave and draft rosters without running or fixing a server.

  • Approve timesheets in bulk (runs: daily): "List pending timesheets at Harbour Cafe, oldest first. Approve the ones that match their roster within 15 minutes, discard shifts nobody worked, and leave the rest for me with a reason." → list_timesheets, get_timesheet, approve_timesheet, discard_timesheet
  • Decide leave requests by rule (runs: daily): "Go through pending leave requests. Approve annual leave for at least 14 days ahead when no more than one person at the location is off, decline the rest with a reason and tell me which ones." → list_leave_requests, list_shifts, approve_leave_request, decline_leave_request
  • Draft next week's roster and publish it (runs: weekly): "Draft next week's shifts at Harbour Cafe like this week's, skip anyone on approved leave, show me the draft, then publish it when I say so." → list_employees, list_shifts, create_shift, publish_shifts
  • Weekly timesheet exceptions report (runs: weekly): "Every Monday, list last week's timesheets with no end time or a break shorter than rostered, by location." → list_locations, list_timesheets, get_timesheet

Can Deputy automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Deputy connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to approve timesheets in bulk, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

WhereHow to connectHow to schedule
Your AI agentAdd https://cotlet.dev/mcp/v1 with your API key.A scheduled agent run, for example a Claude Code routine.
n8nMCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/deputy/locations/{location_id}/timesheets.Schedule Trigger node.
MakeHTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH.Scenario schedule.
ZapierWebhooks by Zapier, Custom Request: the same method, URL, header and body.Schedule by Zapier trigger.
Your own scriptGET https://cotlet.dev/api/v1/deputy/locations/{location_id}/timesheets with your API key.cron or GitHub Actions.

Tools

For AI agents: Every endpoint and its schema is public. The 12 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Deputy.

list_locations

Locations of your Deputy install with their IDs. Access: read. REST: GET /api/v1/deputy/locations. MCP: deputy_read → list_locations.

No parameters.

Returns every location your account can see, with the location_id the other tools take. Run it first when the prompt names a location by its name. A location is the business site a team works at.

Example response:

{
  "locations": [
    {
      "location_id": 1,
      "name": "Harbour Cafe"
    },
    {
      "location_id": 2,
      "name": "Harbour Bakery"
    }
  ]
}

list_employees

Team members of a location with their IDs. Access: read. REST: GET /api/v1/deputy/employees. MCP: deputy_read → list_employees.

ParameterTypeRequiredDescription
location_idintegernoLocation ID from list_locations. Default: all your locations.
searchstringnoPart of the name to match.

Returns team members of one location, or of all your locations when location_id is omitted, with the employee_id other tools take. Terminated employees are left out.

Example response:

{
  "employees": [
    {
      "employee_id": 3,
      "name": "Ana Lopez",
      "location_id": 1
    },
    {
      "employee_id": 4,
      "name": "Tom Becker",
      "location_id": 1
    }
  ]
}

list_shifts

Shifts of a location between two dates, draft, open and published. Access: read. REST: GET /api/v1/deputy/locations/{location_id}/shifts. MCP: deputy_read → list_shifts.

ParameterTypeRequiredDescription
location_idintegeryesLocation ID from list_locations.
date_fromdateyesFirst day, YYYY-MM-DD.
date_todateyesLast day, YYYY-MM-DD.
employee_idintegernoOnly this employee's shifts.

Returns shifts (Deputy calls them rosters) of one location between two dates, in start order. Each shift says whether it is published, open (no employee yet) or a draft only managers see. Without dates, Deputy returns its default window around now, so pass both dates to read a week.

Example response:

{
  "shifts": [
    {
      "shift_id": 714,
      "date": "2026-10-19",
      "start": "09:00",
      "end": "17:00",
      "employee": "Ana Lopez",
      "state": "published"
    },
    {
      "shift_id": 715,
      "date": "2026-10-19",
      "start": "12:00",
      "end": "20:00",
      "employee": null,
      "state": "open"
    }
  ]
}

list_timesheets

Timesheets of a location, oldest first, pending or approved. Access: read. REST: GET /api/v1/deputy/locations/{location_id}/timesheets. MCP: deputy_read → list_timesheets.

ParameterTypeRequiredDescription
location_idintegeryesLocation ID from list_locations.
statusenumnopending (default) or approved.
date_fromdatenoFirst day, YYYY-MM-DD.
date_todatenoLast day, YYYY-MM-DD.
employee_idintegernoOnly this employee's timesheets.

Returns timesheets of one location in date order, oldest first, the order Deputy recommends for approval. status pending (default) lists those waiting for approval, approved lists the done ones. Each row has start, end and break, and a missing end time is shown as null. Pay figures need the Location Manager or System Administrator role.

Example response:

{
  "timesheets": [
    {
      "timesheet_id": 4821,
      "employee": "Ana Lopez",
      "date": "2026-10-12",
      "start": "09:00",
      "end": "17:30",
      "break_minutes": 30,
      "hours": 8,
      "status": "pending"
    },
    {
      "timesheet_id": 4822,
      "employee": "Tom Becker",
      "date": "2026-10-12",
      "start": "10:00",
      "end": null,
      "break_minutes": 0,
      "hours": null,
      "status": "pending"
    }
  ]
}

get_timesheet

One timesheet with its break, comment and the shift it belongs to. Access: read. REST: GET /api/v1/deputy/timesheets/{timesheet_id}. MCP: deputy_read → get_timesheet.

ParameterTypeRequiredDescription
timesheet_idintegeryesTimesheet ID from list_timesheets.

Returns one timesheet with its start, end, break, comment and the scheduled shift next to it, so you can compare worked and rostered time. An unsubmitted timesheet, where nobody clocked in, comes back with no start.

Example response:

{
  "timesheet_id": 4821,
  "employee": "Ana Lopez",
  "date": "2026-10-12",
  "start": "09:00",
  "end": "17:30",
  "break_minutes": 30,
  "hours": 8,
  "comment": null,
  "status": "pending",
  "rostered": {
    "start": "09:00",
    "end": "17:30"
  }
}

list_leave_requests

Pending leave requests with employee, dates, leave type and comment. Access: read. REST: GET /api/v1/deputy/leave-requests. MCP: deputy_read → list_leave_requests.

ParameterTypeRequiredDescription
location_idintegernoLocation ID from list_locations. Default: all your locations.
statusenumnopending (default), approved or declined.

Returns leave requests waiting for a decision, oldest first, with the employee, the first and last day, the leave type the employee picked and their comment. The leave type is only a suggestion. status approved or declined lists decided requests instead.

Example response:

{
  "leave_requests": [
    {
      "leave_id": 311,
      "employee": "Tom Becker",
      "date_start": "2026-11-03",
      "date_end": "2026-11-04",
      "leave_type": "Annual leave",
      "comment": "Family trip",
      "status": "pending"
    }
  ]
}

create_shift

Add a shift to a location as a draft that only managers see. Access: write, asks the user first. REST: POST /api/v1/deputy/locations/{location_id}/shifts. MCP: deputy_write → create_shift.

ParameterTypeRequiredDescription
location_idintegeryesLocation ID from list_locations.
datedateyesDay of the shift, YYYY-MM-DD.
startstringyesStart time, HH:MM.
endstringyesEnd time, HH:MM.
employee_idintegernoEmployee ID from list_employees. Default: open shift.

Adds one shift as a draft, so it shows to managers and not to the team until publish_shifts runs. Leave employee_id out to create an open shift. Returns the shift_id. It never notifies anyone. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "shift_id": 733,
  "date": "2026-10-26",
  "start": "09:00",
  "end": "17:00",
  "employee": "Ana Lopez",
  "state": "draft"
}

publish_shifts

Publish the draft shifts of a location between two dates to the team. Access: write, asks the user first. REST: POST /api/v1/deputy/locations/{location_id}/shifts/publish. MCP: deputy_write → publish_shifts.

ParameterTypeRequiredDescription
location_idintegeryesLocation ID from list_locations.
date_fromdateyesFirst day, YYYY-MM-DD.
date_todateyesLast day, YYYY-MM-DD.

Publishes every draft shift of one location between two dates, so the team sees them. Returns how many were published. Employees may be notified by Deputy, so it waits for you. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "published": 12,
  "location_id": 1,
  "date_from": "2026-10-26",
  "date_to": "2026-11-01"
}

approve_timesheet

Approve one pending timesheet. Access: write, asks the user first. REST: POST /api/v1/deputy/timesheets/{timesheet_id}/approve. MCP: deputy_write → approve_timesheet.

ParameterTypeRequiredDescription
timesheet_idintegeryesTimesheet ID from list_timesheets.

Approves one pending timesheet, which then follows Deputy's payment workflow. Needs the Location Manager or System Administrator role for the pay part. A timesheet with no end time is refused; fix it in Deputy first. Cotlet has no unapprove tool, because Deputy unapproves only in its web app. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "timesheet_id": 4821,
  "employee": "Ana Lopez",
  "date": "2026-10-12",
  "start": "09:00",
  "end": "17:30",
  "break_minutes": 30,
  "hours": 8,
  "status": "approved"
}

discard_timesheet

Discard a timesheet for a shift that was not worked. Access: write, asks the user first. REST: POST /api/v1/deputy/timesheets/{timesheet_id}/discard. MCP: deputy_write → discard_timesheet.

ParameterTypeRequiredDescription
timesheet_idintegeryesTimesheet ID from list_timesheets.

Discards one timesheet, for example an unsubmitted one where the shift was not worked. The employee's pay for that shift is not created. It affects pay, so it waits for you. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "timesheet_id": 4830,
  "employee": "Sam Okafor",
  "date": "2026-10-11",
  "status": "discarded"
}

approve_leave_request

Approve a pending leave request and set the hours of each day. Access: write, asks the user first. REST: POST /api/v1/deputy/leaves/{leave_id}/request/approve. MCP: deputy_write → approve_leave_request.

ParameterTypeRequiredDescription
leave_idintegeryesLeave ID from list_leave_requests.
day_typeenumyesstandard_hours, scheduled_hours or non_working_day, applied to every day of the request.
leave_typestringnoLeave type name as shown in Deputy. Default: the type the employee picked.
commentstringnoComment the employee sees.

Approves one leave request. day_type sets every day: standard_hours, scheduled_hours or non_working_day, matching Deputy's Standard hours, Scheduled hours and Non-working day. leave_type changes the type the employee suggested. For past dates Deputy creates the timesheets at once, for future dates as each day passes. The employee is told. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "leave_id": 311,
  "employee": "Tom Becker",
  "status": "approved",
  "leave_type": "Annual leave",
  "day_type": "standard_hours",
  "days": [
    "2026-11-03",
    "2026-11-04"
  ],
  "comment": "Approved, enjoy the break."
}

decline_leave_request

Decline a pending leave request with a reason. Access: write, asks the user first. REST: POST /api/v1/deputy/leaves/{leave_id}/request/decline. MCP: deputy_write → decline_leave_request.

ParameterTypeRequiredDescription
leave_idintegeryesLeave ID from list_leave_requests.
commentstringyesReason the employee sees.

Declines one leave request. The comment is required, because Deputy requires one to decline, and the employee reads it. The decision reaches the employee, so it waits for you. By default you confirm each call; you can switch that off for this tool.

Example response:

{
  "leave_id": 312,
  "employee": "Ana Lopez",
  "status": "declined",
  "comment": "Two others are off on Nov 10. Could you move it by a day?"
}

How do I connect Deputy to ChatGPT, Claude, Cursor or Codex?

Connecting Deputy takes three steps: sign up, sign in to Deputy once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.

Connect Deputy to your agent.

  1. Create an account Sign up and add Deputy in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.

  2. Sign in to Deputy in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Deputy there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

  3. Add Cotlet to ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

    ChatGPT:

Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth

Claude:

Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:

claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"

Cursor:

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
  1. Ask your agent Ask in plain words. Your agent finds the Deputy tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.
List pending timesheets at Harbour Cafe, oldest first. Approve the ones that match their roster within 15 minutes, discard shifts nobody worked, and leave the rest for me with a reason.

Call Deputy from your scripts.

  1. Export your API key Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.
export COTLET_API_KEY="cotlet_..."
  1. Call a tool Every tool is an endpoint under /api/v1/deputy with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.
curl -X POST https://cotlet.dev/api/v1/deputy/timesheets/4821/approve \
  -H "Authorization: Bearer $COTLET_API_KEY"
  1. Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
  "timesheet_id": 4821,
  "employee": "Ana Lopez",
  "date": "2026-10-12",
  "start": "09:00",
  "end": "17:30",
  "break_minutes": 30,
  "hours": 8,
  "status": "approved"
}

How to use the Deputy REST API

Create your Cotlet API key

Create a Cotlet API key with access to Deputy and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect Deputy in Cotlet and enable it for agents. Account access: Your own Deputy account (Location Manager or System Administrator to approve time and pay, Supervisor for the time part only).

Make your first Deputy API request

REST:

curl https://cotlet.dev/api/v1/deputy/locations \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read locations and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "deputy",
  "tool": "list_locations",
  "result": {
    "locations": [
      {
        "location_id": 1,
        "name": "Harbour Cafe"
      },
      {
        "location_id": 2,
        "name": "Harbour Bakery"
      }
    ]
  }
}

Returns every location your account can see, with the location_id the other tools take. Run it first when the prompt names a location by its name.

A location is the business site a team works at.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

Deputy workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestTimesheets of a location, oldest first, pending or approved. Use list_timesheets in your configured team report.
MakeHTTP > Make a requestPending leave requests with employee, dates, leave type and comment. Use list_leave_requests in your configured team report.
Python or Node.jsREST APIShifts of a location between two dates, draft, open and published. Use list_shifts in your configured team report.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads Deputy; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

Why use Cotlet for Deputy?

Built for agents

  • One MCP server for every app you connect.
  • The same tools as a REST API for scripts and cron jobs.
  • Works with ChatGPT, Claude, Claude Code, Codex and Cursor.

Your login stays yours

  • You sign in to Deputy yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
  • A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
  • The model never sees a login.
  • No stored passwords, no MFA bypass.

You stay in control

  • Scope each API key: its apps, its tools, read only or read and write.
  • Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
  • Every background request listed in your Background activity. Disable for agents in one click.

Kept working for you

  • We test every integration every 6 hours.
  • When Deputy changes, the tool pauses until we fix it.
  • Failed calls cost nothing.

Is it safe to connect Deputy to Cotlet?

Yes. You sign in to Deputy yourself, in your own Cloud Browser, and we never save your password. Your agents only get Deputy once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

  • A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
  • A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
  • A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
  • Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result

How Cotlet protects your access

Common concerns

Who runs Cotlet?

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

Is this an official Deputy integration?

No, Cotlet is independent of Deputy. Deputy's own API is too limited for this work. Cotlet works through your own Deputy account, the way you use Deputy in the browser.

What about client data and GDPR?

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

Can I start with read only?

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

Is it reliable?

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

How do I stop?

Press Disable for agents next to Deputy in your console: your agents lose access at once and you stay signed in. Signing out of Deputy in the browser works too, and Reset browser deletes the whole profile.

Is there a Deputy MCP server on GitHub?

Yes. Community Deputy MCP servers exist on GitHub, some of them read-only, usually maintained by one person. You install one on your own computer, give it a token and keep it running yourself; when the API or your install changes, you or the maintainer fix it. Cotlet hosts the same kind of server for you, and our team keeps it working.

GitHub MCP serverCotlet
SetupClone the repo, install it, create an OAuth client and token in Deputy, add it to each MCP clientSign up, sign in to Deputy once, add one MCP server or API key
When Deputy changesIt breaks until you or the maintainer fix itOur team runs automatic checks and fixes it for you
Your Deputy sessionA token in a file on your computer, readable by any program you runIn your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click
When the session expiresTools fail until you refresh the token or sign in again by handYour Cloud Browser keeps you signed in; if Deputy logs you out, your agent gets a link to sign in again
UpkeepYou update, monitor and debug it yourselfNothing to host or update
Where it runsYour computer, while it is onHosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule
PriceFree, paid for with your timeFree 7-day trial, then pay-as-you-go credit packs, no subscription

Which one fits you

Pick Cotlet if

  • you are not a developer, or you do not want to maintain a server
  • you need it to keep working when Deputy changes, without checking it yourself
  • your agent or a script should run it on a schedule, also while your computer is off

Pick an open-source server if

  • you are comfortable installing, updating and fixing it yourself
  • you want your sign-in to stay on your own computer
  • you only need it now and then, from one MCP client

How much does the Deputy API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Deputy API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

CreditsPrice, one timeCalls at 10 creditsPer 1,000 credits
5,000$29500$5.80
15,000$791,500$5.27
32,000$1493,200$4.66
60,000$2496,000$4.15

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing

How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Deputy account.

  • Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
  • Your sign-in: You sign in to Deputy yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Deputy only after you enable it. When Deputy signs you out, your agent gives you a link to sign in again. Security
  • Revoking access: Press Disable for agents next to Deputy, sign out of Deputy in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
  • What we never do: Store passwords or bypass MFA.
  • Deputy's terms: You use your own Deputy account and stay responsible for following Deputy's terms. Cotlet is independent and not affiliated with Deputy. Terms
  • Contact: Questions about the company, security or an app: contact@cotlet.dev

Also listed on: Odel, mcpbeat

Deputy API and MCP: questions

How do I get access?

Sign up free, open Deputy in the console and press Activate. Then you create your API key and connect Deputy there.

Do I need to be technical?

No. You sign in to Deputy once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

Is it safe to connect Deputy to Cotlet?

Yes. You sign in to Deputy yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Deputy once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

Is a hosted server safer than a local one? My Deputy sign-in would leave my computer.

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Deputy cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

Why does Cotlet send requests instead of clicking in my browser?

To be fast, Cotlet doesn't click through Deputy's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Deputy sees the same browser and IP you signed in with, and every request is listed in your Background activity.

What if someone gets my Cotlet API key?

The key holds no Deputy login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

Why a signed-in browser and not OAuth, like other integration platforms?

Deputy offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

How do I connect Deputy to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Deputy once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Deputy account through Cotlet, in their phone apps too.

What can ChatGPT do in Deputy?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Deputy: approve timesheets in bulk; decide leave requests by rule; draft next week. You ask in plain words, and anything that reaches other people waits for your OK first.

Which Deputy role does my agent need?

Deputy lets Location Managers and System Administrators approve both the time and pay part of a timesheet, and Supervisors only the time part. Leave is decided by a Location Manager or System Administrator. Your agent works with the role of the account you sign in with, so use a manager account for approvals.

Can my agent undo an approved timesheet?

No. Deputy unapproves a timesheet only in its web app, and Cotlet has no tool for it. Approvals wait for your OK by default, so check the list before you confirm.

Can my agent post or send messages in Deputy without asking me?

No. Every call to create_shift, publish_shifts, approve_timesheet, discard_timesheet, approve_leave_request or decline_leave_request waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals.

Can I use the Deputy API in n8n?

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/deputy from the HTTP Request node.

Can I use the Deputy API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.


Give your AI agents your signed-in browser.

Product: Integrations · How it works · Pricing · Security

Resources: Blog · API docs · Help center · Changelog · GitHub

Solutions: For developers · For automation agencies

Company: About · AI info: company facts · Contact

Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors

Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.