FitSW MCP server Let your AI agent do the FitSW admin.

Your AI agent onboards clients with a program, builds workouts from your notes, logs in-person results and spots who is falling behind. Sign in to FitSW once in your own Cloud Browser. No API, no Zapier.

  • Free 7-day trial, no card
  • Unofficial, not affiliated with FitSW
FitSW logo FitSW Cloud Browser

7 tools Read and write

Note to program

What can your AI agent do in FitSW? The admin around the training.

  • Onboard new clients

  • Assign programs

  • Build workouts from notes

  • Log in-person results

  • Spot low compliance

  • Weekly progress reports

No public API

Does FitSW have an MCP server or an API? No public API, no Zapier, and no MCP server.

FitSW has no MCP server, no ChatGPT or Claude app, no public API and no Zapier app (checked 9 Nov 2026). Cotlet runs 7 FitSW tools hosted, over MCP for agents and REST for scripts, in your own FitSW login.

  • FitSW has no API, webhook or developer page.
  • FitSW has no Zapier app.
  • FitSW has no connector in the ChatGPT apps directory or in Claude.
The FitSW API, other options and Cotlet compared
What you need FitSW APIBy handCotlet
Clients and progress No API Yes, one by one Yes
Assign programs No API Yes, one by one Yes, after your OK
Compliance across clients No API Client by client Yes
Ask in ChatGPT or Claude No No Yes
Zapier app None None Not needed

Checked 8 Nov 2026. Sources: FitSW FAQ · FitSW help for trainers · FitSW help: create a multi-day program (web)

Set up once

How does the FitSW MCP server work? Your agent works in your own FitSW login.

  1. 1Sign in to FitSW

    Once, in a browser we host for you.

  2. 2Connect your AI agent

    One address in its settings.

  3. 3Hand it the busywork

    It drafts the work, you OK what customers get.

We never keep your FitSW password, and nothing a client sees in their app changes until you approve it. Who can see your session

Any MCP client

How to connect FitSW to your AI agent

  1. 1

    Sign in to FitSW in a Cloud Browser. Create a Cotlet account, open FitSW in its Cloud Browser, sign in with your trainer login and press Enable for agents.

  2. 2

    Add the Cotlet address. Enter https://cotlet.dev/mcp/v1 as the MCP server or connector URL in your agent.

  3. 3

    Let the agent in. Chat apps open a Cotlet sign-in page. Editors, n8n and scripts send an API key made in the console.

FitSW shares the address https://cotlet.dev/mcp/v1 with every other app you enable, so one connector covers them all. Turned FitSW on after connecting? Refresh the connector and the 7 tools appear.

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"
ChatGPT
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Cursor
// ~/.cursor/mcp.json
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}
Codex
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
n8n
MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: fitsw_read
Make, Zapier
Make: MCP Client > Call a tool
Zapier: MCP Client by Zapier > Run Tool
Server URL: https://cotlet.dev/mcp/v1
Token: <your key>
Tool: fitsw_write
3 read, 4 write

All 7 FitSW MCP tools

Clients3

Search by name; compliance and results come with each client. Adding a client sends their invite, so it waits for your OK.

  • list_clients Clients, searchable by name, with program and compliance. read

    Returns clients with ID, current program, compliance for the last 7 days and last workout.

    MCP callfitsw_read → list_clients

    REST endpointGET https://cotlet.dev/api/v1/fitsw/clients

    Parameters

    Parameters: list_clients
    NameTypeDescription
    query string string Name or email.
    max_compliance integer integer Only clients at or below this compliance percent.
    page integer integer Page number. Default: 1.

    Example response

    {
      "clients": [
        {
          "client_id": "U-31877",
          "name": "Marcus Reed",
          "program": "Hypertrophy 4-day",
          "compliance_7d": "50%",
          "last_workout": "2026-11-05"
        }
      ],
      "page": 1
    }
  • get_client One client with workouts, results, metrics and nutrition. read

    Returns the client's scheduled and completed workouts, recent results, metrics such as weight, and nutrition plan.

    MCP callfitsw_read → get_client

    REST endpointGET https://cotlet.dev/api/v1/fitsw/clients/{client_id}

    Parameters

    Parameters: get_client
    NameTypeDescription
    client_id string required string Client ID from list_clients.

    Example input

    {
      "client_id": "client_8c41d2"
    }

    Example response

    {
      "client_id": "U-31877",
      "name": "Marcus Reed",
      "completed": [
        {
          "workout": "Upper A",
          "date": "2026-11-05"
        }
      ],
      "missed": [
        {
          "workout": "Lower A",
          "date": "2026-11-07"
        }
      ],
      "weight_kg": 84.1,
      "nutrition": "2,600 kcal"
    }
  • add_client Adds a client and invites them to the app. writeasks first

    Creates the client the way Add Client on the web does; FitSW emails their free login. By default you confirm each call; you can switch that off for this tool.

    MCP callfitsw_write → add_client

    REST endpointPOST https://cotlet.dev/api/v1/fitsw/clients

    Parameters

    Parameters: add_client
    NameTypeDescription
    first_name string required string First name.
    last_name string required string Last name.
    email string required string Email for the invite.

    Example input

    {
      "first_name": "first name",
      "last_name": "last name",
      "email": "jane@example.com"
    }

    Example response

    {
      "client_id": "U-31940",
      "name": "Olivia Hartmann",
      "status": "Invited"
    }

Workouts and programs4

New workouts sit in your library and logged results reach no one, so both run at once. Assigning waits for your OK.

  • list_programs Your workouts and multi-day programs. read

    Returns workouts and programs by name and length, so the agent assigns the exact one.

    MCP callfitsw_read → list_programs

    REST endpointGET https://cotlet.dev/api/v1/fitsw/programs

    Parameters

    Parameters: list_programs
    NameTypeDescription
    query string string Name contains.

    Example response

    {
      "programs": [
        {
          "name": "Hypertrophy 4-day",
          "days": 28
        },
        {
          "name": "Beginner full body",
          "days": 21
        }
      ]
    }
  • create_workout Builds a workout in your library from exercises, sets and reps. write

    Creates the workout with exercises from the FitSW exercise list. It sits in your library until assigned, so it runs at once.

    MCP callfitsw_write → create_workout

    REST endpointPOST https://cotlet.dev/api/v1/fitsw/workouts

    Parameters

    Parameters: create_workout
    NameTypeDescription
    name string required string Workout name.
    exercises array required array Exercise name, sets, reps or time, rest.

    Example input

    {
      "name": "Jane Doe",
      "exercises": "exercises"
    }

    Example response

    {
      "workout_id": "W-8812",
      "name": "Lower B, knee friendly",
      "exercises": 6
    }
  • assign_program Assigns a workout or program to a client from a start date. writeasks first

    Schedules the workout or program on the client's calendar; they see it in their app. By default you confirm each call; you can switch that off for this tool.

    MCP callfitsw_write → assign_program

    REST endpointPOST https://cotlet.dev/api/v1/fitsw/clients/{client_id}/program/assign

    Parameters

    Parameters: assign_program
    NameTypeDescription
    client_id string required string Client ID from list_clients.
    program string required string Workout or program name.
    start string required string ISO start date.

    Example input

    {
      "client_id": "U-31940",
      "program": "Beginner full body",
      "start": "2026-11-16"
    }

    Example response

    {
      "client_id": "U-31940",
      "program": "Beginner full body",
      "start": "2026-11-16"
    }
  • record_result Enters a client's results for a session you trained in person. write

    Logs weights, reps or times for the workout, the way Enter Results does. Reaches no one, so it runs at once.

    MCP callfitsw_write → record_result

    REST endpointPOST https://cotlet.dev/api/v1/fitsw/clients/{client_id}/results

    Parameters

    Parameters: record_result
    NameTypeDescription
    client_id string required string Client ID from list_clients.
    workout string required string Workout name.
    results array required array Exercise, set, weight, reps.

    Example input

    {
      "client_id": "client_8c41d2",
      "workout": "workout",
      "results": "results"
    }

    Example response

    {
      "client_id": "U-31877",
      "workout": "Upper A",
      "date": "2026-11-09",
      "logged_sets": 15
    }
Encrypted, revocable

Who can see my FitSW session, and how do I revoke it?

  • What we store

    Your signed-in FitSW profile, AES-256-GCM encrypted, in Finland. No password.

  • What your agent gets

    The 7 FitSW tools, never the session cookie.

  • What the session sees

    What your trainer login sees: clients, workouts, programs, results, nutrition.

  • What no tool touches

    Payments, subscriptions, messages, client documents, deletes.

  • If FitSW signs you out

    You sign in again yourself, in the same Cloud Browser.

  • How to cut access

    Disable for agents, reset the browser, or change your FitSW password.

Cotlet never types your password: you sign in yourself, and the agent only uses the session. Our site scores A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).

Tested every 12 h

What happens when FitSW changes? We repair the tool; your prompts stay the same.

between tests of the FitSW reads
12 h
between tests of sends a customer would notice
24 h
for a call to a FitSW tool paused for repair
$0

When FitSW moves a button in the client view or renames a section, we fix the tool and your agent calls it the same way. status.cotlet.dev checks the site, console and API every 3 minutes.

2 tools ask first

Approvals, undo and mistakes Customers get nothing until you say so.

  1. 01 Reads the week Completed and missed workouts per client.
  2. 02 Works out compliance Against the threshold you set.
  3. 03 Lists who is behind With the sessions they missed.
  4. 04 Leaves the message to you Nothing is sent to clients.
Which FitSW actions can be undone
ActionUndo
Add a clientYes, archive them; the invite stays sent
Assign a programYes, remove it from the calendar
Build a workout or log resultsYes, edit it in FitSW

2 of 7 tools ask first: add_client, assign_program. New workouts and logged results reach no customer, so they run at once. You can turn the wait off per tool once you trust a routine.

MCP call
{
  "name": "assign_program",
  "arguments": {
    "client_id": "U-31940",
    "program": "Beginner full body",
    "start": "2026-11-16"
  }
}
REST
curl -X POST https://cotlet.dev/api/v1/fitsw/clients/U-31940/program/assign \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"program":"Beginner full body","start":"2026-11-16"}'
Response
{
  "client_id": "U-31940",
  "program": "Beginner full body",
  "start": "2026-11-16"
}

A cron job or n8n flow can call the same tools over REST at /api/v1/fitsw with the same key and price, in JSON. Failed calls are free. Each tool row above shows its REST path.

Pay per call

How much does the FitSW MCP server cost?

About $23 a monthfor a trainer with about 30 clients, 4,030 credits. Your FitSW plan stays as it is.

A month of FitSW admin for a 30-client trainer, in credits
JobCallsCredits
New client onboarded3 × 5150
Compliance check, weekly12 × 4480
Workout built1 × 10100
In-person results logged2 × 601,200
Progress report, weekly15 × 4600
Cloud Browser, 30 days1,500
Total4,030
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • Works on your current FitSW plan

FitSW publishes no usage counts, so the month is our example. Dollars at the $29 pack rate.

Cotlet credit packs: price, credits and calls at 10 credits each
Credits Price, one time Calls at 10 credits Per 1,000 credits
5,000 $29 500 $5.80
15,000 $79 1,500 $5.27
32,000 $149 3,200 $4.66
60,000 $249 6,000 $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.

Other options

FitSW MCP server on GitHub, Zapier or hosted: which to use No API and no Zapier.

Other ways to connect FitSW, checked 8 Nov 2026
OptionWhat it doesWhere it stops
FitSW appClients, programs and results on your phone.One client at a time; no questions in plain words.
Spreadsheet exportCopy results out to analyse them yourself.By hand, every week.
By handEvery screen of FitSW, one client at a time.Your time between sessions.

FitSW has no API or Zapier app, so there is nothing to connect a script to. To onboard, build and track from ChatGPT or Claude this week, Cotlet works in the FitSW account you already have.

EU company, since 2019

Who runs Cotlet A company you can look up.

Take Group sp. z o.o. runs Cotlet. It is a software company registered in Poland, EU (VAT PL6342984273), in business since 2019, led by its founders Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Questions about the FitSW tools go to contact@cotlet.dev.

FitSW MCP server: questions

How do I get access?

Sign up free at https://cotlet.dev, open FitSW under Integrations in the console and sign in to FitSW in its Cloud Browser. The trial starts with your first app and asks for no card.

How do I connect FitSW to ChatGPT or Claude?

Sign up at cotlet.dev, log in to FitSW 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 FitSW account through Cotlet, in their phone apps too.

What can ChatGPT do in FitSW?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in FitSW: onboard a new client; spot low compliance; build a workout from a note. You ask in plain words, and anything that reaches other people waits for your OK first.

Is there an official ChatGPT or Claude app for FitSW?

No. FitSW has no ChatGPT or Claude connector of its own and FitSW has no official MCP server (checked 9 Nov 2026). Cotlet is an independent one that works in ChatGPT, Claude, Cursor and any MCP client, on your signed-in account.

Can ChatGPT assign workouts in FitSW?

Yes, with Cotlet. ChatGPT assigns a workout or multi-day program from your library to a client from the date you give, after your OK.

Can ChatGPT check client compliance in FitSW?

Yes, with Cotlet. ChatGPT lists clients below the compliance you set and the workouts they missed, so you know whom to message.

Can ChatGPT build workouts in FitSW?

Yes, with Cotlet. ChatGPT builds a workout from your note with exercises from the FitSW list, sets, reps and rest, and saves it to your library.

Do my clients need to do anything?

No. Clients keep their FitSW app and free login. What your agent assigns shows up in their app as usual.

Is the MCP server different from the REST API?

Only in how it is called. Both carry the same 7 tools, inputs, answers, API key and price. Agents use MCP; scripts and HTTP steps use REST.

Is Cotlet affiliated with FitSW?

No. Cotlet is independent and not affiliated with FitSW.

Hand the FitSW admin to your agent.

Free 7-day trial with 2,000 credits, no card needed.