Everfit MCP Server

Clients, programs and messages for your Everfit coaching business.

Hosted MCP Server

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

Installs into Claude Code, Codex, Cursor and more

Documentation

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

Everfit API and MCP server: Let your AI agent run your Everfit check-ins.

Everfit has no MCP server and no public API (checked 24 Oct 2026). Its API is for Enterprise customers, the 500+ client plan, who ask enterprise@everfit.io for a token. Cotlet runs 23 Everfit tools hosted, over MCP for agents and REST for scripts.

Bring Everfit client progress and coaching activity into your AI agent or reporting workflow. Use MCP, REST, n8n, Make or your own script.

MCP setup REST API guide

Free 7-day trial, no card
Unofficial, not affiliated with Everfit
Page: https://cotlet.dev/integrations/everfit-api-mcp-server

What can you automate in Everfit?

Check in on quiet clients
Draft Inbox replies
Report weight and waist trends
Assign weigh-in tasks
Invite and archive clients
Assign the next program

Does Everfit have an MCP server or an API?

The Enterprise API has 11 endpoint groups (clients, programs, Autoflows, collections, forums, recipe books) and 2 webhooks, client connected and client opened the app. Nothing for Inbox, body metrics, tasks or logged workouts.
Zapier is a paid plugin on Studio, from $19 a month for 1,000 tasks: 1 trigger and 31 actions with the same reach as the API. Zapier MCP exposes those actions; there is no Make app and no n8n node.
Olly, Everfit's own assistant (Beta), drafts messages and tasks inside Everfit, where you still press Send. Your own agent cannot reach it.

What you need	Everfit + Zapier (Studio)	Everfit Enterprise API	Cotlet
Invite clients and assign programs	Yes	Yes	Yes, after your OK
Read and send Inbox messages	No	No	Yes
Body metrics and logged workouts	No	No	Yes, read and log
Tasks with a reminder time	No	No	Yes
Works on Starter or Pro	Studio only	Enterprise only	Yes
Fixed for you when Everfit changes	Yes	Yes	Yes, tested every 12 h

Checked 24 Oct 2026. Sources: Everfit API Integration Guide, Everfit Zapier Integration, Everfit Zapier Integration Pricing, Everfit pricing, Zapier MCP for Everfit

How does Cotlet connect to Everfit?

Sign in to Everfit. Use your own account in its Cotlet Cloud Browser.
Choose MCP or REST. Connect your agent or create a Cotlet API key.
Run your workflow. Ask your agent or send an HTTP request.

We never save your Everfit password, and no message, task or invite reaches a client without your OK.

Connect Everfit to your agent or workflow

Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide.

Turn Everfit on for agents. Sign up, log in to your Everfit coach account in its Cloud Browser and press Enable for agents.
Give your agent the address. Put https://cotlet.dev/mcp/v1/everfit in the MCP or connector settings of your agent.
Sign in or use a key. Chat apps sign you in to Cotlet; editors and scripts take an API key from the console.

https://cotlet.dev/mcp/v1 also works and serves every app you enable. Enabled Everfit after you connected? Refresh the connector in your agent.

Claude:

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

Claude Code:
claude mcp add --transport http cotlet-everfit \
  https://cotlet.dev/mcp/v1/everfit \
  --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-everfit": {
      "url": "https://cotlet.dev/mcp/v1/everfit",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet-everfit]
url = "https://cotlet.dev/mcp/v1/everfit"
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: everfit_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: everfit_write

How to use the Everfit REST API

Create your Cotlet API key

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

Sign in to your Everfit coach account in its Cotlet Cloud Browser and enable the app for agents. Your account permissions and Everfit plan still apply.

Make your first Everfit API request

REST:

curl "https://cotlet.dev/api/v1/everfit/clients?status=active&limit=2" \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read coaching clients and continue the list

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": "everfit",
  "tool": "list_clients",
  "result": {
    "clients": [
      {
        "client_id": "66f1c2a9e4b0a1d2c3f4e5a6",
        "first_name": "Sam",
        "last_name": "Rivera",
        "email": "sam@example.com",
        "type": "online",
        "connection": "connected",
        "archived": false,
        "coach": "Jordan Lee",
        "groups": [],
        "joined_at": "2026-09-15T10:12:00.000Z",
        "last_activity": "2026-10-26T00:00:00.000Z",
        "workouts_30d": {
          "completed": 4,
          "assigned": 5
        },
        "workouts_7d": {
          "completed": 2,
          "assigned": 3
        },
        "tasks_7d": {
          "completed": 1,
          "assigned": 1
        }
      }
    ],
    "total": 1,
    "next_cursor": null
  }
}

Read result.clients and pass result.next_cursor unchanged as cursor until null. Keep the same status, search and limit while paging.

Client pages default to 50 records, with a maximum of 100. Active clients are the default; use a separate archived traversal when your report needs archived clients.

Compare workout counts and current client state as well as client IDs. For inbox summaries, get_conversation returns only the latest messages, at most 200, rather than the complete thread history.

Everfit workflows for agents and automations

Tool	Connect through	Example workflow
n8n	HTTP Request	Combine clients, workouts and workout logs into a weekly report of incomplete sessions in your chosen sheet.
Python or Node.js	REST API	Read body-metric definitions and dated measurements to prepare a progress review with the original units.
Make	HTTP > Make a request	Read conversations and recent messages into a private coaching reply queue without sending replies.

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

Cotlet reads Everfit; 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.

Everfit API endpoints and MCP tools

Clients and programs

Active or archived clients with their coach, groups and workouts completed against assigned. In a team workspace, owners and admins can give a new client to another coach.

List clients (list_clients, read): Clients with type, connection, coach, groups and recent workout completion.
Get client (get_client, read): Client overview: profile, goal, private note, workouts tracked and assigned programs.
Invite client (invite_client, write, asks first): Add a client and, by default, email them Everfit's invitation.
Archive client (archive_client, write): Archive a client: they leave the active client list.
Unarchive client (unarchive_client, write): Bring an archived client back to the active list.
List programs (list_programs, read): Programs in your Program Library with weeks and workout counts.
Get program (get_program, read): A program with its weeks, workout days and workouts.
Assign program (assign_program, write, asks first): Put a program from your Program Library on a client's training calendar.

Workouts, tasks and habits

A client's calendar and the sets they logged. Tasks and habits remind the client at the time you set. Habits need the Pro plan.

List workouts (list_workouts, read): Workouts on a client's training calendar in a date range, with completion.
Get workout log (get_workout_log, read): One workout on a client's calendar with the sets the client logged.
List workout library (list_workout_library, read): Workouts saved in your Workouts library, to assign to a client's day.
Assign workout (assign_workout, write, asks first): Put a workout from your Workouts library on a client's calendar day.
List tasks (list_tasks, read): Tasks on a client's calendar in a date range, with status.
Add task (add_task, write, asks first): Add a task with optional instructions and reminder to a client's calendar day.
List habits (list_habits, read): A client's active habits with goal, unit and frequency.
Add habit (add_habit, write, asks first): Prescribe a habit with a daily or weekly goal to a client.

Body metrics

Only metrics enabled for that client. Entries come in the unit they were stored in, each with its unit.

List body metrics (list_body_metrics, read): Body metrics enabled for a client, with unit and latest entry.
Get body metrics (get_body_metrics, read): Entries of one body metric for a client in a date range, with the change.
Log body metric (log_body_metric, write): Save a result for one body metric of a client.
Delete body metric entry (delete_body_metric_entry, write): Remove one body metric entry of a client.

Inbox

Direct chats with clients. A client who never joined the app cannot be messaged.

List conversations (list_conversations, read): Your Inbox conversations, newest first, with the last message and unread count.
Get conversation (get_conversation, read): The latest messages of your Inbox conversation with one client, oldest first.
Send message (send_message, write, asks first): Send a text message to one client in Inbox, under your name.

Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/everfit-api-mcp-server#tools

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

What we store. Your logged-in Everfit profile, AES-256-GCM, in Finland. Not your password.
What your agent gets. Everfit tools only. No cookie, no login.
What the session sees. What your coach login sees: clients, their goals and private notes, your Inbox.
What no tool touches. Payments and packages, billing, team settings and your password.
If Everfit logs you out. You get an email with a sign-in link. We never log in for you.
How to cut access. Disable for agents, reset the browser or delete the key. The next call stops.

A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results). No SOC 2 report or third-party pentest yet.

Is it against Everfit's terms? Account safety

Use any robot, spider, or other automatic device, process, or means to access the Website for any purpose, including monitoring or copying any of the material on the Website.

Everfit Terms of Service, 26 Nov 2024

The same list lets Everfit suspend access "for any or no reason". It applies to every Everfit tool without the Enterprise API, the client-side GitHub server included. We found no public case of a coach account closed for automation (checked 24 Oct 2026).

How we keep your account looking like you:

Your own coach account, logged in by you
One Cloud Browser with its own IP and cookies
Messages, tasks, programs, habits and invites wait for your OK
You finish sign-in and 2FA yourself
Should Everfit object, we pause Everfit for every user within 24 h

invite_client with send_invite off adds an offline client and mails nobody.

What happens when Everfit changes?

12 h between tests of every Everfit tool
24 h between tests of writes a client would see
37/37 checks passed on Nov 6, 2026
$0 for calls to a tool paused for a fix

Everfit ships features every month (March 2026: Response Comparison, a barcode scanner, an AI push-up challenge) and runs Olly and the Check-in Dashboard as Betas. Screens that move that often are why the tests exist. status.cotlet.dev checks the site, console and API every 3 minutes.

Approvals, undo and mistakes

Builds the roster. Active clients, your own in a team workspace.
Splits quiet from unplanned. Workouts planned but none tracked, or nothing on the calendar.
Waits for your OK. Each check-in shows up in your Cotlet console.
Reports back. Sent, held, and who needs a new program.

Action	Undo
Send a message	Edit plain text within 60 minutes, in Everfit
Invite a client	No, the email goes out at once; archive the client
Assign a program or workout	Yes, remove it in Everfit
Add a task or habit	Yes, remove it in Everfit
Archive a client	Yes, unarchive_client
Log a body metric	Yes, delete_body_metric_entry

6 of 23 tools ask first: every write that reaches a client as a message, push reminder, calendar change or email. For a scheduled run, turn the wait off per tool, or enable Everfit read only.

Reads never ask: clients, workouts, metrics, chats
A client Everfit cannot message is listed, not skipped silently
Your private notes stay private; clients never see them

MCP call:

{
  "name": "assign_program",
  "arguments": {
    "client_id": "66f1c2a9e4b0a1d2c3f4e5a6",
    "program_id": "65d8b7c6a5f4e3d2c1b0a9f8",
    "start_date": "2026-11-09"
  }
}

REST:

curl -X POST https://cotlet.dev/api/v1/everfit/clients/66f1c2a9e4b0a1d2c3f4e5a6/programs \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"program_id":"65d8b7c6a5f4e3d2c1b0a9f8","start_date":"2026-11-09"}'

Tool output:

{
  "client_id": "66f1c2a9e4b0a1d2c3f4e5a6",
  "program": {
    "program_id": "65d8b7c6a5f4e3d2c1b0a9f8",
    "title": "Beginner Strength",
    "weeks": 8
  },
  "start_date": "2026-11-09",
  "start_day": 1,
  "end_day": 56,
  "status": "assigned"
}

REST under /api/v1/everfit has the same tools for scripts and cron jobs. A call Everfit refuses, like a message to an offline client or a habit on Starter, fails and costs no credits. The tools table lists the REST path of each tool.

How much does the Everfit MCP server cost?

About $43 a month for a coach with 35 active clients, 7,460 credits. Your Everfit plan is billed by Everfit as before.

Job	Calls	Credits
Answer unread Inbox chats, daily	7 × 30	2,100
Check in on quiet clients, weekly	17 × 4	680
Weight and waist report with weigh-in tasks, weekly	76 × 4	3,040
Next program for clients who finished one	7 × 2	140
Cloud Browser, 30 days		1,500
Total		7,460

Free 7-day trial, no card
10 credits per successful call, MCP or REST
50 credits a day for the Cloud Browser
No Studio plan or Zapier plugin needed

35 clients is Everfit's $75 Pro tier and where most solo coaches level off (Coachway, Aug 2026). Most calls go to the weekly reads, one per client; the daily Inbox run assumes 3 unread chats. Dollars at the $29 pack rate.

Everfit MCP server on GitHub, Zapier or hosted: which to use

Option	What it does	Where it stops
mistersimon/everfit-mcp	MCP server and CLI for the client app: your own sessions, workout detail and profile. Node, MIT.	Client side, not coach; 0 stars, last commit 5 Sep 2026, runs on your computer with your password.
Zapier MCP for Everfit	The 31 Zapier actions as MCP tools: invites, programs, Autoflows, collections, forums.	Studio plan plus the plugin, from $19 a month per 1,000 tasks; no Inbox, metrics or tasks.
Olly	Everfit's own assistant: voice requests, message and task drafts, a read on one client.	Inside Everfit only, in Beta, and you press Send.
Assistant Coach	Another coaching platform with a read-only ChatGPT and Claude connector.	You move your clients off Everfit, and it "cannot send messages to clients".

Pick Zapier if you are on Studio and only need invites and Autoflow enrollment from a form or a checkout. Ask Everfit for the Enterprise API past 500 clients. Pick Cotlet if your agent should read workouts and metrics and write to clients on Starter or Pro.

Also listed on: Odel, mcpbeat

Who runs Cotlet

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

Everfit API and MCP: questions

Can I use the Everfit 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.

How do I get access?

Sign up free at https://cotlet.dev, open Everfit under Integrations in the console and log in to your Everfit coach account in its Cloud Browser. Your free trial starts when you sign up, no card needed.

How do I connect Everfit to ChatGPT or Claude?

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

What can ChatGPT do in Everfit?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Everfit: check in on clients who stopped training; weekly client progress report; answer client Inbox messages. You ask in plain words, and anything that reaches other people waits for your OK first.

Does Everfit notify clients when my agent assigns something?

Yes, the same as when you do it by hand. A program, workout, task or habit lands in the client's app, which notifies the client, task and habit reminders go out at the time you set, a message arrives in Inbox, and an invite sends an email unless send_invite is false. That is why invite_client, assign_program, assign_workout, add_task, add_habit and send_message ask for your OK by default. archive_client, unarchive_client and the body metric writes reach nobody.

Can it message every client?

Only clients who joined the app. Everfit refuses a message to an offline client, one who never signed in to the client app, and send_message says so. list_clients shows the connection of each client.

Which Everfit plan do I need?

Whatever your plan allows. We build and test on a coach account on the Pro trial. Habits (list_habits, add_habit) need Pro; every other tool works on Starter. Past the plan's client limit invite_client fails in Everfit, the same as by hand.

What can it not do yet?

Autoflows, broadcasts, forms and check-in answers, nutrition and meal plans, progress photos, creating or editing programs and workouts, building a one-off workout from exercises, deleting a client, removing a task, habit or assignment, resending an invitation, and payments, packages and team settings are not built. get_client leaves out the injuries and limitations list. Messages to offline clients, voice notes and attachments cannot be sent.

Does Everfit have webhooks?

Two, on Enterprise only: a client joined your workspace, and a client opened the app. The Everfit team sets them up on a URL you send them. Below Enterprise, run your agent on a schedule and read Inbox and the calendar.

Does it work on the free Starter plan?

Yes, it works in whatever your plan allows. Starter covers up to 5 clients and every tool except habits, which need Pro, the same as by hand.

Is the MCP server different from the REST API?

Only the way in. Both have the same 23 tools, inputs and answers, one API key and one price. Agents use MCP; scripts, cron jobs and HTTP steps use REST.

Is Cotlet affiliated with Everfit?

No. Cotlet is independent and not affiliated with Everfit Technologies, Inc.

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.