QuickCoach MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
QuickCoach MCP server through Cotlet.dev
Connect QuickCoach to ChatGPT, Claude, Codex and Claude Code through Cotlet.dev. Read your coaching roster, prepare client plans and review check-ins in your own signed-in coach account.
This is an unofficial integration, not affiliated with QuickCoach. Cotlet.dev hosts the connection through your Cloud Browser. This repository provides an optional Python stdio MCP bridge.
Connect your account
Open https://app.quickcoach.fit/ in your Cotlet.dev Cloud Browser. Enter your coach email and type the code QuickCoach sends you, then enable QuickCoach for agents.
Connect your agent. Refresh the connector if you enabled QuickCoach after connecting.
ChatGPT
Open Settings > Apps & Connectors > Create. Enter https://cotlet.dev/mcp/v1/connect as the MCP server URL and choose OAuth.
Claude
Open Settings > Connectors > Add custom connector and enter https://cotlet.dev/mcp/v1/connect.
Codex
Create a Cotlet.dev API key in your console and set COTLET_API_KEY in your environment. Add:
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"Claude Code
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"Related MCP server: CoachingPortal MCP Server
Coaching workflows
Examples from the live QuickCoach integration reference:
Find clients with few upcoming plans and prepare their next drafts.
Read client feedback and workout history before proposing a plan change.
Publish and reorder plans after reviewing the changes.
Set client macros and review food logs when your QuickCoach plan includes them.
Prepare a push notification for your approval.
Review Client Billing and prepare a package payment link.
The live reference lists 26 hosted capabilities: 6 read and 20 write. They are available through quickcoach_read and quickcoach_write. Writes ask for confirmation by default, configurable per tool. Review client names, plan changes, notification recipients and payment amounts before approving.
QuickCoach clients work through an ordered plan queue rather than a calendar. Edits to published plans reach clients immediately. QuickCoach has no message inbox; replies use plans or push notifications. Pro features require the corresponding QuickCoach plan. Your Stripe connection, payouts, QuickCoach subscription and sign-in email remain outside these tools.
Optional local stdio bridge
Python 3.10 or newer is required, with no runtime dependencies. Clone this repository and configure a client that supports stdio:
{"mcpServers":{"quickcoach":{"command":"python3","args":["/absolute/path/to/quickcoach-mcp/quickcoach_agent.py"],"env":{"COTLET_API_KEY":"your-cotlet-key"}}}}The local bridge lists seven browser helpers: quickcoach_guide, quickcoach_status, quickcoach_open, quickcoach_read, quickcoach_click, quickcoach_type and quickcoach_close. They forward to Cotlet.dev's shared browser tools. The local helper names are separate from the hosted workflow groups and their 26 capabilities. Call the guide first and close the browser when finished.
Discovery works without a key. Executing a tool requires your Cotlet.dev API key and connected account.
python3 quickcoach_agent.py connect
python3 quickcoach_agent.py guide
python3 quickcoach_agent.py status
python3 quickcoach_agent.py serveYou can also build the included Dockerfile and pass COTLET_API_KEY as an environment variable.
Reference and access
Licensed under Elastic License 2.0. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Access approved FITsociety clients, schedules, bookings and coaching data with AI assistants.
Manage fitness coaching clients, workouts, programs, chats and funnels from your assistant.
Create, personalize and deliver branded workouts and programs from any AI assistant.
Connect authorized ad accounts to AI assistants for audits, reporting, and approval-gated changes.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables an AI client to query one AimHarder account for classes, participants, workouts, bookings, personal activity, and strength records, and to make or cancel bookings and save or delete PRs after explicit confirmation.21305 npmMIT
- AlicenseAqualityBmaintenanceEnables ChatGPT, Claude, and other AI agents to work with client check-ins, workout templates, and training programs in a user's signed-in account, with approval required before actions reach other people.7Elastic 2.0
- AlicenseNot gradedqualityBmaintenanceConnects Claude, ChatGPT, and other MCP-speaking assistants to a user's training account, enabling retrieval of prescribed sessions, weekly reviews, recovery metrics, activities, strength and lab results, and scheduling of sessions, routines, races, goals, daily updates, and body-composition scans under scoped permissions.MIT
- AlicenseNot gradedqualityCmaintenanceEnables users to connect their coaching account to ChatGPT, Claude, Cursor, and other AI agents to review clients, workouts, progress, Inbox, and task workflows using natural language.Elastic 2.0