Gravl builds you a personalized strength training plan, coaches you through every workout and tracks your progress. Just show up. Gravl handles the rest.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · mcp.gravl.ai
42tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.gravl.ai/mcp
Skill page: https://www.mcpbundles.com/skills/gravl-mcp-e2d62df9ed
Explore capabilities (42)
read 10
write 4
other 11
Showing 25 of 42
Showing 25 of 42 tools from the public preview. Connect the server to inspect the full live tool list.
Get7
Patch7
List3
Create Workout2
Validate Workout2
Other capabilities4
Get MCP API schema
read
get_mcp_schema
Returns the MCP API endpoint list and hard limits exposed by Gravl.
Get MCP API schema — Returns the MCP API endpoint list and hard limits exposed by Gravl.
Get MCP options — Returns API-backed readable id/name options for settings, muscles, equipment categories, workout types, set types, and other enum fields.
Get account context — Fetches the user's settings, workout settings, custom splits, and gym profiles in one call. Use before editing account configuration.
Get all settings — Fetches all editable settings groups in one response: user, workout, warmup, rest time, appearance, and training mode.
Update training goals — Updates training setup: goal, experience level, workout duration, workout place, weekly goal, gym name. Partial update: only send the fields the user asked to change. Body-profile fields (weight, height, gender) cannot be changed here — the user must edit them in the Gravl app.
Update general preferences — Updates display and workout preferences: weight/distance units, first day of week, exertion rating prompt, supersets, exercise distribution, default effort. Partial update: only send the fields the user asked to change.
Update equipment settings — Updates equipment settings: equipment ids, sub-equipment ids, bodyweight-only mode, plate calculator. Partial update: only send the fields the user asked to change. List fields are full replacements — fetch current settings first before adding or removing single items.
Update muscle focus — Updates focused and excluded muscles/submuscles. Partial update: only send the fields the user asked to change. List fields are full replacements — fetch current settings first before adding or removing single items.
Get system splits — Lists Gravl's built-in system training splits: externalId, name, description, supported days per week, and session names. Use to resolve the name behind trainingMode.systemMuscleSplitExternalId, or to pick a systemMuscleSplitExternalId before calling select_training_mode.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Gravl builds you a personalized strength training plan, coaches you through every workout and tracks your progress. Just show up. Gravl handles the rest.
How do I connect Gravl to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does Gravl provide?
Operate this server?
Request removal if you do not want Gravl listed here, or claim the listing if you want to manage it on MCPBundles.
Operate Gravl?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Select training mode — Selects recovered, system, or custom training mode. system requires systemMuscleSplitExternalId (list valid ones with get_system_splits); custom requires customMuscleSplitExternalId. Does not select programs; use program APIs for that later.
Update workout settings — Updates workout-generation settings. Partial update: only send the fields the user asked to change.
Patch warmup settings — Updates warmup settings. Send only fields the user asked to change.
Patch rest time settings — Updates rest-time settings. Durations are seconds.
List recent workouts — Lists recent completed workouts with compact summary fields. Includes workouts synced from external platforms (Apple Health, Strava, ...) unless filtered via source.
List workouts — Lists completed workouts with pagination, filtered by date range, contained exercise, trained muscle, workout type, or name. Includes workouts synced from external platforms (Apple Health, Strava, ...) unless filtered via source. Use list_recent_workouts for a quick latest-first view.
Get workout — Fetches one workout with exercise and set details. Get workoutExternalId from list_recent_workouts or list_workouts; ids from public share links (app.gravl.ai/quick-workout/public/...) are share-snapshot ids and will not resolve here.
Validate workout — Validates a workout payload before creating it. Takes the same shape as create_workout.
Create workout — Logs a completed workout. Gravl normalizes units and assisted/bodyweight loads, then calculates volume, estimated strength calories, progression, and personal records. Sensor metrics remain absent unless a device later enriches the workout. Validate first unless the user explicitly asks to create immediately.
Delete workout — Permanently deletes a logged workout and its personal records. Irreversible - only call after the user explicitly confirms which workout to delete.
List workout templates — Lists saved workout templates with ids, names, descriptions, and exercise counts.
Get workout template — Fetches one workout template by external id.
Validate workout template — Validates a workout template payload before create/replace. Takes the same shape as create_workout_template.
Create workout template — Creates a saved workout template. Use exercise ids from list_exercises or resolve_exercises.
Replace workout template — Full-replaces an existing workout template's metadata and exercises. Prefer this for AI edits because the final state is explicit.
Showing the first 25 tools — full list and schemas: Directory API.
MCPBundles probed 42 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does Gravl require?
Gravl may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.