Productivity

gravl.ai

Manages user workout settings, training goals, and gym profiles for the Gravl fitness platform.

1 endpoint42 known toolsFirst detected September 9, 2026Last detected September 9, 2026

ENDPOINT 1

https://mcp.gravl.ai/mcp

No auth detected

MCP server metadata

Name: gravl-mcp
Version: 0.1.0

Capabilities

tools.listChanged

Server instructions

Gravl is a workout tracking app. This server operates on the connected user's own Gravl account. Conventions: - Most enum fields (goals, muscles, set types, workout types, ...) are numeric ids. Call get_mcp_options once early and reuse it to translate ids to readable names. - Exercises are referenced by numeric ids. Always call resolve_exercises (or list_exercises with search) before building workouts or templates from user-provided exercise names - never guess ids. - When a movement has no match in the catalog, create it with create_custom_exercise instead of substituting a different exercise - custom exercises behave exactly like catalog ones in workouts, templates, and analytics. - Workout writes require explicit weightUnit and distanceUnit values. Set weights use weightUnit; long distances use kilometres/miles and loaded carries use metres/yards according to distanceUnit. Heights and settings values use the user's configured units. Rest durations are in seconds; workout durations are in minutes. - Settings updates are partial: send only the fields the user asked to change. List fields (equipmentIds, focusedMuscles, ...) are full replacements - fetch current values first when adding or removing single items. - validate_* tools accept the same payload as their create/replace counterpart; validate first for complex payloads. - Completed workout writes require a stable externalId. Generate it once and reuse it if the same save is retried. - Writes sync to the user's app automatically (version-based sync), no extra action needed. - delete_* tools are permanent and irreversible. Only call them after the user explicitly confirms the specific item.

Known tools 42

get_mcp_schema

Returns the MCP API endpoint list and hard limits exposed by Gravl.

Inferred read-only

get_mcp_options

Returns API-backed readable id/name options for settings, muscles, equipment categories, workout types, set types, and other enum fields.

Inferred read-only

get_account_context

Fetches the user's settings, workout settings, custom splits, and gym profiles in one call.

Inferred read-only

get_all_settings

Fetches all editable settings groups in one response: user, workout, warmup, rest time, appearance, and training mode.

Inferred read-only

patch_training_goals

Updates training setup: goal, experience level, workout duration, workout place, weekly goal, gym name.

Inferred read-only

patch_general_preferences

Updates display and workout preferences: weight/distance units, first day of week, exertion rating prompt, supersets, exercise distribution, default effort.

Inferred read-only

patch_equipment_settings

Updates equipment settings: equipment ids, sub-equipment ids, bodyweight-only mode, plate calculator.

Inferred read-only

patch_muscle_focus

Updates focused and excluded muscles/submuscles.

Inferred read-only

get_system_splits

Lists Gravl's built-in system training splits: externalId, name, description, supported days per week, and session names.

Inferred read-only

select_training_mode

Selects recovered, system, or custom training mode.

Inferred read-only

update_workout_settings

Updates workout-generation settings.

Inferred read-only

patch_warmup_settings

Updates warmup settings.

Inferred read-only

patch_rest_time_settings

Updates rest-time settings.

Inferred read-only

patch_appearance_settings

Updates appearance settings.

Inferred read-only

list_recent_workouts

Lists recent completed workouts with compact summary fields.

Inferred read-only

list_workouts

Lists completed workouts with pagination, filtered by date range, contained exercise, trained muscle, workout type, or name.

Inferred read-only

get_workout

Fetches one workout with exercise and set details.

Inferred read-only

validate_workout

Validates a workout payload before creating it.

Inferred read-only

create_workout

Logs a completed workout.

Inferred read-only

delete_workout

Permanently deletes a logged workout and its personal records.

Inferred read-only

list_workout_templates

Lists saved workout templates with ids, names, descriptions, and exercise counts.

Inferred read-only

get_workout_template

Fetches one workout template by external id.

Inferred read-only

validate_workout_template

Validates a workout template payload before create/replace.

Potential side effects

create_workout_template

Creates a saved workout template.

Inferred read-only

replace_workout_template

Full-replaces an existing workout template's metadata and exercises.

Inferred read-only

delete_workout_template

Permanently deletes a saved workout template.

Inferred read-only

list_custom_splits

Lists the user's custom muscle splits and sessions.

Inferred read-only

get_custom_split

Fetches one custom muscle split by external id.

Inferred read-only

validate_custom_split

Validates a custom split payload before creating or replacing sessions.

Inferred read-only

create_custom_split

Creates a custom split with its explicit sessions.

Inferred read-only

update_custom_split

Updates custom split metadata.

Inferred read-only

replace_custom_split_sessions

Full-replaces all sessions in a custom split.

Inferred read-only

delete_custom_split

Permanently deletes a custom muscle split.

Inferred read-only

list_exercises

Lists exercises available to the user.

Inferred read-only

get_exercise

Fetches detailed exercise data by numeric exercise id.

Inferred read-only

resolve_exercises

Resolves natural-language exercise names to Gravl exercise ids.

Inferred read-only

create_custom_exercise

Creates a custom exercise in the user's library for movements missing from the catalog (e.g.

Inferred read-only

list_equipment

Lists all Gravl equipment ids and readable names/options.

Inferred read-only

get_equipment

Fetches one equipment item by numeric equipment id.

Inferred read-only

list_measurements

Lists the user's body measurements (weight, body fat, girths) newest first.

Inferred read-only

list_personal_records

Lists the user's personal records (1RM, max weight, max volume, max reps, duration, distance), optionally filtered to one exercise.

Inferred read-only

list_gym_profiles

Lists the user's gym profiles, including selected equipment context.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.gravl-mcp]
url = "https://mcp.gravl.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "gravl-mcp": {
      "type": "http",
      "url": "https://mcp.gravl.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: gravl-mcp
Remote MCP URL: https://mcp.gravl.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "gravl-mcp": {
      "url": "https://mcp.gravl.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "gravl-mcp": {
      "type": "http",
      "url": "https://mcp.gravl.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "gravl-mcp",
  "transport": "streamable-http",
  "url": "https://mcp.gravl.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.