MusclesWorked MCP Server

Exercise-to-muscle mapping: 856 exercises, 65 muscles, workout analysis & alternatives.

Local serverstdio

What is the MusclesWorked MCP server?

Connect MusclesWorked to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Exercise-to-muscle mapping: 856 exercises, 65 muscles, workout analysis & alternatives. The musclesworked mcp server is what makes that connection.

What the server does

MCP server for the musclesworked.com exercise-to-muscle mapping API.

Installation

musclesworked-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • get_muscles_worked — Get primary, secondary, and stabilizer muscles for an exercise
  • find_exercises — Find exercises targeting a specific muscle with optional filters
  • analyze_workout — Analyze a workout for coverage, gaps, and imbalances
  • get_alternatives — Find alternative exercises ranked by muscle overlap
  • search_exercises — Search exercises by name to discover IDs
  • search_muscles — Search muscles by name to discover IDs
  • Cursor — The Cursor tool exposed by this server

Credentials and setup notes

Configuration is passed through the environment: MUSCLESWORKED_API_KEY, MUSCLESWORKED_API_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MusclesWorked's toolset — get_muscles_worked, find_exercises, analyze_workout and 4 more — is a fair guide to whether it matches your workflow. It is maintained by csjoblom; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
get_muscles_workedGet primary, secondary, and stabilizer muscles for an exercise
find_exercisesFind exercises targeting a specific muscle with optional filters
analyze_workoutAnalyze a workout for coverage, gaps, and imbalances
get_alternativesFind alternative exercises ranked by muscle overlap
search_exercisesSearch exercises by name to discover IDs
search_musclesSearch muscles by name to discover IDs
CursorThe Cursor tool exposed by this server.

How to install the MusclesWorked MCP server

{
  "mcpServers": {
    "musclesworked": {
      "command": "npx",
      "args": ["-y", "musclesworked-mcp"],
      "env": {
        "MUSCLESWORKED_API_KEY": "mw_live_..."
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
MUSCLESWORKED_API_KEYCredential the server authenticates with.Yes
MUSCLESWORKED_API_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use MusclesWorked to get muscles worked.
  • Use MusclesWorked to find exercises.
  • Use MusclesWorked to analyze workout.

Frequently asked questions

It connects MusclesWorked to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (get_muscles_worked, find_exercises, analyze_workout, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MusclesWorked directly.