wger-agent 0.1.29

Wger Workout Manager — exercise database, workout routines, nutrition plans, body measurements, and progress tracking.

Wger - A2A | AG-UI | MCP

Version: 0.1.29

Overview

Wger MCP Server + A2A Agent

Wger Workout Manager — exercise database, workout routines, nutrition plans, body measurements, and progress tracking.

This repository is actively maintained - Contributions are welcome!

MCP

Using as an MCP Server

The MCP Server can be run in two modes: stdio (for local testing) or http (for networked access).

Environment Variables

• WGER_INSTANCE: The URL of the target service.
• WGER_ACCESS_TOKEN: The API token or access token.

Run in stdio mode (default):

export WGER_INSTANCE="http://localhost:8080"
export WGER_ACCESS_TOKEN="your_token"
wger-mcp --transport "stdio"

Run in HTTP mode:

export WGER_INSTANCE="http://localhost:8080"
export WGER_ACCESS_TOKEN="your_token"
wger-mcp --transport "http" --host "0.0.0.0" --port "8000"

A2A Agent

Run A2A Server

export WGER_INSTANCE="http://localhost:8080"
export WGER_ACCESS_TOKEN="your_token"
wger-agent --provider openai --model-id gpt-4o --api-key sk-...

Docker

Build

docker build -t wger-agent .

Run MCP Server

docker run -d \
  --name wger-agent \
  -p 8000:8000 \
  -e TRANSPORT=http \
  -e WGER_INSTANCE="http://your-service:8080" \
  -e WGER_ACCESS_TOKEN="your_token" \
  knucklessg1/wger-agent:latest

Deploy with Docker Compose

services:
  wger-agent:
    image: knucklessg1/wger-agent:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=http
      - WGER_INSTANCE=http://your-service:8080
      - WGER_ACCESS_TOKEN=your_token
    ports:
      - 8000:8000

Configure mcp.json for AI Integration (e.g. Claude Desktop)

{
  "mcpServers": {
    "wger": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "wger-agent",
        "wger-mcp"
      ],
      "env": {
        "WGER_INSTANCE": "http://your-service:8080",
        "WGER_ACCESS_TOKEN": "your_token"
      }
    }
  }
}

Install Python Package

python -m pip install wger-agent

uv pip install wger-agent

Repository Owners

Graph Architecture

This agent uses pydantic-graph orchestration for intelligent routing and optimal context management.

---
title: Wger Agent Graph Agent
---
stateDiagram-v2
  [*] --> RouterNode: User Query
  RouterNode --> DomainNode: Classified Domain
  RouterNode --> [*]: Low confidence / Error
  DomainNode --> [*]: Domain Result

• RouterNode: A fast, lightweight LLM (e.g., nvidia/nemotron-3-super) that classifies the user's query into one of the specialized domains.
• DomainNode: The executor node. For the selected domain, it dynamically sets environment variables to temporarily enable ONLY the tools relevant to that domain, creating a highly focused sub-agent (e.g., gpt-4o) to complete the request. This preserves LLM context and prevents tool hallucination.