Wger Agent
Knuckles-Team/wger-agent
MCP server para Wger Workout Manager com segurança enterprise e rastreamento integrado
Ver no GitHubMCP server production-grade para integração com Wger Workout Manager, permitindo gerenciamento de exercícios, rotinas, planos nutricionais e rastreamento de progresso. Implementa ferramentas action-routed otimizadas, segurança enterprise com políticas Eunomia e telemetria nativa via OpenTelemetry.
Instalação
npx convez-ai Knuckles-Team/wger-agent1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Automação de planos de treino e nutrição via agentes Claude
- Integração de dados de exercícios e progresso em aplicações fitness
- Gerenciamento centralizado de rotinas e medições corporais com IA
Veredito

Solução robusta e bem arquitetada para integração com Wger, com foco em otimização de tokens e segurança enterprise. Ideal para desenvolvedores que precisam automatizar fluxos fitness com Claude, mas requer familiaridade com MCP e configuração avançada.
README
A tradução para o português deste README ainda está na fila.
Wger Agent
CLI or API | MCP | Agent
Version: 0.31.0
Documentation — Installation, deployment, usage across the MCP, API, and agent interfaces, and guidance for provisioning the Wger Workout Manager platform are maintained in the official documentation.
Overview
Wger Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Wger Workout Manager — exercise database, workout routines, nutrition plans, body measurements, and progress tracking..
Key Features
- Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
- Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
- Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
- Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.
CLI or API
This agent wraps the Wger Workout Manager — exercise database, workout routines, nutrition plans, body measurements, and progress tracking. API. You can interact with it programmatically or via its integrated execution entrypoints.
Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.
MCP
This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.
Available MCP Tools
| Tool Module | Toggle Env Var | Enabled by Default | Description & Nested Methods |
|---|---|---|---|
| Routine | ROUTINETOOL | True | Manage wger routine operations. Action-routed methods: create_day, create_routine, create_slot, create_slot_entry, delete_day, delete_routine, get_days, get_public_templates, get_routine, get_routines, get_slots, get_templates. |
| Routineconfig | ROUTINECONFIGTOOL | True | Manage wger routineconfig operations. Action-routed methods: create_repetitions_config, create_rest_config, create_rir_config, create_sets_config, create_weight_config, get_repetitions_configs, get_weight_configs. |
| Exercise | EXERCISETOOL | True | Manage wger exercise operations. Action-routed methods: get_equipment, get_exercise_categories, get_exercise_images, get_exercise_info, get_exercises, get_muscles, get_variations, search_exercises. |
| Workout | WORKOUTTOOL | True | Manage wger workout operations. Action-routed methods: create_workout_log, create_workout_session, delete_workout_log, delete_workout_session, get_workout_logs, get_workout_session, get_workout_sessions. |
| Nutrition | NUTRITIONTOOL | True | Manage wger nutrition operations. Action-routed methods: create_meal, create_meal_item, create_nutrition_plan, delete_nutrition_plan, get_ingredient_info, get_ingredients, get_nutrition_diary, get_nutrition_plan_info, get_nutrition_plans, log_nutrition. |
| Body | BODYTOOL | True | Manage wger body operations. Action-routed methods: create_measurement_category, delete_weight_entry, get_gallery, get_measurement_categories, get_measurements, get_weight_entries, log_body_weight, log_measurement. |
| User | USERTOOL | True | Manage wger user operations. Action-routed methods: get_languages, get_repetition_units, get_user_profile, get_user_statistics, get_user_trophies, get_weight_unit_settings. |
Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.
Dynamic Tool Selection & Visibility
This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.
You can configure tool filtering via multiple input channels:
- CLI Arguments: Pass
--toolsor--toolsets(or their disabled counterparts--disabled-toolsand--disabled-toolsets) during startup. - Environment Variables: Define standard environment variables:
MCP_ENABLED_TOOLS/MCP_DISABLED_TOOLSMCP_ENABLED_TAGS/MCP_DISABLED_TAGS
- HTTP SSE Request Headers: Pass custom headers during transport initialization:
x-mcp-enabled-tools/x-mcp-disabled-toolsx-mcp-enabled-tags/x-mcp-disabled-tags
- HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
?tools=tool1,tool2?tags=tag1
When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.
MCP Configuration Examples
stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)
Configure your IDE's mcp.json to launch the MCP server via uvx:
{
"mcpServers": {
"wger-agent": {
"command": "uvx",
"args": [
"--from",
"wger-agent",
"wger-mcp"
],
"env": {
"WGER_URL": "your_wger_url_here",
"WGER_API_KEY": "your_wger_api_key_here",
"WGER_DEFAULT_EMAIL": "your_wger_default_email_here",
"WGER_DEFAULT_PASSWORD": "your_wger_default_password_here"
}
}
}
}
Streamable-HTTP Transport (Recommended for production deployments)
Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:
{
"mcpServers": {
"wger-agent": {
"command": "uvx",
"args": [
"--from",
"wger-agent",
"wger-mcp"
],
"env": {
"TRANSPORT": "streamable-http",
"HOST": "0.0.0.0",
"PORT": "8000",
"WGER_URL": "your_wger_url_here",
"WGER_API_KEY": "your_wger_api_key_here",
"WGER_DEFAULT_EMAIL": "your_wger_default_email_here",
"WGER_DEFAULT_PASSWORD": "your_wger_default_password_here"
}
}
}
}
Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:
{
"mcpServers": {
"wger-agent": {
"url": "http://localhost:8000/wger-agent/mcp"
}
}
}
Deploying the Streamable-HTTP server via Docker:
docker run -d \
--name wger-agent-mcp \
-p 8000:8000 \
-e TRANSPORT=streamable-http \
-e PORT=8000 \
-e WGER_URL="your_value" \
-e WGER_API_KEY="your_value" \
-e WGER_DEFAULT_EMAIL="your_value" \
-e WGER_DEFAULT_PASSWORD="your_value" \
knucklessg1/wger-agent:latest
Additional Deployment Options
wger-agent can also run as a local container (Docker / Podman / uv) or be
consumed from a remote deployment. The
Deployment guide has full, copy-paste
mcp_config.json for all four transports — stdio, streamable-http,
local container / uv, and remote URL:
- Local container / uv — launch the server from
mcp_config.jsonviauvx,docker run, orpodman run, or point at a local streamable-http container byurl. - Remote URL — connect to a server deployed behind Caddy at
http://wger-mcp.arpa/mcpusing the"url"key.
Agent
This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.
Running the Agent CLI
To start the interactive command-line agent:
# Set credentials
export WGER_URL="your_value"
export WGER_API_KEY="your_value"
export WGER_DEFAULT_EMAIL="your_value"
export WGER_DEFAULT_PASSWORD="your_value"
# Run the agent server
wger-agent --provider openai --model-id gpt-4o
Docker Compose Orchestration
The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:
version: '3.8'
services:
wger-agent-mcp:
image: knucklessg1/wger-agent:latest
container_name: wger-agent-mcp
hostname: wger-agent-mcp
restart: always
env_file:
- ../.env
environment:
- PYTHONUNBUFFERED=1
- HOST=0.0.0.0
- PORT=8000
- TRANSPORT=streamable-http
ports:
- "8000:8000"
healthcheck:
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
interval: 30s
timeout: 10s
retries: 3
start_period: 10s
logging:
driver: json-file
options:
max-size: "10m"
max-file: "3"
wger-agent-agent:
image: knucklessg1/wger-agent:latest
container_name: wger-agent-agent
hostname: wger-agent-agent
restart: always
depends_on:
- wger-agent-mcp
env_file:
- ../.env
command: [ "wger-agent" ]
environment:
- PYTHONUNBUFFERED=1
- HOST=0.0.0.0
- PORT=9004
- MCP_URL=http://wger-agent-mcp:8000/mcp
- PROVIDER=${PROVIDER:-openai}
- MODEL_ID=${MODEL_ID:-gpt-4o}
- ENABLE_WEB_UI=True
- ENABLE_OTEL=True
ports:
- "9004:9004"
healthcheck:
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9004/health')"]
interval: 30s
timeout: 10s
retries: 3
start_period: 10s
logging:
driver: json-file
options:
max-size: "10m"
max-file: "3"
Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.
Security & Governance
Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:
Access Control & Policy Enforcement
- Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports
none, localembedded(mcp_policies.json), or centralizedremotemodes. - OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
- Scoped Credentials: Execution context runs restricted to the specific caller identity.
Runtime Security Grid
| Feature | Functionality | Enablement |
|---|---|---|
| Tool Guard | Sensitivity inspection with human-in-the-loop validation | Enabled by default |
| Prompt Injection Defense | Input scanning, repetition monitoring, and recursive loop blocks | Enabled by default |
| Context Safety Guard | Stuck-loop detectors and contextual overflow preemptive alerts | Enabled by default |
Installation
Install the Python package locally:
# Using uv (highly recommended)
uv pip install wger-agent[all]
# Using standard pip
python -m pip install wger-agent[all]
Documentation
The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.
| Page | Contents |
|---|---|
| Installation | pip, source, extras, prebuilt Docker image |
| Deployment | run the MCP and agent servers, Compose, Caddy + Technitium, env config |
| Usage | the MCP tools, the WgerApi client, the agent CLI |
| Backing Platform | deploy the Wger Workout Manager with Docker |
| Overview | the standardized agent-package pattern |
| Concepts | concept registry (CONCEPT:WGER-*) |
Repository Owners
Contribute
Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:
- Format code using
ruff format . - Lint code using
ruff check . - Validate type-safety with
mypy . - Execute test suites using
pytest