---
title: Exercise Catalog MCP connector
description: Private exercise catalog bridge for agent-built workouts.
canonical: https://wellness.delx.ai/connectors/exercise-catalog
content_signal: ai-train=no, search=yes, ai-input=yes
---

# Exercise Catalog MCP connector

A private MCP connector for exploring how agents can combine wearable readiness with exercise selection and Telegram-ready recommendations.

## Short answer

The Exercise Catalog MCP server is the local process provided by exercise-catalog-mcp-private. Add its MCP configuration to a compatible client and it exposes the provider records listed on this page to that client. It is not an official Exercise Catalog product and Delx does not host a copy of the data.

## Install

This connector is documented as a private lab. Public docs intentionally avoid provider endpoints and sensitive implementation details.

## Agent client config

```json
{
  "mcpServers": {
    "exercise_catalog": {
      "command": "node",
      "args": ["dist/index.js"]
    }
  }
}
```

## Signals

- Exercises
- Muscle Groups
- Equipment
- Video Guidance
- Workout Builder

## Data availability

- Exercise search and catalog metadata: available. Private provider-dependent data.
- Muscle groups and equipment filters: available. Used for agent workout construction.
- Video guidance links: conditional. Only when the provider returns public video URLs.
- Medical or injury diagnosis: not_available. The connector is not a clinical decision system.

## MCP tools

### Start here

- `exercise_catalog_connection_status`
- `exercise_catalog_capabilities`
- `exercise_catalog_build_workout`

### Catalog

- `exercise_catalog_search`
- `exercise_catalog_get_exercise`
- `exercise_catalog_list_filters`

### Agent readiness

- `exercise_catalog_agent_manifest`
- `exercise_catalog_privacy_audit`

## Prompts

- `exercise_catalog_recommend_workout`
- `exercise_catalog_telegram_workout`

## Resources

- `exercise-catalog://capabilities`

## Privacy

- Private lab by default.
- No provider endpoint is published on the marketing site.
- Rate limits should protect the upstream service.
- Agent output should remain non-medical and user-goal oriented.

## Best for

- Wearable-aware workout recommendation
- Telegram exercise suggestions
- Muscle and equipment filtering
- Internal provider testing

## Known limits

- Private lab, not public npm.
- Provider terms and rate limits must be respected.
- Not medical advice.

## Links