mcpField
P
PRzilla

PRzilla

Remote
przilla.appHealth0Updated 1d ago

About PRzilla

PRzilla is an MCP connector for searching a public catalog of CrossFit and HYROX workouts and movements. Its read-only tools provide catalog details, not personal training history or personalized plans.

Key features

  1. 01Search workouts by name, movement, and category
  2. 02Get prescriptions, scaling guidance, and benchmark targets
  3. 03Look up movement technique, equipment, and easier variations
  4. 04Find demonstration videos and example workouts

Use cases

  1. 01Find workouts containing specified movements
  2. 02Check a workout's prescription and target time
  3. 03Look for scaling options for beginners
  4. 04Learn movement technique and alternatives

MCP support

The connector exposes unauthenticated, read-only catalog tools to MCP clients over Streamable HTTP at https://przilla.app/mcp.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://przilla.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

PRzilla MCP connector

Search PRzilla's public CrossFit and HYROX workout and movement library from an AI assistant.

This repository contains registration metadata and setup documentation for the hosted connector. The PRzilla application and catalog implementation are maintained separately.

Connect

  • Endpoint: https://przilla.app/mcp
  • Transport: Streamable HTTP
  • Authentication: None
  • Website: przilla.app

Add the endpoint as a custom remote MCP server in an assistant that supports it. Enable its read-only tools and select PRzilla when asking a catalog question. No PRzilla account or API key is required. Availability depends on the assistant's plan and administrator settings.

The endpoint accepts JSON-RPC POST requests. Opening it as a web page returns HTTP 405.

Available tools

  • search_workouts: Find public workouts by name, movements, and optional catalog category.
  • get_workout: Read a named workout's prescription, movements, available scaling guidance, and benchmark targets.
  • search_movements: Look up movement technique, equipment, easier variations, available demonstration videos, and example workouts.

Input and output schemas are advertised by the server through tools/list.

Search results are fuzzy summaries. Fetch the full workout before judging whether it includes a movement or quoting its prescription or time cap. Performance targets are catalog benchmarks, not personal results or official competition rankings. A movement's example-workout links lead to workouts, not movement profile pages.

Example questions

  • What's the Fran workout and what's a good time?
  • Find Hero WODs with rope climbs.
  • How do I scale Murph for a beginner?
  • What's a thruster and what can I do instead?
  • Which HYROX formats are in the catalog?

Scope and privacy

The connector reads public catalog data. It cannot access personal history or custom workouts, save scores, create personalized training plans, or change accounts.

Lookup terms are sent to PRzilla. See the privacy policy for data handling and the terms of use. The assistant provider's own privacy policy governs conversations with that assistant.

Support

Contact [email protected] with the assistant name and error message. Do not include credentials or private training records.

Registry publication

server.json describes the production endpoint for the official MCP Registry. The manual GitHub Actions workflow verifies the publisher release, checks the live connector, validates the manifest, and publishes using GitHub OIDC. It requires no stored registry token.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.