Skip to main content
MCP prompts for common Contree workflows. Prompts provide structured instructions that guide AI agents through multi-step tasks.

prepare-environment

run-python

run-shell

sync-and-run

install-packages

parallel-tasks

build-project

debug-failure

inspect-image

multi-stage-build

​
Quick Reference

PromptDescriptionKey Parameters
prepare-environmentPrepare container environment with CHECK-PREPARE-EXECUTE flowtask, base, project, packages
run-pythonRun Python code in isolated containercode
run-shellRun shell command in isolated containercommand, image
sync-and-runSync local files and run commandsource, command, image
install-packagesInstall packages and create reusable imagepackages, image
parallel-tasksRun multiple tasks in paralleltasks, image
build-projectBuild project: install deps and run testssource, install_cmd, test_cmd
debug-failureDiagnose failed operationoperation_id
inspect-imageExplore container image contentsimage
multi-stage-buildMulti-stage build with rollback pointssource, install_cmd, build_cmd, test_cmd

​
Using Prompts

​
With MCP Clients

MCP-compatible clients can invoke prompts directly: 
{
  "prompt": "prepare-environment",
  "args": {
    "task": "Train ML model",
    "base": "python:3.11-slim",
    "packages": "numpy pandas scikit-learn"
  }
}

​
Prompt Output

Prompts return structured instructions that guide the agent through:
  1. Step-by-step workflows - Ordered operations with clear dependencies
  2. Tool selection - Which Contree tools to use and when
  3. Parameter guidance - Correct values for each tool call
  4. Best practices - Following the CHECK-PREPARE-EXECUTE pattern

​
Categories

​
Environment Setup

​
Code Execution

​
Building and Testing

​
Operations