AI Agent Usage

Overview

The Monito CLI is designed for AI agent consumption. Every command supports --json for structured output, and data is cleanly separated from human text (stdout vs stderr).

Authentication

Set the MONITO_TOKEN environment variable:

export MONITO_TOKEN=$(monito-cli auth token)

Or retrieve a token programmatically:

TOKEN=$(monito-cli auth token)

Structured Output

Use --json to get machine-readable output:

# List projects
monito-cli project list --json
 
# Get run results
monito-cli run view <id> --json
 
# Get session events
monito-cli session events <id> --type network --json

Parsing with jq

# Get project IDs
monito-cli project list --json | jq '.projects[].id'
 
# Get failed runs
monito-cli run list --json | jq '.runs[] | select(.status == "failed")'
 
# Get bug report titles from a session
monito-cli session view <id> --json | jq '.bugReports[].ticketTitle'

Workflow Example

A typical AI agent workflow:

# 1. List projects
monito-cli project list --json
 
# 2. Run all scenarios for a project
monito-cli project run <project-id> --json
 
# 3. Check results
monito-cli run view <run-id> --json
 
# 4. If failed, inspect the debug session
monito-cli session view <session-id> --json
 
# 5. Get network events for debugging
monito-cli session events <session-id> --type network --json

Claude Code Integration

When using Monito CLI with Claude Code, the AI agent can:

Run monito-cli project list --json to discover available projects
Run monito-cli scenario run <id> --json to execute tests
Parse the JSON output to understand test results
Use monito-cli session events <id> --json to debug failures

The --json flag ensures all output is parseable, and exit codes indicate pass/fail status.