Skip to main content
The Celesto CLI provides fast, serverless deployment for Agentor agents, MCP servers, and AI applications with built-in observability and scalability.

Installation

The Celesto CLI is installed automatically with Agentor:
Verify installation:

Quick Start

Deploy an agent in three steps:
Your agent is now live at:

Authentication

Get your API key from the Celesto Dashboard. Set it as an environment variable:
Or configure it directly:

Deployment Options

Deploy Specific Directory

Deploy with Custom Name

Deploy with Environment Variables

Deploy MCP Server

Deploy:
Access at:

Configuration File

Create celesto.yaml for advanced configuration:

Environment Variables

From .env File

Create a .env file:
Variables are automatically loaded during deployment.

From Command Line

From YAML

Managing Deployments

List Deployments

Output:

Get Deployment Info

View Logs

Follow logs in real-time:

Update Deployment

Make changes to your code, then redeploy:
The existing deployment will be updated.

Delete Deployment

Using Deployed Agents

HTTP Requests

Streaming Requests

A2A Protocol

Access the agent card:
Send A2A messages:

MCP Protocol

Connect to deployed MCP server:

Production Best Practices

Troubleshooting

Deployment Fails

Check logs:
Common issues:
  • Missing dependencies in requirements.txt
  • Invalid environment variables
  • Syntax errors in code

Application Crashes

View error logs:
Enable debug mode:

Slow Performance

  • Check model selection (lighter models are faster)
  • Enable caching for MCP servers
  • Review trace data for bottlenecks

Connection Timeouts

Increase timeout in client:

Cost Optimization

  • Use lighter models for simple tasks (gpt-5-mini vs gpt-4o)
  • Implement caching for repeated queries
  • Set appropriate max_tokens limits
  • Monitor token usage in dashboard

Support

Get help:

Next Steps

Last modified on June 30, 2026