Skip to Content
Cloud platform (PaaS)Working with AI assistants

Working with AI assistants

Cloud Noce works with Claude Code, Cursor, Codex, Gemini Antigravity and any MCP-compatible agent through the MCP server built into the CLI. An agent can inspect projects and services, deploy source code, read logs and builds, manage variables and domains, and perform lifecycle operations.

Install the CLI and sign in

Run gerdoo login. MCP uses the same saved token.

Connect your agent

Run this in the repository root:

gerdoo setup agent

This command writes MCP settings and the use-gerdoo guidance skill for recognized agents.

Test the connection

Ask the agent to show the current account and project list, then identify the target service by slug or ID.

Example requests

  • “Inspect the latest failed build of the api service and report only its cause.”
  • “Set NODE_ENV=production as a runtime variable on the web service and redeploy it.”
  • “Deploy the current folder as a private service in the demo project.”
  • “Check the service domain and tell me which records are needed; do not make changes yet.”

Access scope and safety

The agent uses your full CLI token to access every project available to your account. Secret values are redacted in tool output, but key names remain visible. Deletion, rollback and suspension require confirm: true and should be shown as destructive actions in the client.

Always explicitly identify the project, environment and service. Before confirming destructive operations, check the ID and the effects on volumes, domains and users.

For each agent’s configuration files, global installation and the tool list, see the complete MCP and agents guide.