Claude Code is Anthropic’s terminal-based coding agent. It speaks MCP natively and can run shell commands, which means it can use both the Ntro MCP server and theDocumentation Index
Fetch the complete documentation index at: https://docs.ntropii.com/llms.txt
Use this file to discover all available pages before exploring further.
ntro CLI — exactly the two surfaces a runbook author needs.
Prerequisites
- Claude Code installed and signed in
ntro-mcpinstalled and reachable on$PATH(or by absolute path)- A working
~/.ntro/config.toml(runntro auth loginif you haven’t)
Add the MCP server
Claude Code reads~/.claude/mcp.json for global config and <project>/.claude/mcp.json for project-local config. Pick whichever fits — global if you want Ntro available in every Claude Code session, project-local if you want it scoped to one workspace.
ntro-mcp isn’t on $PATH (common with uv editable installs), use the absolute path:
/mcp reconnect inside it). The Ntro tools should appear in /mcp.
Verify it’s working
In Claude Code, ask:ntro auth whoami works at the terminal — the MCP server uses the same config.
Make the CLI usable too
The MCP tools cover write operations. For reading runs, viewing schedules, and running the local test harness, Claude Code is most effective when it can shell out to thentro CLI:
ntro is on $PATH, Claude Code can run it directly. With editable installs from a custom venv, either:
- Add the venv’s
bin/to$PATHin your shell init, or - Tell Claude Code to use the absolute path:
/home/you/.ntro-dev/bin/ntro workflow test ...
Example: scaffold a runbook
A real session looks roughly like:Shipping it
Two ways to deploy from Claude Code:Related
Copilot Studio
Same MCP server, different client.
Skill definitions
The prompts that teach a coding agent how to author Ntropii runbooks.