Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.userintuition.ai/llms.txt

Use this file to discover all available pages before exploring further.

The User Intuition CLI is the same binary as the MCP server, invoked as a plain command-line tool. Every tool the MCP server exposes — ask_humans, list_studies, create_assistant, analyze_transcripts, all 72 of them — is reachable as a subcommand. No MCP client required.

​
When to reach for the CLI

  • Shell scripts and CI jobs. Pipe study results into jq, write a cost-gate before launching a Panel study, automate cleanup of test assistants.
  • Cron and scheduled work. Run nightly status sweeps, refresh cached reports, alert on long-running studies.
  • Ad-hoc debugging. Pin down whether a problem is the tool, the backend, or your MCP client — by isolating the call from the agent.
  • Onboarding a teammate. A single userintuition-mcp call list_studies line teaches more than three paragraphs of API docs.

​
When to use the MCP server instead

If an AI agent should choose the tool and fill in arguments (Claude, ChatGPT, Cursor), use the MCP server. The CLI assumes you already know which tool and which arguments.

​
What you get

The CLI ships with the Node build of the MCP server (@userintuition-ai/mcp on npm, 0.2.6+). It uses the same USERINTUITION_API_KEY, the same input validation, and the same backend endpoints — the only thing that changes is the transport.
The CLI is Node-only. The Python build (uvx userintuition-mcp) speaks MCP only — use the REST API for Python-first shell work.

​
Next steps

Quickstart

Install the binary and make your first call in under two minutes.

Command reference

Every subcommand, every flag, with examples.

Recipes

Practical patterns — CI cost gates, lifecycle scripts, batch operations.

Troubleshooting

Auth errors, missing binaries, common pitfalls.