1. Choose a connection
Use the hosted Streamable HTTP endpoint with OAuth when your client supports it:https://mcp.userintuition.ai/core/mcp for the research workflow, https://mcp.userintuition.ai/read-only/mcp for read-only tools, or https://mcp.userintuition.ai/compact/mcp for grouped administrative operations. Authorize each endpoint separately. The full URL above exposes every tool. Local stdio clients can append --profile core, --profile read-only, or --profile compact to the server command.
To try study design and reports in staging, connect to https://mcp.sandbox.userintuition.ai/mcp with a staging account. Follow the sandbox quickstart for Test with AI, three synthetic responses, and the participant-link limitation.
Local stdio remains supported for clients that need a local process. Create a key under Settings → API Keys at app.userintuition.ai. Keys start with ui_sk_.
2. Connect your client
- ChatGPT
- Codex
- Claude Desktop
- Cursor
- Claude Code
- VS Code
- Install User Intuition from the ChatGPT plugin directory.
- Sign in to User Intuition when prompted.
- Start a new chat and ask for your studies.
3. Verify the connection
Ask your client:List my User Intuition studies.The agent should call
get_account. A successful account-scoped response confirms authentication; merely seeing tool names does not. The current surface includes queue_customize_study, review_study, search_research, and answer_research.
4. Give the agent a workflow
Connection proves the tools work. A Skill tells the agent how to use them reliably. Install the create-study-from-brief Skill, then ask the agent to use it. The Skill adds the question order, readiness checks, plan review, and approval gates needed for a safe study-creation flow.Install the Skill
Add the reusable study-design workflow to your AI client.
Read the MCP playbook
Understand the workflow rules already advertised by the server.
Use the create-study-from-brief Skill to help me design a Panel study about why trial users do not activate. Dry-run the panel cost, but do not launch without my confirmation.For a healthy end-to-end run, the agent should keep the study name to 40 characters, ask you to choose the recruiting method when it is missing, create a metadata draft, and pass your research brief to
queue_customize_study. Poll get_customize_study_job until it succeeds and read its result; use synchronous customize_study for a native concept image. Omitted interview settings default to an English voice interview with the male interviewer voice. The default decisions: "human" relays questions[] to you. If you delegate research-design choices, decisions: "agent" lets the planner proceed with assumptions and report them back; remaining required questions still come back in questions[]. The agent must then call get_study, return the complete persisted plan for review, and obtain approval of that exact version before creating BYOP participants or launching paid Panel recruitment. A Panel launch also requires an explicit single country and separate approval of its estimate.
Public API MCP tools return full JSON in structuredContent.result; supplemental tools use structuredContent directly. MCP text content also contains the full JSON for model tool chaining. view_research_answer supplies readable answer text and quotation labels alongside its structured data.
Troubleshooting
If the tools are missing after hosted OAuth setup, restart the client or start a new chat/task. For stdio, restart the client and force a fresh package download withnpx -y @userintuition-ai/mcp@latest. See Troubleshooting for authentication and cache checks.
