Skip to main content
User Intuition’s MCP server exposes the complete research workflow to AI agents: 50 tools on every transport, covering the versioned public API plus account context, catalogs, interview usage, and a read-only study review app.

​
MCP tools and Skills

The MCP server gives an agent the tools. A User Intuition Skill gives it the workflow: when to ask for Panel versus BYOP recruitment, how to conduct the Customize Plan conversation, when to dry-run cost, and when confirmation is required.

Connect the MCP server

Configure Claude, Cursor, VS Code, or ChatGPT and verify the connection.

Install a research Skill

Teach your agent a repeatable study-creation or analysis workflow.

​
One surface on every transport

For read-only exploration in Claude’s directory, use the separate Claude directory research connector.
  • Streamable HTTP accepts OAuth for interactive clients and organization API keys for headless clients. Connect to https://mcp.userintuition.ai/mcp.
  • stdio remains available for Claude Desktop, Cursor, Claude Code, VS Code, and other local clients. It authenticates with a ui_sk_ API key.
Both transports expose the same 50 tools. Choose the authentication method that fits the client.

​
Smaller profiles

For the common study → interview → report workflow, connect to https://mcp.userintuition.ai/core/mcp (33 tools). It omits webhook, feasibility, external-panel, and platform-admin administration. For existing research without write actions, connect to https://mcp.userintuition.ai/read-only/mcp (25 tools). The https://mcp.userintuition.ai/compact/mcp profile keeps the research workflow and groups less common webhook, feasibility, and external-panel operations into 41 tools. Each URL has its own OAuth protected-resource metadata, so authorize the specific URL your client uses. The full /mcp URL remains available for all 50 tools. Local stdio clients can pass --profile core, --profile read-only, or --profile compact after the package name. The default is the full profile. Resource and prompt support remains available on these profiles. Measured from the complete tools/list response in the cited-answer and cursor MCP change set: The token estimate divides bytes by four; actual model context usage varies by host and tokenizer. CI checks each profile against its payload budget.

​
Tool groups

The tool reference documents every registered tool. The study-creation playbook documents the behavioral rules agents should follow. The server also exposes attachable study and report resources for clients that show MCP resources in the conversation. These resources read the same authenticated public API as the research tools.

​
Safety model

The server advertises MCP safety annotations for every tool. Agents should also follow these product rules:
  1. Use customize_study for the plan, audience, screeners, and concept material; do not reconstruct those fields in the MCP host.
  2. Return the complete persisted study plan and obtain approval of its current version before creating BYOP participants, sharing an external-panel entry link, or launching paid Panel recruitment.
  3. Use estimate_panel, show the complete estimate, and carry its estimate_id into an approved paid panel launch.
  4. Require explicit user confirmation before rewards, webhooks, stopping fieldwork, or deleting studies, participants, or interviews.

​
Runnable developer examples

Use the developer examples to inspect study execution, report retrieval, and evidence search. The public repository includes fictional no-spend fixtures, a matching MCP/CLI walkthrough, and release compatibility notes.

​
Agent homepage

Start at research.userintuition.ai for the three research workflows, connection options, machine-readable guidance, and public examples. This documentation remains the detailed operation reference.