Agentic Research MCP Integration Quickstart

Connect an MCP-compatible agent to User Intuition to plan customer research and retrieve participant evidence. Start by connecting and reading existing resources; commission a study only after reviewing its plan and recruitment.

Connect your agent

Use the hosted endpoint, https://mcp.userintuition.ai/mcp, with OAuth in compatible clients. For local stdio, run npx -y @userintuition-ai/mcp with USERINTUITION_API_KEY set to your ui_sk_ key. The CLI supports browser login and API-key management. Hosted OAuth does not require exchanging a user-supplied API key.

For a local stdio client that uses an MCP configuration file:

{
  "mcpServers": {
    "userintuition": {
      "command": "npx",
      "args": ["-y", "@userintuition-ai/mcp"],
      "env": {"USERINTUITION_API_KEY": "ui_sk_your_key_here"}
    }
  }
}

Keep real keys out of version control. For shell workflows:

npm install -g @userintuition-ai/mcp
userintuition-mcp login
userintuition-mcp list
userintuition-mcp list_studies

Start with a read such as list_studies to check your connection. See the current MCP setup guide for client-specific instructions and the research skills for workflow guidance.

What can your agent do once connected?

MCP exposes study planning, recruitment, interviews, results, evidence search, and supporting configuration operations. The CLI provides shell access to research workflows. Use the current tool catalog and API reference for exact names and arguments; tool counts vary by release.

Create a metadata draft with create_study, then send the research brief through customize_study. Relay any planning questions to the user. Retrieve the persisted plan with get_study and obtain approval before recruitment. The user must choose panel or BYOP explicitly.

For a panel study, use launch_panel with dry_run: true to obtain the recruitment estimate. Show the country, language, cost, and timeline; launch with the same settings after approval. Each launch specifies one country. Audiences below 10% incidence require a feasibility request.

For a BYOP study, use create_participants with 1–100 unique participant emails per batch after the saved plan and invitations are approved. Invitations send by default; set silent: true on individual participant records when invitations should not send. Source customer lists through your own authorized export or integration; MCP has no direct CRM segment-sync tools.

How do you retrieve findings?

Study results expose findings, participant responses, sample profiles, recommendations, and source references in JSON. Use generate_report when analysis is needed, and get_interview to verify supporting messages and recording links. Preference shares, credibility scores, and ranked themes are not guaranteed typed fields in this response.

Record the study ID and check interview progress later. A completed interview does not establish that all planned fieldwork is done. Paginate interview records before reporting totals, and check whether the report is stale before treating it as the latest analysis.

How do you use earlier research?

Agents can search findings and participant responses across authorized studies, then retrieve the underlying reports and interviews. Results preserve study context and source links; the calling agent interprets the evidence. Search coverage is explicit, and retrieving evidence does not launch research.

Common troubleshooting issues

Discovery or connection fails. Check the client-specific setup instructions and authentication method. Hosted OAuth and local stdio API-key setup are different paths.

The agent cannot find a tool from an older article. Use the current server catalog. Participant Evidence describes the research workflow. Discover the current catalog and use documented search and retrieval operations.

A study has no findings yet. Inspect the study and interview records. The study may still need planning or recruitment, or interviews may not have completed. Do not infer fielding state from interviewer provisioning alone.

A write times out. Read persisted state before repeating creation, invitations, or recruitment. A lost response does not prove the operation failed.

MCP or dashboard?

Use MCP when the question arises inside your agent workflow and you want to plan and review research in that conversation. Use the dashboard when you want to explore the Customer Intelligence Hub directly or inspect the full workspace visually. Both can work with the same account’s study records; they do not expose identical features.

Pricing

The MCP connection itself has no separate fee. Research uses platform credits, with panel recruitment priced separately in the estimate. User Intuition voice interviews cost $30 each with no subscription required. Recruitment is priced separately. Chat uses 0.5 credit, voice 1, and video 2 per interview. Three free interviews are available on signup; review recruitment charges before launching a panel study.

See current pricing and agentic research.

Where can I run the examples?

The public TypeScript examples cover study execution, the four report sections, and research search. Run fixture mode first; it is a local demonstration with fictional data. Check the release compatibility notes before using live calls.