Great Question MCP Guide

The ultimate guide to UX research with MCP

The guide to running UX research from inside Claude, Cursor, or ChatGPT. Written for the people approving it, the people rolling it out, and the people actually using it. Check back for regular product updates.

Install MCP in 5 minutesBook an MCP demo
Webb · Stellar Jet · 2025 · NASA
115+
Tools across the research workflow
Unlimited
No metering on MCP use
< 5 min
Median time to first prompt

The Great Question MCP server connects your research repository to your AI client of choice. Every study, every transcript, every highlight, every insight. Once connected, your AI can read your research, design new studies, recruit panelists, and synthesise findings without leaving the chat.

Customer research is moving inside the AI client. The MCP is how Great Question gets there with you.

The guide

Who this is for

This guide covers security, how to start quickly, and how to best roll it out across your organization. Start where it's most useful to you, or share the section that matters most to whoever else needs to say yes.

  1. 01The person evaluating it. Security, IT, ReOps, vendor risk.
  2. 02The person rolling it out. Head of Research, Product, Design, CIO.
  3. 03The person using it. Researcher, PM, designer, CSM, exec. The "what can I actually do?"
  4. 04The person buying it. Same nuance as above. The evidence you want is in customer stories.

Quick start

Install it yourself. No engineer. No API key.

No procurement gate. Pick your client, paste the server URL, authorize in the browser. First prompt in under 5 minutes.

Server URL
https://greatquestion.co/api/mcp/v1

Claude Desktop

  1. Profile picture → Customize → Connectors → Add custom connector
  2. Name: Great Question. URL: paste the server URL. Click Connect.
  3. Authorize in the browser window that opens.
  4. Restart Claude Desktop.
  5. Try: "What studies have I run in the last 6 months?"

Claude Code

Prompt
claude mcp add --transport http GreatQuestion https://greatquestion.co/api/mcp/v1

Approve in the browser. Verify with claude mcp list. Done.

Cursor

Open settings (Cmd-Shift-J). MCP tab → New MCP Server. Paste:

Prompt
{"mcpServers":{"great-question":{"url":"https://greatquestion.co/api/mcp/v1"}}}

Save, Connect, authorize.

ChatGPT

Settings → Apps → Advanced settings → toggle Developer mode. Create app with name Great Question, paste server URL, OAuth. Authenticate via browser.

Other clients

Windsurf, Zed, VS Code, Codex, Jules, Cline, Gemini, Cowork: standard MCP HTTP transport with the server URL above. Standard OAuth 2.1. No API keys.

Connected tools

Works with the AI tools your team already uses

Connect once through the Great Question MCP and run your entire research workflow from any of these tools: create studies, recruit participants, build screeners, analyze results, and pull insights.

  • Claude

    Spin up studies, recruit participants, and analyze results. The full research workflow from Claude and Claude Code.

  • Cursor

    Run your whole research operation without leaving your IDE: create studies, build screeners, and pull insights.

  • ChatGPT

    Launch surveys and interviews, manage participants, and dig into results inside ChatGPT.

  • Gemini

    From recruiting to synthesis, operate the entire platform through Gemini.

  • Copilot

    Create studies, invite candidates, and surface insights via Microsoft Copilot.

What you can do

11 MCP prompts for inspiration

Get an insight into how you can use the MCP for UX research.

Read research

Prompt
"What are the top 3 things customers said about onboarding last quarter?"
Prompt
"For Project Atlas, find every study, highlight, and insight tagged 'X'. Build a stakeholder readout."
Prompt
"Read this PRD [paste]. Mark every claim as supported, partial, contradicted, or no evidence. Link to highlights."

Create research

Prompt
"Create a 5-question survey on willingness-to-pay for atier. Send me the share link."
Prompt
"Author a 30-minute moderated interview study for SMB owners who churned in the last 60 days."
Prompt
"Add 12 candidates matching senior IC + product/design + US/EU + not contacted in 90 days. Send the screener invitation."

Synthesise across studies

Prompt
"For the 18 interviews in study stu_xyz, extract the top 7 themes, attach 2–3 quotes per theme with timestamps."
Prompt
"Search for the theme 'cognitive load' across studies in the last 18 months. Group by study, list quote count, identify segments."

Govern the repo

Prompt
"List all candidates last contacted more than 18 months ago. Bucket by industry. Flag for re-consent or archiving."
Prompt
"Find all studies in 'draft' status owned by people who no longer work here. Suggest archive or reassign."

Multi-step / agentic

Prompt
"I want to test pricing sensitivity for our enterprise plan. Create the study, write the screener, recruit 40 from our paying-customers segment, send invites, configure the calendar, and tell me how many have booked so far."

real mcp use cases

How our customers are using the MCP today

Get inspiration on how to use the MCP for everyday research.

FINTECH SCALEUP

"Building our own research stack makes no sense."

"This feels like a long-time vision coming together. The value comes from the connection of all of these data sources together, that's huge."
Head of Product Foundations

TRADING PLATFORM

"It can 10x our output."

"The time to plan, conduct, and analyze research is the biggest bottleneck. If we can integrate automated workflows, the potential for research to be more impactful is so much more evident."
Brand Research

ENTERPRISE PLATFORM

"Are you in Claude all day now? Basically, yes."

Lone researcher. Enabled MCP live on the call.

PAYMENTS COMPANY

"No prototype, no meeting."

Built a Claude skill on top of Great Question MCP that creates synthetic users from past interview transcripts and pre-validates designs against them.
Product Designer

AI COMPANY

"The MCP is our wedge."

"UI will shrink, CLI will grow." T is deprecating UserTeting specifically because it's not AI-native.

SAAS COMPANY

Running a pilot on MCP + repo

Paying to integrate research with Claude for "speeding up the creation of shaping docs and PRDs."
Head of Product Design
“For us internally, we basically don't work with any vendors anymore that don't have an MCP and aren't leaning aggressively into AI.”
Ned DwyerCEO, Great Question

Security

What happens when you turn MCP on?

The most common enterprise question: "If I flip it on, can my entire org suddenly see everything?"

No. MCP respects exactly the permissions you already have in Great Question. If a user can't see a study in the UI, they can't see it via MCP.

  • RBAC inheritance, by default. A researcher with full repo access sees the same via MCP as in the UI. No new data classes are exposed.
  • PII redacted by default. Names, emails, phone numbers redacted at our server before responses leave. Admins can toggle for approved workflows. The toggle is audit-logged.
  • Every tool call is audit-logged. User ID, tool name, parameters, timestamp, workspace ID. Your natural-language prompt never reaches Great Question, only the structured tool call does.
  • OAuth 2.1. No API keys. No long-lived secrets stored on your device. Your existing Great Question DPA covers MCP. No MCP-specific sub-processors.
Architecture, 90 seconds
[ AI Client ]        [ Great Question ]   [ Your LLM ]
Claude/Cursor         MCP server           Anthropic/
ChatGPT/Code          api/mcp/v1           OpenAI/etc.
     |                     |                    |
     | 1. OAuth 2.1         |                    |
     |-------------------> |                    |
     | 2. Tool call         |                    |
     |-------------------> |                    |
     |          RBAC + PII redaction             |
     | 3. Result            |                    |
     |<------------------- |                    |
     | 4. Client -> LLM     |                    |
     |----------------------------------------->|
  • Your prompt never reaches Great Question. Only the structured tool call does.
  • Path from Great Question to your LLM is governed by your contract with that provider.
  • Every tool call audit-logged with user attribution.

mcp features

MCP coverage across the entire research workflow

Read + write access across candidate management, study design, scheduling, recruitment, analysis, synthesis, and more.

01

Candidates

Participants & panel
CandidatesCandidate SegmentsConsent Forms

Candidates

Write
  • Create & update profiles
  • Manage custom attributes
  • Permanently forget (GDPR)
  • Full profiles & history
  • Search by name, email, study, date

Candidate Segments

New
  • View & search saved segments
  • Filter candidate search by segment

Consent Forms

Write
  • Attach a consent form to any interview, survey or unmoderated study
  • Browse & search signed consent forms
02

Design

Studies & screeners
StudiesInterviews, Surveys & Prototype TestsStudy Messaging & Templates

Studies

Read
  • View, list & search all study types

Interviews, Surveys & Prototype Tests

Write
  • Create, update & delete studies
  • Assign to teams & transfer ownership
  • Incentives (manual / Tremendous) & currency
  • Participation caps (total + weekly)
  • Set study language and localization
  • Build unmoderated tests for card sort, tree test, prototype test, questions, welcome screens, permission set up
  • Interview scheduling, provider & duration
  • Screeners with qualification & skip logic

Study Messaging & Templates

Write
  • Compose & edit invitations, screener invites & reminders
  • Templates across 13 message kinds
  • Merge tags
03

Scheduling

Calendar & team assignment
Interview CalendarInterview ModeratorsTeams

Interview Calendar

Write
  • Set availability, booking limits, timezones, and buffer time
  • View booking windows, daily/weekly limits
  • Set scheduling notice & livestream options

Interview Moderators

Write
  • Add/update/remove moderators & observers
  • View assigned team members

Teams

New
  • View & search teams for assignment
04

Recruit

Shortlist & invite
Shortlist CandidatesScreener Invitations

Shortlist Candidates

Write
  • Shortlist onto any study type
  • Interview, survey or prototype studies
  • Auto-skips ineligible candidates

Screener Invitations

Write
  • Invite for interview studies
  • Invite for survey studies
  • Invite for prototype test studies
05

Analyze

Sessions, transcripts & responses
SessionsTranscriptsHighlightsScreener ResponsesSurvey & Prototype Submissions

Sessions

Read
  • Details, tags & metadata
  • Speaker-attributed transcripts
  • Search by candidate, creator, study

Transcripts

Read
  • Full speaker-attributed transcripts
  • Full-text search

Highlights

Read
  • Annotated excerpts with video
  • Search by candidate, creator, study

Screener Responses

Read
  • Answers, match scores & status
  • Search by submission date

Survey & Prototype Submissions

New
  • Survey answers & status
  • Prototype completion rate, top paths & per-screen drop-off
  • Links back to Great Question for heatmap & funnel views
  • Recording transcript on prototype responses
06

Synthesize

Insights & knowledge base
InsightsReels

Insights

New
  • Findings & stories
  • Export as PDF
  • Search by creator, study, title

Reels

Read
  • Curated highlight reels with video
  • Search by creator, study, title
WriteWrite = action
ReadRead = search
NewNew = shipped recently

Agent-led, human-supervised

Explore what the MCP does today and where human-in-the-loop remains

The MCP agent reads your full repository, drafts and configures studies, and sources and triages participants, so you arrive at a ready-to-launch study fast.

You stay in control of the moments that need a person to oversee: launching a study, approving who advances, and direct outreach.

Rolling out MCP across your org

Customers who get the most out of MCP roll it out in waves rather than blasting it organization-wide on day one.

  1. Wave 1 · Week 1

    Research + ReOps

    Senior researchers and your ReOps lead. Prove value, build the prompts library, set the tone for governance.

    • Outcome: 5 to 10 prompts that fit your workflows.
    • Metric: Daily MCP use by end of week.
  2. Wave 2 · Weeks 2 to 4

    Product + Design ICs

    PMs and designers who consume research the most. Shift research consumption left. Reduce find-me-a-quote requests.

    • Outcome: ICs self-serving top research questions.
    • Metric: % of PRDs citing MCP-sourced evidence.
  3. Wave 3 · Month 2+

    CS, Sales, Support, Exec

    Customer-facing teams and leadership. Spread customer voice deeper into your organization.

    • Outcome: QBRs and battlecards citing research.
    • Metric: Decisions referencing MCP-sourced evidence per month.

Governance and quality

The biggest risk with MCP is not security. It is sloppy AI-generated synthesis that looks authoritative but is not. Our customers have shared their real use cases and how they're managing governance and quality.

The fix: ReOps becomes the enforcer. Tag the repo well, author rubric prompts, run AI outputs through a human review loop. Most customers use MCP for synthesis and still bring humans in for the final framing.

Five ways to engage

In order of commitment. Start with the one that fits where you are.

  1. 01DIY install. Help docs cover every client. Most customers are live in under 5 minutes. Quick start
  2. 0230-minute setup call for customers. Customer Success walks you through your first three prompts on your actual repo. Free on Pro. Contact success@greatquestion.co
  3. 03Want to learn more if you're not a customer yet? We'll walk through your AI use case, and run you through our enterprise security. Book a demo
  4. 04MCP-curious live workshops. Catch our regular live events on AI workflows and the MCP. Register
  5. 05Want to be featured? Doing something interesting with the Great Question MCP? We would love to put you on stage, write a customer story, or co-host a salon at your office. Submit here

Your repo is already the best dataset you will never use. MCP is how you finally use it.

No metering. Five-minute install. Your existing permissions, your existing data, now in the AI tool your team already lives in.

Install MCP now

Book a time

The questions we hear on every prospect and security call.

Frequently asked

If I turn it on, can my whole org access everything?

No. MCP inherits your existing Great Question RBAC. A user can only see and do via MCP what they can already see and do in the UI.

Is my data used to train AI models?

No. We do not train models on your data. The LLM your AI client uses is governed by your contract with that provider.

Where does my data go when I use MCP?

From Great Question to your AI client to the LLM provider you chose. We do not proxy MCP responses through any LLM provider ourselves.

What about PII?

A workspace-wide Hide PII via MCP toggle is on by default. Names, emails, and phone numbers are redacted at our server before responses leave. Admins can turn it off for approved workflows. The toggle is audit-logged.

Can I limit which users in my workspace can use MCP?

Today the toggle is workspace-wide. Per-user enable and disable is on the Q3 2026 roadmap. In the meantime, use RBAC to scope what each user can see. That scoping applies to MCP automatically.

Does it work with my AI client?

If it speaks MCP over HTTPS, yes. We officially test Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, Codex, Jules, Windsurf, Zed, Cline, Gemini, and Cowork.

Does it support audio or video?

Not via MCP. Text transcripts only.

Is there a separate DPA or sub-processor list for MCP?

No. Your existing Great Question DPA covers MCP. There are no MCP-specific sub-processors.

Can I run a trial before paying?

MCP is included on Pro and above. A trial or sandbox path is in exploration. Talk to your CS rep for early access.

Get the blog in your inbox

Latest insights for customer-obsessed product builders. Once a month, no noise.