Optimal Blog

Imagine you've just joined a new research team. There is a vast amount of research in the repository. Hundreds of interviews, usability tests, surveys, and notes. Everyone tells you, "We've probably researched that already," but nobody knows when or where.

‍

Instead of manually searching projects or asking around, Model Context Protocol (MCP) lets you ask questions about studies conducted in Optimal and instantly surface the evidence you need.

‍

Here are practical ways UX researchers can use MCP with Optimal to understand past research, accelerate new studies, and uncover insights across their repository.

‍

‍

‍

1. Get up to speed on past and current research

‍

‍

One of the best ways to use MCP is understanding what's already known. Instead of combing through different studies, ask MCP to summarize existing knowledge before planning your next study.

‍

Try asking:

• Based on the research I’ve run in Optimal, what are the biggest UX opportunities for our product?
• Summarize the key findings from checkout research over the past year.
• What usability issues have been identified most frequently?
• What research should I read first to understand this project?

‍

‍

‍

2. Define your next research study

‍

‍

Before creating your next study, writing discussion guides or recruiting participants, check what questions have already been answered and which gaps remain.

‍

MCP can help identify opportunities for follow-up research and prevent unnecessary duplication.

‍

Try asking:

• What questions about account creation are still unanswered?
• What themes need further investigation?
• Based on previous studies, what should our next usability test focus on?
• What hypotheses should we validate next?

‍

‍

‍

3. Find supporting evidence faster

‍

‍

Whether you're preparing a presentation or writing a report, MCP can help to surface quotes, observations, participant metadata, and findings in seconds.

‍

Try asking:

• Find participant quotes describing frustration during onboarding.
• Show examples of navigation issues from recent usability tests.
• How many participants completed this study on mobile?
• Which sessions mentioned difficulty finding pricing information?
• Pull task completion rates from all prototype tests in the Dashboard project as a CSV.

‍

‍

‍

4. Discover research before starting from scratch

‍

‍

One of the easiest ways to waste research effort is repeating work that's already been done. Use MCP to explore what's already in your repository before creating a new study.

‍

Try asking:

• What research already exists about navigation?
• Have we previously tested this feature?
• What have we already learned about search?
• Which studies relate to account settings?

‍

‍

‍

5. Identify patterns across multiple studies

‍

‍

The biggest insights often emerge when you zoom out. Instead of reviewing studies individually, MCP can synthesize findings across projects to reveal recurring themes, behaviours, and pain points.

‍

Try asking:

• What pain points appear consistently across checkout studies?
• Compare findings from our last five usability tests.
• What themes have become more common over the past six months?
• Which usability issues keep appearing regardless of product area?

‍

‍

‍

6. Create stakeholder-ready summaries

‍

‍

Research is most valuable when it's easy to share. Use MCP to turn large volumes of research into concise summaries or visualizations tailored to your audience.

‍

Try asking:

• Summarize this quarter's most important customer insights.
• Create an executive summary for leadership.
• Create a pie chart with a breakdown of onboarding studies by study method. 
• What are the three biggest opportunities we should prioritize?
• Write a summary suitable for our product team.

‍

‍

‍

7. Bring research into your existing workflows

‍

‍

Connect it with the AI tools and platforms your team already uses so research becomes part of everyday decision-making.

‍

Examples include:

• Ask research questions and post insights directly into Slack.
• Create a new page in Notion summarizing research findings.
• Draft insight summaries for Google Docs and Confluence.

‍

‍

‍

Best practices for getting the best answers from MCP

‍

‍

Like any AI assistant, the quality of the output depends on the context you provide. A few simple habits can make a big difference.

‍

‍

Start with a clear goal

‍

Rather than asking broad questions, explain what you're trying to achieve. Instead of Tell me about onboarding.

‍

Try: I'm planning a usability study on onboarding. What problems have previous research uncovered that we should investigate further?

‍

‍

Narrow your search when appropriate

‍

Large repositories can contain a wealth of research.

‍

Specify:

• Study tool and/or project
• Research method
• Time period
• Team
• Participant segment

‍

For example: Summarize usability studies about checkout conducted during the past 12 months.

‍

‍

Decide whether you need one study or many

‍

Sometimes you need detailed findings from a single study. Other times you're looking for patterns across dozens of studies. Tell MCP which perspective you want.

‍

‍

Ask follow-up questions

‍

Treat MCP like a research partner rather than a search engine. For example:

‍

• Can you show supporting participant quotes?
• Which studies contributed to this finding?
• Are there conflicting findings?
• What evidence supports this recommendation?

‍

‍

Tell MCP how you want the answer

‍

Different audiences need different outputs.

‍

Ask for:

• Bullet-point summaries
• Executive briefings
• Presentation-ready insights
• Charts
• Tables
• Research reports
• Action items
• Product recommendations

‍

MCP helps researchers spend less time hunting for information and more time generating insights that move products forward. 

‍

How will you use MCP with your Optimal data? Whether you're uncovering past insights, planning new studies, or connecting research with the rest of your tools, we'd love to hear how you're putting it to work.

You've invested time, budget, and effort into your research. But when you or someone else needs an answer, finding the right insight often means searching through projects, remembering which study covered the topic, and piecing insights together manually.

‍
The Model Context Protocol (MCP) changes that. It connects AI tools like Claude, ChatGPT, and Cursor securely to your research in Optimal, so your team can ask questions in plain language and get insightful answers or connect your research to AI-powered workflows.

‍
Below, we cover what MCP makes possible and how to connect it, so you finally get full value from the research you've already done and the repository you’ve built.

‍
Getting started: What can MCP do for research teams?

‍
Once connected, MCP turns your repository into something you can ask directly, so all that past and current research is always instantly accessible. Here are 5 ways to use it:

‍

1. Research assistance

‍

Ask "What usability issues have we found recently?" or "What have we learned about onboarding?" Pull participant data and metadata e.g. “How many participants took this study on mobile?”

‍

2. Discovery

‍

‍Ask "What research already exists on navigation?" so work isn't duplicated. You can also use MCP to pull quotes or review transcript data. “Surface participant quotes that highlight points of friction when navigating the homepage.”

‍
3. Executive summaries

‍

Ask your AI tool to summarize the most important themes from research this quarter or format findings into charts or graphs.

‍
4. Cross-study synthesis

Surface recurring participant pain points across multiple usability studies at once.

‍
5. AI assistants & workflows

Connect Optimal research with the tools and workflows your team already integrated with your AI tools, like Zapier, Slack, Jira, and Notion.

‍
What can you ask? Real questions, by research method

‍
Here are some practical examples of the kinds of questions teams can ask.
‍

Across studies

• What themes appear across multiple usability studies?
• What are recurring participant pain points this quarter?
• Which studies were conducted around onboarding in the past year?
• Summarize all checkout-related findings from studies this quarter.
  ‍

Interviews

• Can you summarize the key pain points for participants who have downloaded and used the mobile app?
  ‍

‍Prototype testing

• Which task had the lowest success rate in the latest prototype test, and what usability issues contributed to it?
• What usability issues contributed to task failure?
• Pull task completion rates from all prototype tests in the Dashboard project as a CSV.

‍
Tree testing‍

• What % of users found the checkout successfully in last week's tree test, and where did the rest drop off?
• Where did users drop off?

‍
Card sorting

• Which categories did participants consistently group together in the navigation card sort?

‍
First-click testing

• Where did users first click when asked to find the Pricing page in the first click test?

‍

‍
How do you set up MCP with Optimal?

‍
‍
Step 1: Sign in to your AI tool
Log into your preferred AI assistant (e.g. Claude, ChatGPT, or Cursor).
‍
Step 2: Connect your Optimal account
Go to your AI tool’s settings and add a new MCP connection. Authenticate your Optimal account via OAuth 2.0 to securely grant access to your Optimal data.
‍
Step 3: Start asking questions
Return to your AI tool and begin with simple, high-value questions grounded in your research.

‍
Step 4: Embed it into your workflow‍
Use MCP regularly to explore insights, synthesize findings, and support decision-making.
The most effective MCP implementations are not standalone tools; they are embedded into daily decision-making.

‍
If your AI tool is already connected to tools like Slack, Jira, Notion, or Zapier, you can use your Optimal research to trigger workflows, such as:

‍

• Sending Slack alerts when key findings are uncovered
• Creating tickets in Jira when usability issues are detected
• Feeding insights into product documentation tools
• Connecting findings to internal AI assistants used by product and design teams

‍
You've already done the hard part: running the studies and capturing the findings. The value is sitting in your repository. MCP helps you unlock what's already in your repository, making it easy to discover, reuse, and turn into action.

‍

Whether a study was conducted yesterday or months ago, you’ll be able to gather insights with MCP to make faster, more informed decisions today.

Nearly 18 years ago, Optimal helped define what UX research could be, pioneering practices and tools that would become industry standard and change how teams worldwide better understand their users. As the industry has evolved, so has Optimal, expanding the platform, advancing participant recruitment, and building Optimal Intelligence AI to accelerate insight to action.
‍

Now, we’re at the edge of another major shift. With the launch of the Model Context Protocol (MCP), we’re entering a new realm, moving from traditional research workflows to AI-powered intelligence.
‍

‍

What is MCP (Model Context Protocol)?

Research data is one of the most valuable assets in any organization, but until now, it has been scattered across studies and reports, time-consuming to search and synthesize, and different to search or reuse. MCP now changes that for research teams. 
‍

Model Context Protocol (MCP) enables you to connect your Optimal research directly to AI tools, like ChatGPT, Claude, or Cursor, to explore and analyze your data seamlessly. Insights can go beyond data downloads, dashboards, or static reports. Access your insights and explore further with natural conversation.
‍

Get instant insights for questions like: 
‍

• “Based on all the research I’ve run in Optimal, what are the biggest UX opportunities for our product?” 
• “What usability issues have been identified by studies conducted in the past 3 months?”
• “What themes appear across onboarding studies?”
• “What research already exists about navigation improvements?”
  ‍
  ‍

What MCP Unlocks (Beyond Search)

With MCP-connected tools, you can:
‍

• Analyze studies: Understand patterns, findings, and trends across research automatically.
• Cross-study synthesis: Identify recurring themes across multiple studies in seconds.
• Pull key insights: Extract findings from individual studies without manual review.
• Search & explore research: Filter studies by creator, title, participant group, or timeframe.
• Analyze transcript insights & sessions: Surface usability issues, pain points, and behavioral patterns.
• Turn insights into deliverables: Automatically format findings into summaries and stakeholder-ready outputs. Get more ideas here.
• Connect with other tools & workflows: Use MCP along with your AI tool's existing integrations to create alerts and automate next steps e.g. create a Slack notification when a participant completes a study, share milestones, create a JIRA ticket and follow-up tasks.
  ‍
  ‍

From Early UX Research to AI-Native Intelligence

The evolution is clear.

We started by helping teams understand users through early UX research methods.
We helped formalize how research is conducted, analyzed, and shared.
‍

And now, with MCP in Optimal, we’re helping teams move beyond analysis altogether toward conversational, AI-driven research intelligence.
‍

Log in to Optimal, connect with your AI tools, and get the most value from your research or book a demo to start building your research repository with Optimal.

We recently hosted a live webinar introducing Optimal's new Usability Testing tool, a powerful solution that brings multiple research methods together in a single study, helping you get better insights, faster.

‍

Looking for the highlights? We've rounded up answers to the most common questions from the session.

‍

‍

‍

What is Usability Testing?

‍

‍

Optimal's new Usability Testing tool is a mixed-methods research tool that brings Prototype Testing, Live Site Testing, and Surveys into a single, end-to-end study workflow. Instead of treating each method as its own initiative, you can combine them inside a single study to allow participants to move naturally between tasks, experiences, and questions.

‍

With this tool, you can compare multiple prototypes side by side, benchmark a current live experience against a redesigned concept, evaluate a competitor's experience, and more. And researchers get everything analyzed in one place with AI-powered summaries, task results, video clips, and evidence-backed insights surfaced automatically.

‍

‍

‍

Is Usability Testing supported for mobile testing?

‍

Yes, participants can complete Usability Testing studies on mobile devices using their mobile browser or the Optimal Participant App. If screen recording is required, participants are prompted to download the Optimal Participant App, available for both iOS and Android. 

‍

Do you have to use multiple methods, or can you run just one?

‍

You can keep it simple and run a single survey, a standalone prototype test, or a live site session on its own. Or, mix methods or run multiple of the same method, such as multiple prototypes or live website tests in one study. The tool supports however your study needs to be shaped.

‍

Can you run bilingual studies?

‍

Usability Testing currently supports over 30 languages enabling what participants see and guiding how AI models interpret responses, generate summaries, identify themes, and surface insights. Today, studies are configured around a single language, so participants are expected to respond in the chosen language. That said, multilingual study support is something we're exploring for our roadmap.

‍

Are participants recruited once across all methods, or separately for each?

‍

Just once. From the participant's perspective, this looks and feels like a single study regardless of how many methods are included. They move through the experience naturally from start to finish.

‍

To what extent can sections and questions be randomized?

‍

Section-level randomization shuffles the order of any sections, while question-level randomization works within a specific section, shuffling the order of tasks and follow-up questions. Both are supported, giving researchers the flexibility to reduce order bias, particularly useful when comparing multiple experiences.

‍

Can you test multiple prototypes within the same study?

‍

Yes, with no limitations on the number of prototypes you can link to a single study so you can add multiple Figma prototype sections and connect a different prototype to each one.

‍

Can you reorder sections and questions in a study?

‍

Given that Usability Testing studies can grow complex, the ability to reorder things quickly was a priority. You can reorder individual tasks and questions within a section, and sections themselves by dragging them in the Build panel.

‍

How effectively can Usability Testing scale across a business?

‍

Scaling research isn't just about running more studies, it's about helping more people across the business access insights, understand them, and use them to make decisions. With Usability Testing, product managers, designers, and stakeholders can quickly understand what happened and why without having to see hours of recording through the automatically generated highlight reels, key quotes, and transcripts.

‍

Watch the full webinar

‍

If you want to experience the full walkthrough, demo, and Q&A, watch the recording to see Usability Testing in action and pick up tips and best practices straight from the session.

👉 Watch the full webinar here.

‍

Coordinating user interviews shouldn’t feel like a full-time job. Between juggling calendars, chasing confirmations, and sending reminders, scheduling can be the hidden bottleneck in research velocity and quietly consume the time you actually want to spend talking to customers. 
‍

If you want to run more interviews and generate insights more consistently, simplifying your scheduling process is one of best ways to remove friction and streamline your workflow.
‍

‍

‍

Save time and streamline your workflow

‍

What does a simpler workflow look like? 

With a tool like Optimal’s Interviews Scheduler, you can:
‍

• Invite participants via a booking link or email
• View upcoming and completed sessions in one place
• Connect with tools you already use like Google Calendar, Microsoft Outlook, Google Meet, Zoom, and Microsoft Teams.
• Let participants reschedule themselves. No back-and-forth emails.
• Add collaborators and automatically notify everyone of changes.
• Set session limits and calendar buffers.
• Automate email invites, reminders, confirmations, and thank-you messages.
  ‍

It’s everything you need to manage interviews without the chaos.
‍
‍

‍

Calendar integrations: Avoid conflicts and save time

With the Interviews Scheduler, you can sync your availability with Google Calendar and Microsoft Outlook in real time. Connect your own calendar or your team’s to ensure every busy slot is accounted for. Avoid double bookings, block out busy times, and keep everything in one place. 

Once set up, your availability automatically updates, and participants can book directly into open slots, eliminating the back-and-forth. Plus, depending on your preferences, your sessions will either sync directly to your calendar or come through as an .ics file in the confirmation email, saving you one more step.
‍

‍
‍

Seamless video conferencing integrations

The Interviews Scheduler integrates directly with Zoom, Microsoft Teams, and Google Meet.

When someone books a session:

• A video link is automatically generated
• It’s added to the calendar invite
• Everyone receives confirmation details
• Sessions can be automatically recorded

No copying links. No switching between tools.
‍

‍
‍

Built for research teams

‍

The Interviews Scheduler isn’t just about booking time slots. It’s about removing friction from your research workflow.

‍

With integrations at its core, you can:

• Keep your calendar, video tools, and participants in sync
• Reduce manual coordination
• Eliminate scheduling errors
• Focus on insights instead of admin

‍

Whether you’re running one-off interviews or managing weekly research sprints, the Interviews Scheduler helps you move faster and stay organised.

‍

Ready to give it a try? Log in to your Optimal account and get started or book a demo to learn more.

‍

So, you’re ready to run a study. It’s designed, you’ve planned your questions, your methodology is sound. Your discussion guide is carefully crafted to avoid leading questions and dig into real user motivations…then you start recruiting participants.

‍

Suddenly, you’ve hit a massive bottleneck. Your perfect study depends entirely on finding the right people, getting them to show up, and hoping they provide thoughtful responses rather than one-word answers and distracted multitasking. You’ve now hit the crunch point that every researcher faces: your insights are only as good as your participants. What happens when participant quality isn’t great? 

‍

‍

‍

The hidden cost of "good enough"

‍

‍

Let's be honest about what typically happens with recruitment. You need a minimum number of participants to get statistically significant results (depending on study type). You’ve got a time limit in which you need to get results so they’re still relevant to your product development lifecycle. You start reaching out through your usual channels: customer lists, screening surveys, panel providers, social media posts, begging colleagues to connect you with people who fit your criteria. 

‍

After a week of this, you've got a few confirmed participants, but not enough. Some people have expressed interest but haven't confirmed times and it’s teeming more and more like your study is going to launch late, and you’re going to miss product deadlines. 

‍

So you make compromises.

‍

You accept the participant who sort of fits your criteria but isn't quite in the target demographic. You take the person who can only do a 30-minute session instead of the planned 60 minutes. You keep the flaky participant who's rescheduled twice because you need the numbers. 

‍

Then the sessions happen.

‍

One person no-shows. Another is clearly distracted, giving minimal responses while probably checking email. A third seems to have misunderstood the screening criteria entirely and doesn't actually use the type of product you're researching. The two good participants provide valuable insights, but now you're making conclusions based on a sample size of two.

‍

This isn't research. This is educated guessing with extra steps.

‍

‍

‍

What bad participants cost you

‍

‍

1. Quality  In, Quality Out. Poor participant quality isn't just annoying. It has real consequences that ripple through everything that comes after. The worst outcome isn't getting no data. It's getting bad data that you treat as good data. A participant who doesn't match your target users provides feedback, but that feedback doesn't represent your actual users. If you act on it, you're optimizing for the wrong people. Bad data doesn't just waste research time. It sends product decisions in the wrong direction. 
2. Wasted team time. You spend hours recruiting, scheduling, conducting sessions, and analyzing results. When the research is based on poor-quality participants, all of that time is wasted. Or worse, it's spent acting on misleading information. One bad research study doesn't just cost the time invested in that study. It costs the time spent implementing the wrong solutions based on faulty insights.
3. Damaged credibility. Research teams build credibility over time by providing insights that prove valuable. Stakeholders learn to trust research because it leads to better decisions. But credibility is fragile. When research based on poor participants leads to recommendations that don't pan out, stakeholders start questioning whether research is worth the investment. 
4. Slower velocity. Settling for mediocre participants to move faster actually slows you down. You run your study quickly with whoever you can find. The insights are muddy. You're not quite sure what to conclude. So you run a follow-up study to clarify. Or you make a decision with low confidence and have to course-correct later when it doesn't work. Meanwhile, teams that spend time getting quality participants upfront get clear insights the first time. They make decisions confidently and move forward quickly because they trust what they learned. The bottleneck isn't the time spent recruiting quality participants. It's the back-and-forth that comes from unclear results based on poor participants.

‍

‍

‍

What do we really mean by quality participants? 

‍

‍

When you're under pressure to deliver research quickly, it's tempting to view participants as interchangeable. You need 8 people. Any 8 people who vaguely fit the criteria will do. But that’s not actually the case at all. The whole point of user research is to understand your specific users. Their context, their mental models, their workflows, their pain points. Generic "users" don't exist. There are only specific people with specific needs trying to accomplish specific things. If the participants in your study don't actually represent your target users, you're not doing research. You're doing work that looks like research but doesn't provide real insights. When we say quality participants we mean: 

‍

1. They match your target criteria.  This seems obvious, but it's where most compromises happen. Every compromise in targeting dilutes the relevance of your insights. Quality participants don't just technically qualify. They deeply represent the actual people you're designing for.
2. They're engaged and thoughtful. A quality participant shows up prepared, gives full attention during the session, thinks carefully about questions, and provides detailed responses based on real experience. Engagement matters as much as targeting. A perfectly targeted participant who phones it in provides almost no value.
3. They show up. Seems basic, but no-shows are a massive problem. Quality participants honor their commitments. Consistent show rates mean you can actually plan research without padding your schedule with backup participants and hoped-for reschedules.
4. They're honest. Participants who tell you what they think you want to hear are worse than useless. You need people who'll be direct about confusion, frustration, and problems. Quality participants don't try to be nice or avoid hurting feelings. They give genuine feedback even when it's critical.

‍

‍

‍

The panel problem

‍

‍

Many teams rely on user research panels, databases of people willing to participate in studies for compensation,  which are often limited by the platform that they’ve purchased to one, proprietary panel for their research. Panels solve the recruitment problem by providing quick access to participants. But panels come with significant limitations.

‍

1. You're limited to who's in the panel. Need product managers at Series B startups in fintech? Need parents of children with specific developmental needs? If they're not in the panel, you can't reach them. You end up compromising your targeting to fit who's available rather than finding who you actually need.
2. Professional participants. Some people do user research studies regularly, almost as a side job. They're good at interviews. They know what researchers want to hear. They've done enough studies to unconsciously game the process. These "professional participants" might give you data, but they don't represent typical users. Their feedback is shaped by their experience participating in dozens of studies.
3. Quality inconsistency.  Panel quality varies dramatically. Some panels carefully vet participants and maintain high standards. Others will provide anyone who roughly matches your screener to hit the numbers you've requested. 

‍

When you're locked into a single panel provider, you're stuck with whatever quality standards they maintain.

‍

‍

‍

The panel ecosystem approach

‍

‍

The alternative to depending on a single panel is having access to multiple sources for participants. This means you're not limited by one panel's database. When you need specific, hard-to-reach audiences, you can access specialized panels that focus on those groups. When you need B2B professionals, you use networks that focus on business users. When you need consumers with specific characteristics, you access consumer panels with better targeting. The ecosystem model provides flexibility, better matching, and higher quality because you're not forcing every recruitment need through the same funnel. By the way, this is the way Optimal has intentionally chosen to offer participant recruitment via our platform for our customers (a panel ecosystem approach). 

‍

‍

‍

What changes when recruitment isn't the constraint

‍

‍

Imagine recruitment takes two days instead of two weeks. Imagine you can specify exactly the targeting you need and trust you'll get quality participants who match. How does your research change?

‍

1. You run more studies. When recruitment isn't a weeks-long process, research becomes more viable for smaller questions. More research means more informed decisions across the board.
2. You're more rigorous about targeting. When getting participants is easy, you don't have to compromise on criteria. You can be specific about exactly who you need and actually get them. Your insights become more reliable because they're based on truly representative participants.
3. You test more variations. Instead of showing 5 participants one design and hoping it works, you can test multiple variations with appropriate sample sizes for each. You can run A/B comparisons. You can validate results across different user segments. Better participant access enables more sophisticated research.
4. You move faster. Your timeline shrinks dramatically when recruitment isn't the bottleneck. Research becomes a viable input for time-sensitive decisions, not just long-term strategic work.

‍

Poor participant quality isn't a minor annoyance. It's the difference between research that drives confident decisions and research that creates false confidence in bad decisions. Quality in, quality out isn't just a principle. It's the foundation that determines whether your research is worth doing at all. 

‍

The recruitment bottleneck is real. But it's solvable. Teams that solve it don't just do more research. They do research that's actually worth acting on.

‍