UserTesting Launches MCP Servers to Embed Human Insight Into AI Workflows
UserTesting has announced the availability of Model Context Protocol (MCP) Servers for its UserTesting and User Interviews platforms, enabling product, design, UX, and research teams to recruit participants, run studies, and retrieve customer feedback without leaving AI applications such as ChatGPT, Claude, and Figma Make. The combined participant network spans more than seven million people across 34 countries. Both servers are currently available in Early Access.
UserTesting announced on 25 September 2026 the availability of Model Context Protocol (MCP) Servers for both its UserTesting and User Interviews platforms, giving product, design, UX, and research teams direct access to customer insight from within AI applications including ChatGPT, Claude, Figma Make, and other MCP-compatible clients.
The two new servers connect to a combined participant network of more than seven million people across 34 countries, according to the company. Teams can use the servers to recruit participants, create and launch studies, retrieve customer feedback, and validate AI-generated concepts without leaving their AI workflow.
Jennifer Artabane, Vice President of Product Management at UserTesting, said the launch addresses a gap created by the accelerating pace of AI-assisted work. "AI has dramatically accelerated how teams generate ideas, designs, and content. Speed only creates value when it's grounded in real customer understanding," Artabane said. "With MCP servers for both UserTesting and User Interviews, we're bringing human insight directly into the AI workflows where decisions are made. Teams can move from asking AI what's possible to validating what actually works with real customers without breaking their creative flow."
The company described the broader context in its announcement: as organizations increasingly rely on AI to accelerate product development and design, AI trained on existing patterns tends to pull toward the familiar rather than the distinctive. According to UserTesting, the MCP servers are designed to close that gap by connecting AI-generated concepts with real human feedback.
Oli Mival, VP Product Strategy, Innovation and Experience at Picsart, provided a customer perspective. "At Picsart we've built an AI-powered product development lifecycle that gets from concept to shipped experience in a fraction of the time it used to take," Mival said. "UserTesting's MCP server lets us keep real people in that loop without slowing it down, so human insight is woven through every stage rather than a checkpoint we pass once. It means we're not just building fast; we're building the right things in the right way."
UserTesting said the launch reflects a broader shift in the product development lifecycle. Research and customer feedback are no longer a discrete phase, but an ongoing input woven throughout a compressed development cycle. The company stated the servers must also be accessible to AI agents, which it said are now doing a growing share of work that once required a person to open a separate tool.
Both MCP servers are currently available in Early Access and support ChatGPT, Claude, Figma Make, Gemini, and other MCP-compatible applications. UserTesting said additional capabilities for surfacing customer insight throughout AI workflows will continue to expand over time.
Prepared with AI assistance and reviewed by the editorial team.
