Miro, the collaboration and context layer for the AI era, has reported more than 16 million calls to its MCP server since its launch in February 2026, with usage more than doubling since May. In September alone, MCP calls are on track to reach 6 million, showing momentum as teams embrace the canvas for AI collaboration.
Teams increasingly rely on AI to accelerate work from discovery and planning to design and code, yet most AI interactions happen in chat windows or static outputs that exist separately from the team's actual workspace. Miro's MCP server changes this by giving users a way to make output from AI tools visual, immediately editable, and accessible to the whole team on a shared canvas.
Miro user data shows Claude Desktop and Claude Code represent almost two-thirds of usage in August at 65%. ChatGPT has become the second-largest client, growing 71% in users between August and September. In total, 15 different AI clients have now connected via the MCP integration, including Microsoft Copilot, Gemini Enterprise, and Grok Build.
Further analysis demonstrates the Canvas is being leveraged as both an input and output for AI agents. 57% of August calls were Miro-to-code, where an agent reads a board and acts on it, and 41% were code-to-Miro, where agents generate boards, diagrams and layouts directly.
The demographic of users adopting MCP has shifted beyond engineering. MCP has jumped the developer niche with users in engineering and developer roles accounting for under a quarter of MCP users. Product, design, marketing, operations and project management together outnumber engineers roughly two to one, showing broad cross-functional adoption.
The pattern shows teams adopting Miro as the central interface for AI-assisted work, visualizing complex ideas across multiple formats on a collaborative canvas. With the canvas serving as both source and destination for agents, better ideas reach engineering faster as PMs turn thinking directly into requirements.
Teams are adopting Miro as the central interface for AI-assisted work. With 16 million MCP calls since its launch and adoption spreading across all job functions, the need for a workspace that supports how teams actually work—visual, shared, and endlessly editable—is clear as AI agents move closer to active work.
About Miro
Miro is the collaborative workspace where agents and teams converge to think, decide, and build together. As AI accelerates work, the challenge for organizations isn't doing more; it's turning individual output into scaled impact. Serving more than 100 million users across 250,000 customers, Miro's shared, secure canvas surfaces the context that empowers teams to solve harder problems, make better decisions, and move work forward faster. Founded in 2011, Miro currently employs 1,600 people in 13 hubs around the world.
