MCP (Model Context Protocol)
Last updated 2026-06-14
Definition
MCP, the Model Context Protocol, is an open standard for connecting tools and data sources to AI clients like Claude or ChatGPT. A tool exposes typed actions over MCP, and the AI calls them safely. Quri ships a hosted MCP server, so you can ask your AI assistant about your metrics and Quri answers from your connected sources.
How to do this in Quri
- Run Quri’s hosted MCP server so your AI client can reach your metrics.
- Connect it inside an MCP-aware client like Claude or ChatGPT.
- Ask the assistant about your data; it calls Quri’s read tools over MCP.
- Quri returns answers scoped to your workspace, with operator tools gated by permission.
Frequently asked
- Why does MCP matter for analytics?
- It lets you keep working inside your AI assistant and still reach live product data. With Quri’s MCP server, you ask in chat and get answers from your real metrics, no separate dashboard.
- Is MCP access secure?
- Quri scopes every MCP call to your workspace and hides operator or cross-tenant tools unless your role allows them, so an assistant only sees what you are entitled to.