Introduction to MCP¶

The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external data sources, tools, and services. It defines a common language for how AI models discover and call the capabilities a system exposes, without a custom connector for each tool.

Qualytics runs an MCP server. Any compatible AI client, such as ChatGPT, Claude Desktop, Claude Code, Cursor, or VS Code, can connect to it and work with your data quality infrastructure through the same tools AgentQ uses. The client brings its own model and conversations, and Qualytics runs each tool call as you, with your permissions.

MCP and AgentQ¶

AgentQ is the assistant built into Qualytics, and it talks to an AI provider that your organization connects. The MCP server works the other way around: your own client talks to its own model and calls Qualytics only to run tools. AgentQ is not involved in that path, and no AI provider has to be configured in Qualytics. Both share the same tool catalog and the same permission checks. For everything the AI Assistants section covers, see the AI Assistants Overview.

Where to Start¶

Read How It Works first. It explains how a client, the Qualytics MCP server, and the model work together on a request, and what the model receives. From there:

• Connecting External AI Clients covers what you need before you start, and the setup for each company's clients.
• Examples shows requests you can make once a client is connected.
• Best Practices and Permissions cover keeping connections secure and what a client can do on your behalf.

Why MCP Matters for Data Quality¶

Traditional integrations between AI tools and data platforms require custom-built connectors, hardcoded API calls, and constant maintenance as APIs evolve. MCP standardizes this so any MCP-compatible AI client can connect to any MCP server and immediately discover its capabilities.

For data quality workflows, this means:

• Portability: The same Qualytics MCP server works with Claude Desktop, ChatGPT, Cursor, and any future MCP-compatible tool, without changes.
• Security: The MCP server enforces authentication and RBAC on every tool call. The LLM receives results through authenticated, permission-aware tools rather than connecting directly to your databases.
• Auditability: Every tool call is a discrete, logged action. You can see exactly what the AI did and why.
• Composability: Complex workflows emerge naturally from combining simple tools, driven by the LLM's reasoning rather than hardcoded orchestration logic.

See Also¶