How Your AI Assistant Can Actually Do Things With Your Files: Not Just Talk About Them

July 25, 2026

MCP stands for Model Context Protocol. It's an open standard that lets AI assistants like Cursor and VS Code call external tools: not just talk about them, but actually use them.

The Problem

AI assistants are great at generating text. But they can't run Python on your actual file, score data quality, or build a chart that proves the number. They can tell you how to do it, but they can't do it for you. getqueryly can.

How MCP Works

MCP is like a USB port for AI. Instead of building custom integrations for every AI platform, you build one MCP server and every compatible AI assistant can use it.

Here's the flow:

You connect an AI assistant to an MCP server (like getqueryly)
The AI discovers what tools are available
When you ask it to do something, it picks the right tool
It calls the tool, gets the result, and gives it to you

A Real Example

Say you need to know what is driving revenue. With getqueryly's MCP server, you just say in Cursor or VS Code:

Analyze /tmp/sales.csv: what is my best product by revenue and show a bar chart

Your assistant calls getqueryly's ds_upload then ds_query, which runs Python on your actual file and returns the chart plus the numbers. You get the answer without leaving your chat.

What Makes getqueryly Different

Most MCP servers are simple wrappers. getqueryly has 20 tools covering the full data lifecycle:

Data upload and query: upload any file (CSV, Excel, PDF, JSON and more), then ask in plain English and get real Python results with charts
Quality and insights: health check (2 Makes), insights (3 Makes), smart test picker (1 Make), dashboard (2 Makes), elasticity and graph (1 Make each)
Reports and visuals: multi-analyst swarm quick 5 or full 8, report 3, visuals 2, diagram and infographic 1 each
Everyday helpers: chat 1, web search 2, Kaggle search free, plus usage and costs tools to check your balance

And every tool uses the same Makes cost system as the web UI. No separate billing, no surprises.

How to Connect

Add this to your AI assistant config:

{
  "mcpServers": {
    "getqueryly": {
      "url": "https://getqueryly.com/mcp/sse",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Get your API key at getqueryly.com: sign in, go to Settings - API Keys, generate one with a name and expiry, then copy once. Works with one header X-API-Key for both REST and MCP at https://getqueryly.com/mcp/sse.

The Bigger Picture

MCP is becoming the standard for AI tool integration. Anthropic open-sourced it, and it's now managed by a neutral foundation alongside OpenAI's agent standard. This means it's going cross-lab, not staying locked to one company.

For developers, this means: build one MCP server, and every AI assistant can use your tools. For users, this means: your AI can actually do things, not just talk about them.

Try getqueryly