> For the complete documentation index, see [llms.txt](https://docs.aisuru.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aisuru.com/en/advanced-features/integrations/mcp/aisuru-mcp-which-ones-and-how-to-activate/6.-aisuru-data-analysis.md).

# 6. AIsuru Data Analysis

AIsuru Data Analysis is a JavaScript MCP hat can read and analyse files full of information. It lets your Agent run JavaScript/TypeScript code for complex analysis, processing, and business intelligence.

This MCP is useful for:

* Analyzing complex datasets
* Performing very precise calculations and aggregations
* Processing data in real time during conversations

## **What kind of files can it work with?**

It understands the most common data formats:

* **CSV (Comma-separated values)** – like a spreadsheet saved as a simple text file
* **TSV (Tab-separated values)** – similar to CSV, but with tabs instead of commas
* **JSON (JavaScript object notation)** – a structured data format often used by apps and websites

### **What can you ask it to do?**

Here are some examples:

* *"How many sales were made in August?"*
* *"Who are the top 5 best-performing salespeople?"*
* *"What's the total revenue this month?"*
* *"Filter only the orders that are still pending."*

If your data is in a file, you can upload it in chat (or give a publicly accessible URL) and ask **plain questions** to get **clear answers**: no technical skills needed on your end!

## Configuration parameters

This MCP doesn't require mandatory parameters in the basic configuration. The execution environment is provided automatically.

### Custom parameters

* **timeout**: maximum operation time (seconds)
* **allowedFormats**: Accepted file formats

```json
{
  "timeout": 120,
  "allowedFormats": ["json", "csv", "xlsx"]
}
```

## Important notes

* Code runs in an isolated environment
* Code can handle both simple expressions and complex code with variables and refactoring
* Always check memory and timeout limits before using this MCP for intensive analysis.