# IterableData

> IterableData is an open-source MCP server for analytics and data. Stream, inspect and convert data files in 100+ formats from an AI assistant. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted
- **Website:** https://datenoio.github.io/iterabledata/integrations/MCP
- **Repository:** https://github.com/datenoio/iterabledata
- **MCP Registry name:** io.github.datenoio/iterabledata
- **Categories:** analytics and data, files and documents
- **Listing updated:** 2026-11-14

## About

The server wraps the IterableData Python library, which reads and writes records one row at a time through a single iterator API and keeps nested structures as dictionaries rather than flattening them. That covers formats from CSV, JSON Lines and XML to binary formats, compressed files, cloud URIs and lakehouse tables such as Delta Lake and Iceberg.

The MCP tools are mostly read-first: detect_format, describe_capabilities, read_sample, infer_schema, analyze_dataset and generate_documentation. The only writing tool, convert_file, refuses to write unless confirm=True. The documentation says to use read_sample with redact=True for sensitive data, and warns that generate_documentation may call external LLM APIs.

Install with pip install iterabledata[mcp] and run iterable-mcp over stdio, then point Cursor or Claude Desktop at it.

## Features

- **Format detection:** Identifies file type and compression from name or content.
- **Row sampling:** Reads sample rows, with a redact option for sensitive data.
- **Schema inference:** Infers a schema for a dataset.
- **Dataset analysis:** Summarises a dataset's structure.
- **Gated conversion:** Converts files only when confirm=True is passed.
- **Documentation generation:** Builds dataset documentation, possibly via external LLM APIs.

## Good for

- Peek at an unfamiliar data file without loading it all
- Convert a CSV to Parquet with confirmation
- Infer a schema for an XML or JSON Lines export
- Document a dataset before sharing it

## Install

### Claude Code (Terminal)

```sh
claude mcp add iterabledata -- uvx iterabledata
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "iterabledata": {
      "command": "uvx",
      "args": [
        "iterabledata"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "iterabledata": {
      "command": "uvx",
      "args": [
        "iterabledata"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "iterabledata": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "iterabledata"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "iterabledata": {
      "command": "uvx",
      "args": [
        "iterabledata"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "iterabledata": {
      "command": "uvx",
      "args": [
        "iterabledata"
      ]
    }
  }
}
```

## Tools

- `detect_format`: Detects file format and compression.
- `describe_capabilities`: Describes what a format supports.
- `read_sample`: Reads sample rows, with optional redaction.
- `infer_schema`: Infers a dataset schema.
- `analyze_dataset`: Analyses a dataset.
- `generate_documentation`: Generates documentation for a dataset.
- `convert_file`: Converts a file; writes only with confirm=True.

## FAQ

### How do I install it?

pip install iterabledata[mcp], then run iterable-mcp.

### Can it overwrite files?

Writes happen only through convert_file with confirm=True.

### How do I avoid exposing sensitive rows?

Use read_sample with redact=True.

### Does it send data elsewhere?

generate_documentation may call external LLM APIs when used.

### Is IterableData free?

Yes. IterableData is open source, so you can use and self-host it for free.

### How do I add IterableData to Claude Code?

Run this command in your terminal: claude mcp add iterabledata -- uvx iterabledata

### What are the best alternatives to IterableData?

The closest alternatives to IterableData are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Tapetide - Indian Stock Market MCP, World Monitor and CompanyData.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [ASTra](https://ai-powered.com/mcp/astra): ASTra is a freemium MCP server for files and documents.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [Quantivex Research](https://ai-powered.com/mcp/quantivex-research): Quantivex Research is a free MCP server for finance and payments.

---
Source: https://ai-powered.com/mcp/iterabledata
