# IterableData

Give an agent tools to read and convert files across many data formats, one record at a time. Handy when nested structures need to stay intact.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 37
- Author: datenoio
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/datenoio/iterabledata
- Updated: 2026-08-20
- HTML: https://affpapa.org/en/nevibecode/mcp/iterabledata

## What it does

IterableData lets an agent inspect and transform data files in formats such as CSV, JSON, Parquet, and XML. It processes records through an iterator-based interface and keeps nested structures intact. Ask it to identify a file’s format or convert a group of files.

In Claude Code, connect the server with `claude mcp add iterabledata -- uvx iterabledata`. The project description also gives `iterable-mcp` as the launch command after installing `iterabledata[mcp]`. Format detection can use a filename or file contents, and compressed files are supported. Malformed input raises a typed error by default, so it won’t be silently treated as an empty dataset.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add iterabledata -- uvx iterabledata
```
uvx runs the command named after the package; if the README names another one, use uvx --from iterabledata <command>

### Codex

**Platform CLI**
```bash
codex mcp add iterabledata -- uvx iterabledata
```
uvx runs the command named after the package; if the README names another one, use uvx --from iterabledata <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "iterabledata": {
            "command": "uvx",
            "args": [
                "iterabledata"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from iterabledata <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "iterabledata": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "iterabledata"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from iterabledata <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add iterabledata uvx iterabledata
```
uvx runs the command named after the package; if the README names another one, use uvx --from iterabledata <command>

## When to use it
- read records from a file with an unknown format
- convert CSV records to JSONL
- batch-convert files in a directory
- inspect nested fields in a data file

## Example prompts
- Identify the format of `data.bin` and read its records.
- Convert the CSV files in this folder to JSONL.
- Show the nested fields in `events.json`.

## Similar
- [query](https://affpapa.org/en/nevibecode/skills/query.md) — skill · 1400 installs
- [read-file](https://affpapa.org/en/nevibecode/skills/read-file.md) — skill · 1200 installs
- [jDataMunch MCP](https://affpapa.org/en/nevibecode/mcp/jdatamunch-mcp.md) — MCP server · ★ 82
- [explore-data](https://affpapa.org/en/nevibecode/skills/explore-data.md) — skill · 5900 installs
- [elasticsearch-ingest](https://affpapa.org/en/nevibecode/skills/elasticsearch-ingest.md) — skill · 1000 installs
- [ae-data-integration](https://affpapa.org/en/nevibecode/skills/ae-data-integration.md) — skill · 606 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md