# Unstructured Transform

Converts files and raw documents into parsed, chunked, and embedded records for AI agents. It handles over 60 formats without manual pipeline setup.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: Unstructured-IO
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Unstructured-IO/unstructured-mcp-integrations
- Updated: 2026-08-04
- HTML: https://affpapa.org/en/nevibecode/mcp/unstructured-transform

## What it does

The MCP server connects directly to `https://mcp.transform.unstructured.io` over streamable-HTTP. It takes in spreadsheets, image scans, emails, and PDFs across 60+ formats. Output arrives as partitioned text chunks with metadata and embeddings ready for vector search or agent memory.

The server exposes several tools for the workflow. Files go through `request_file_upload_url`, while processing starts via `start_transform_job` or `start_extraction_job`. It can also recommend schema definitions with `suggest_extraction_schema_for_file`. Progress checks and final payloads rely on `check_job_status` and `get_job_results`.

Clients lacking native remote MCP capabilities must connect via `npx mcp-remote`.

## Requirements
- Remote server: `https://mcp.transform.unstructured.io`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http transform https://mcp.transform.unstructured.io
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add unstructured-transform --url https://mcp.transform.unstructured.io
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "unstructured-transform": {
            "url": "https://mcp.transform.unstructured.io"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "unstructured-transform": {
            "type": "http",
            "url": "https://mcp.transform.unstructured.io"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http unstructured-transform https://mcp.transform.unstructured.io
```

## When to use it
- parse raw PDFs and scans into chunked text for RAG
- generate embeddings directly from document uploads
- draft extraction schemas for unstructured image or file data
- ingest spreadsheets and emails without external ETL pipelines

## Example prompts
- Upload `contract.pdf` and extract key clauses using a suggested schema
- Process `quarterly_results.xlsx` into embedded chunks for vector storage
- Check the status of transform job `job-9872` and fetch results

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40459
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27844
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49863

---
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