# flatmark

Converts PDF, Word, PowerPoint, Excel, and HTML files into clean Markdown through an MCP endpoint. Useful when your coding agent needs to read complex office docs or scanned pages.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: flatmark-dev
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/flatmark-dev/flatmark
- Updated: 2026-10-02
- HTML: https://affpapa.org/en/nevibecode/mcp/flatmark

## What it does

Small files up to 8 MB are processed directly in a single request using MarkItDown. When documents exceed this limit, flatmark routes files up to 25 MB or 200 pages into a Docling processing queue. That pipeline handles OCR extraction alongside table recognition, delivering Markdown plus structural JSON via signed webhooks or polling.

Hosting operates out of Germany. You can start without an account on the anonymous tier, though strict rate limits apply until you export a `FLATMARK_API_KEY`. The free plan includes 100 monthly credits without asking for payment card details.

## Requirements
- Remote server: `https://api.flatmark.dev/mcp/`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http markdown-converter https://api.flatmark.dev/mcp/
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add flatmark --url https://api.flatmark.dev/mcp/
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "flatmark": {
            "url": "https://api.flatmark.dev/mcp/"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "flatmark": {
            "type": "http",
            "url": "https://api.flatmark.dev/mcp/"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http flatmark https://api.flatmark.dev/mcp/
```

## When to use it
- convert Excel sheets and tables into Markdown
- extract text from scanned PDF documents via OCR
- turn PowerPoint presentations into structured text
- feed HTML pages into agent context as clean Markdown

## Example prompts
- Convert `specs.pdf` to Markdown using flatmark.
- Run OCR on `contract_scan.pdf` and extract all tables as Markdown.
- Turn `budget.xlsx` into a clean Markdown table.

## Similar
- [markitdown](https://affpapa.org/en/nevibecode/skills/julianobarbosa-markitdown.md) — skill · 1600 installs
- [pdf-to-markdown](https://affpapa.org/en/nevibecode/skills/pdf-to-markdown.md) — skill · 831 installs
- [paddleocr-doc-parsing](https://affpapa.org/en/nevibecode/skills/paddleocr-doc-parsing.md) — skill · 471 installs
- [markdown-converter](https://affpapa.org/en/nevibecode/skills/steipete-markdown-converter.md) — skill · 339 installs
- [kordoc](https://affpapa.org/en/nevibecode/mcp/kordoc.md) — MCP server · ★ 2816
- [anymd](https://affpapa.org/en/nevibecode/mcp/anymd.md) — MCP server · ★ 1055

---
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