# ReadAnyDoc

ReadAnyDoc — an MCP server for Claude Code that converts PDFs, scans, and Office files into Markdown or typed schema fields with bounding boxes. Runs document pages through vision models.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 11 repo stars
- Author: arpitpatel25
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/arpitpatel25/ReadAnyDoc
- Updated: 2026-11-16
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/readanydoc

## What it does

ReadAnyDoc processes document pages using vision models (Claude Haiku 5.5 by default) and extracts tables, Markdown text, or schema fields with exact bounding boxes for every value. Its layout engine identifies block types, forms, headers, and footers.

Two execution modes are supported: full `engine` mode using local CPU layout models, or a minimal `model-only` mode. On its first run, the engine downloads roughly 200 MB of model weights, and optionally relies on system Tesseract.

Operation requires Python 3.12 and an active `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Environment variables: `ANTHROPIC_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add readanydoc -e ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY> -- uvx readanydoc
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from readanydoc <command>

### Codex

**Platform CLI**
```bash
codex mcp add readanydoc --env ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY> -- uvx readanydoc
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from readanydoc <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "readanydoc": {
            "command": "uvx",
            "args": [
                "readanydoc"
            ],
            "env": {
                "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from readanydoc <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "readanydoc": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "readanydoc"
            ],
            "env": {
                "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from readanydoc <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY> readanydoc uvx readanydoc
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from readanydoc <command>

## When to use it
- convert scanned documents and multi-page PDFs into clean Markdown
- extract invoice fields into structured schemas with exact bounding boxes
- process handwritten document pages using Claude Sonnet
- preserve complex table layouts without manual block cropping

## Example prompts
- Parse `invoice.pdf` and convert it into Markdown format
- Extract total amount and date from `statement.pdf` with citations
- Process scanned document `form.pdf` and extract all table blocks

## Similar
- [pdf-processing-pro](https://affpapa.org/en/nevibecode/skills/pdf-processing-pro.md) — skill · 5869 installs
- [liteparse](https://affpapa.org/en/nevibecode/skills/k-dense-ai-liteparse.md) — skill · 1700 installs
- [pdf-to-structured](https://affpapa.org/en/nevibecode/skills/pdf-to-structured.md) — skill · 149 installs
- [markitdown](https://affpapa.org/en/nevibecode/skills/julianobarbosa-markitdown.md) — skill · 1700 installs
- [paddleocr-doc-parsing](https://affpapa.org/en/nevibecode/skills/paddleocr-doc-parsing.md) — skill · 483 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
