# anymd

Converts PDF, office documents, web pages, and media into clean Markdown locally. Keeps AI agent context accurate without sending files to third-party services.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 1051
- Author: SylphxAI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/SylphxAI/anymd
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/anymd

## What it does

Built in native Rust, anymd converts files locally. No API key is needed. The tool handles documents page by page in parallel: it reconstructs multi-column text into logical reading order, recovers borderless tables, and inserts page citation anchors. Beyond PDF, it processes Word, Excel, PowerPoint, EPUB, web URLs, audio, and video files.

Running the server via npx requires Node 18 or newer. OCR and audio transcription depend on local engines like tesseract, ffmpeg, and bundled Qwen3-ASR, which download model files only after explicit opt-in.

The server protects context limits with token budgets and cursors. To isolate the server to a specific folder on your drive, use the `--allow-dir` flag.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add anymd -- npx -y @sylphx/anymd
```

### Codex

**Platform CLI**
```bash
codex mcp add anymd -- npx -y @sylphx/anymd
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "anymd": {
            "command": "npx",
            "args": [
                "-y",
                "@sylphx/anymd"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "anymd": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@sylphx/anymd"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add anymd npx -y @sylphx/anymd
```

## When to use it
- convert PDF files and office spreadsheets into Markdown
- parse borderless tables without breaking layout
- feed local document contents to an agent without external cloud calls
- search across mixed file formats in a single folder

## Example prompts
- Extract the financial table from page 4 of `report.pdf`
- Search for authentication details across the `docs/` folder
- Convert `presentation.pptx` into clean Markdown with front matter

## Similar
- [Reactive Resume](https://affpapa.org/en/nevibecode/mcp/reactive-resume.md) — MCP server · ★ 44874
- [Sui Knowledge Base (kapa.ai)](https://affpapa.org/en/nevibecode/mcp/sui-knowledge-base-kapaai.md) — MCP server · ★ 7784
- [Claude Code Ultimate Guide](https://affpapa.org/en/nevibecode/mcp/claude-code-ultimate-guide.md) — MCP server · ★ 6237
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5548
- [RevoGrid DataGrid MCP Pro](https://affpapa.org/en/nevibecode/mcp/revogrid-datagrid-mcp-pro.md) — MCP server · ★ 3450
- [Claude Code Explorer MCP](https://affpapa.org/en/nevibecode/mcp/codeaashu-claude-code-explorer-mcp.md) — MCP server · ★ 3409

---
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