# pdf-toolkit-mcp

pdf-toolkit-mcp — an MCP server with 22 tools to read, build, encrypt and merge PDFs. Renders pages to images so the model can read scanned documents with no text layer.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12 repo stars
- Author: AryanBV
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/AryanBV/pdf-toolkit-mcp
- Updated: 2026-07-22
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/pdf-toolkit-mcp

## What it does

The server reads and writes PDFs: it pulls text and metadata, fills and flattens forms, builds documents from Markdown or structured data, overlays QR codes, encrypts with AES-256, splits, merges and reorders pages. The `pdf_render_pages` tool rasterizes pages so a vision model can read scans or PDFs with no extractable text. Merge and split operations keep AcroForm fields instead of dropping them; when names collide, the server namespaces each source.

Engines run on WASM and JavaScript, so native dependencies and a compiler are not required. Launch with a single `npx` command on Node 20 and later. Works offline, no API keys.

There are 22 tools: six for reading (`pdf_extract_text`, `pdf_get_metadata`, `pdf_get_form_fields`, `pdf_to_markdown`, `pdf_search`, `pdf_compare`), eight for manipulation (`pdf_merge`, `pdf_split`, `pdf_delete_pages`, `pdf_reorder_pages`, `pdf_rotate_pages`, `pdf_flatten`, `pdf_encrypt`, `pdf_add_page_numbers`, `pdf_embed_qr_code`) and a set for creating new documents.

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

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add pdf-toolkit-mcp -- npx -y @aryanbv/pdf-toolkit-mcp
```

### Codex

**Platform CLI**
```bash
codex mcp add pdf-toolkit-mcp -- npx -y @aryanbv/pdf-toolkit-mcp
```

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add pdf-toolkit-mcp npx -y @aryanbv/pdf-toolkit-mcp
```

## When to use it
- read a scanned PDF with no text layer
- merge multiple PDFs with forms and preserve fields
- encrypt a document with AES-256 and an owner password
- build a PDF from Markdown or structured data
- fill a form and flatten it into static content

## Example prompts
- Pull text from the first ten pages of `report.pdf`
- Merge `invoice.pdf` and `contract.pdf`, save to `merged.pdf`
- Render pages 2 through 5 of `scan.pdf` to PNG so I can read what's there

## Similar
- [pdf-tools](https://affpapa.org/en/nevibecode/skills/pdf-tools.md) — skill · 186 installs
- [pdf-to-markdown](https://affpapa.org/en/nevibecode/skills/pdf-to-markdown.md) — skill · 870 installs
- [oma-pdf](https://affpapa.org/en/nevibecode/skills/oma-pdf.md) — skill · ★ 1472 repo stars
- [PDF Generator API](https://affpapa.org/en/nevibecode/mcp/pdf-generator-api.md) — MCP server · 346 installs
- [PDF Form Filler](https://affpapa.org/en/nevibecode/skills/pdf-form-filler.md) — skill · 4900 installs
- [pdf](https://affpapa.org/en/nevibecode/skills/nous-research-pdf.md) — skill · 283 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
