# oxidize-pdf MCP Server

Hands your agent 12 PDF tools: read metadata, pull text, build files, split, merge and fill forms. Runs locally over stdio.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: bzsanti
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/bzsanti/oxidize-python
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/oxidize-pdf-mcp-server

## What it does

Start it with `oxidize-mcp` and the agent talks to it over stdio. Twelve tools sit inside. `read_pdf` reports page count, version, encryption status, title and author. `extract_text` pulls text from every page or just one. `convert_pdf` turns a document into markdown, chunks or a RAG-friendly format. `create_pdf` and `save_pdf` write new files, with optional encryption on save. `manipulate_pdf` splits, merges, rotates, extracts, reverses and overlays pages. `manage_forms` creates, fills, reads and validates form fields, while `secure_pdf` handles encryption, permissions and signature checks. Two more tools, `extract_entities` and `analyze_pdf`, pull structured entities and validate structure, corruption and PDF/A compliance. The server also serves resources with session data and prompts for guided workflows.

Every path has to resolve inside a sandbox. `OXIDIZE_WORKSPACE` sets that root, and it defaults to `~/Documents/oxidize-mcp`. Point it somewhere else at launch if your PDFs live elsewhere — otherwise the first file outside the folder gets rejected.

You need Python 3.10+ and the extras install: `pip install "oxidize-pdf[mcp]"`. The base library ships without MCP, so skipping the brackets leaves you without a server. On Windows, install and start the server from the same Python environment or tool registration breaks.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add oxidize-pdf-mcp -- uvx oxidize-pdf
```
uvx runs the command named after the package; if the README names another one, use uvx --from oxidize-pdf <command>

### Codex

**Platform CLI**
```bash
codex mcp add oxidize-pdf-mcp-server -- uvx oxidize-pdf
```
uvx runs the command named after the package; if the README names another one, use uvx --from oxidize-pdf <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "oxidize-pdf-mcp-server": {
            "command": "uvx",
            "args": [
                "oxidize-pdf"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from oxidize-pdf <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "oxidize-pdf-mcp-server": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "oxidize-pdf"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from oxidize-pdf <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add oxidize-pdf-mcp-server uvx oxidize-pdf
```
uvx runs the command named after the package; if the README names another one, use uvx --from oxidize-pdf <command>

## When to use it
- read PDF metadata and page count
- extract text from one page or all of them
- merge several PDFs into one file
- split a document and pull out chosen pages
- fill in form fields and validate them

## Example prompts
- How many pages does `report.pdf` have?
- Extract the text from page 2 of `contract.pdf`
- Merge `part1.pdf` and `part2.pdf` into one file

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
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