oxidize-pdf MCP Server

Rust-powered PDF library for Python. Generate, parse, split, merge, and manipulate PDFs with native performance. Ships with a built-in MCP server so AI agents can work with PDFs out of the box. Its 12 documented tools cover pdf, extract. It runs locally over stdio via the published package.

People connecting this server to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-20 · ★ 4 · #107 OF 848 MAINTAINED OTHER · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install oxidize-pdf MCP Server

before you install - you'll need

Set OXIDIZE_WORKSPACE before connecting.

Claude Code

claude mcp add bzsanti-oxidize-python -- uvx oxidize-pdf

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "bzsanti-oxidize-python": {
      "command": "uvx",
      "args": [
        "oxidize-pdf"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package oxidize-pdf - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.bzsanti is GitHub-verified and matches the repo owner

03 · What oxidize-pdf MCP Server can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can read metadata - page count, version, encryption status, title, author, extract text from all pages or a specific page, convert to markdown, chunks, or RAG-optimized format, and create a new PDF with optional metadata.

Capability map

Tools grouped from the project's README - what oxidize-pdf MCP Server lets an agent do.

Pdf

8 tools - e.g. Read metadata - page count, version, encryption status, title, author; Convert to markdown, chunks, or RAG-optimized format; Create a new PDF with optional metadata

read_pdf · convert_pdf · create_pdf · save_pdf · annotate_pdf · manipulate_pdf…

Extract

2 tools - e.g. Extract text from all pages or a specific page; Extract structured entities from pages

extract_text · extract_entities

create & write

1 tool - e.g. Add pages, text, and graphics to a session

add_content

Manage

1 tool - e.g. Create, fill, read, and validate form fields

manage_forms

Latest releases

v0.18.0 · 2026-08-20

Release v0.18.0 · Summary · Updates the bundled oxidize-pdf core from =4.3.0 to =4.6.0 and exposes · the new parser-side font-resolution, Type 3 glyph, and bounded in-memory image · extraction APIs in Python. · Added…

v0.17.0 · 2026-08-14

Release v0.17.0 · Summary · Updates the bundled oxidize-pdf core from =4.2.0 to =4.3.0 and exposes · its opt-in visual reading-order extraction in Python. The release also inherits · the core's correctness fixes for…

v0.16.0 · 2026-07-22

Release v0.16.0 · Summary · Exposes the advanced shading surface added in oxidize-pdf core 4.1.0 · (upstream #407) and bumps the bundled core from =4.1.0 to =4.2.0. Three · new classes - GouraudVertex…

04 · Who maintains oxidize-pdf MCP Server

oxidize-pdf MCP Server is maintained by bzsanti. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

category
other - ranked #107 of 848 actively-maintained other servers as of 2026-08-25.
release cadence
10+ releases in the last 90 days (latest 2026-08-20)
registry
io.github.bzsanti/oxidize-pdf-mcp (active, first published 2026-03-30 · 13 versions)
packages
pypi:oxidize-pdf

06 · oxidize-pdf MCP Server FAQ

Is oxidize-pdf MCP Server still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-20 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

What can oxidize-pdf MCP Server do?

With this server connected, an agent can read metadata - page count, version, encryption status, title, author, extract text from all pages or a specific page, convert to markdown, chunks, or RAG-optimized format, and create a new PDF with optional metadata.

How do I install oxidize-pdf MCP Server?

Run `uvx oxidize-pdf`. The README documents one environment variable (OXIDIZE_WORKSPACE) to set first. Set OXIDIZE_WORKSPACE before connecting. You can also paste the ready-made client config above.

Does oxidize-pdf MCP Server run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to oxidize-pdf MCP Server