How do I install Markitai?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Markitai need an API key?

The publisher lists these environment variables: MODEL, MARKITAI_HOME.

What transport does Markitai use?

Markitai runs locally over stdio.

When was Markitai last checked?

Last checked 2026-11-09. Convert documents, images and web pages to clean Markdown, for agents: single, URL and batch tools.

Markitai MCP server

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

uvx markitai==2.3.2

Credentials from the publisher

MODEL — provider/model for --llm enhancement, e.g. gemini/gemini-flash-lite-latest; with the matching API key env var set
MARKITAI_HOME — Markitai's configuration, cache and model directory (default ~/.markitai)

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1MODEL=<value> MARKITAI_HOME=<value> claude mcp add io.github.ynewtime-markitai -- uvx markitai==2.3.2

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "io.github.ynewtime-markitai": {4      "command": "uvx",5      "args": [6        "markitai==2.3.2"7      ],8      "env": {9        "MODEL": "<value>",10        "MARKITAI_HOME": "<value>"11      }12    }13  }14}

claude_desktop_config.json

Local · pypiPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 2.3.2
API key

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

Markitai

Opinionated Markdown converter with native LLM enhancement support.

Multi-format: DOCX, PPTX, XLSX, PDF, EPUB, EML, TXT, MD, images (JPG/PNG/WebP), and URLs → clean Markdown; legacy .doc/.ppt via the legacy extra
LLM enhancement: format cleaning, frontmatter metadata, and vision analysis of embedded images, all through litellm, so any provider works (OpenAI, Anthropic, Gemini, local CLIs, and more)
Batch processing: concurrent conversion with progress display and --resume for interrupted jobs
OCR: scanned PDFs and images via local RapidOCR (optional extra, see below), or --ocr --llm to have the vision model read the page images directly (VLM-OCR)
Web fetching: static HTTP with cache revalidation, or Playwright rendering for JS-heavy pages
Local web workspace: upload files or folders, submit URLs, configure LLM providers, compare results, retry failures, and revisit conversion history. CLI runs can opt in to that history too, with --record-history

Docs: https://markitai.dev

Install

Guided installer (recommended). It installs Python and uv if they are missing, lets you pick extras and the Playwright browser, and offers a mirror when the default index is unreachable. Bilingual (EN/中文).

# Linux/macOS
curl -fsSL https://markitai.dev/setup.sh | sh
# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://markitai.dev/setup.ps1 | iex"

Already have Python 3.11–3.13? Install the package on its own and run the two setup steps yourself:

uv tool install markitai     # or: pipx install markitai
markitai doctor              # check core and optional capabilities
markitai init                # config and LLM provider

On Windows on Arm, add --python cpython-3.13-windows-x86_64: some libraries markitai needs have no ARM64 build, so it runs on an emulated x64 Python (setup.ps1 does this for you).

Browser rendering needs the browser extra, then Chromium:

uv tool install "markitai[browser]" --force
markitai doctor --fix

Both routes install markitai and the shorter mkai alias.

Extras

Extra	Enables
`browser`	Playwright rendering for JS-heavy pages
`claude-agent`	Claude Agent SDK as an LLM provider
`copilot`	GitHub Copilot SDK as an LLM provider
`extra-fetch`	curl-cffi HTTP client (better anti-bot compatibility)
`heif`	HEIC/HEIF/AVIF image input
`legacy`	Legacy Office conversion (`.doc`/`.ppt`) via the anydoc Rust backend
`mcp`	Bundled `markitai-mcp` server for AI agents (Model Context Protocol)
`ocr`	Local OCR for scanned PDFs and images (`--ocr`)
`serve`	Local web workspace and REST API
`svg`	SVG rasterization via cairosvg
`all`	Everything above

ocr is opt-in because it pulls in ~160MB of models. The guided installer asks whether you want it, and markitai doctor prints the install command when it is missing:

uv tool install "markitai[ocr]" --force

Launch the local web workspace with:

uv tool install "markitai[serve]" --force
markitai serve

Quick start

markitai document.pdf -o out/            # convert a file
markitai https://example.com -o out/     # convert a URL
markitai ./docs -o out/                  # batch convert a directory
markitai ./docs -o out/ --json           # machine-readable results for automation
markitai https://example.com --no-remote-fetch -o out/  # local URL extraction only
markitai doctor                          # check dependencies and configuration

For LLM enhancement, export any supported provider key. markitai picks the model up from the environment; you don't need a config file:

export GEMINI_API_KEY=...                # or OPENAI_/ANTHROPIC_/DEEPSEEK_/OPENROUTER_API_KEY
markitai document.pdf -o out/ --llm      # clean formatting + generated frontmatter
markitai document.pdf --preset rich      # LLM + alt text + descriptions + screenshots
markitai init                            # or configure it interactively, once

MCP server

markitai-mcp exposes conversion to AI agents over the Model Context Protocol with four tools: convert_document, convert_url, batch_convert, job_status. There is nothing to install, since uvx runs it on demand, and large outputs land on disk instead of in the model context. For Claude Code:

claude mcp add markitai -- uvx --from "markitai[mcp]" markitai-mcp

The MCP guide covers other clients, LLM enhancement and batch jobs. markitai mcp starts the same server through the CLI itself, which is how the MCP Registry lists it.

Documentation

Getting started: install, first conversion, output layout, supported formats
CLI reference: every command and flag
Configuration: config file, environment variables, LLM providers, every setting
Fetch policy: the URL strategy cascade, domain profiles, what stays local
Output profiles: rag, obsidian and okf output shaping
Web workspace: markitai serve, its history and REST API
Python API: convert() and aconvert() as a library
Conversion performance: measured local-conversion results and how to reproduce them
Why Markitai: how it compares with markitdown, docling and anydoc

Contributors start at CONTRIBUTING.md.

How markitai compares

Two of the tools we compare markitai with are also its dependencies: markitdown converts the Office formats, and anydoc handles legacy .doc/.ppt behind markitai[legacy]. Against them and docling, markitai gives up ecosystem reach, ML document-structure models and dependency-free speed, and gets a built-in LLM pipeline, live web fetching and a local workspace in return. The feature-by-feature table lives in Why Markitai.

License

markitai's own source code is MIT.

The default installation is not uniformly MIT, because the PDF engine is not. The PyMuPDF packages pymupdf, pymupdf-layout and pymupdf4llm come from Artifex Software and are dual-licensed under AGPL-3.0 or a commercial licence from Artifex. They are required dependencies: PDF conversion does not work without them. Running the CLI on your own machine, or a markitai serve instance only you talk to, carries no AGPL obligation. Redistributing the combined work, or offering it to other people over a network, does.

NOTICE carries the full terms, the rest of the dependency licensing, and the attribution for the code markitai ports from defuddle (MIT) and marker (Apache-2.0).