Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@markitdown-ocr-mcp Convert the scanned PDF at ~/documents/report.pdf to Markdown."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server exposing OCR-enabled PDF → Markdown conversion to Claude Code.
MarkItDown + the official markitdown-ocr LLM-vision plugin, backed by a local
oMLX server running PaddleOCR-VL (or any OpenAI-compatible vision endpoint).
uv sync --group dev
uv tool install --editable .
claude mcp add markitdown-ocr-mcp --scope user -- ~/.local/bin/markitdown-ocr-mcpoMLX must be running (omlx start) with a vision model loaded.
Related MCP server: DocMistral MCP Server
inspect_pdf(path) — per-page classification (text / scanned / mixed / blank), no OCR
ocr_pdf(path, pages?, out_path?) — full hybrid conversion to Markdown; pages ("1-5,9") extracts only a page subset; out_path writes to file
omlx_models() — oMLX health check + available models + resolved OCR model
uv run pytest # unit + integration, no oMLX needed
uv run python scripts/smoke_omlx.py # live OCR smoke test (needs oMLX)
uv run python scripts/probe_mcp.py # end-to-end probe of the installed binaryVar | Default |
|
|
| auto-read from |
| auto-discovered from |
|
|
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
High-fidelity PDF to structured Markdown conversion and document field extraction.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/phatpham9/markitdown-ocr-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
