# Mdkit

> Convert documents (PDF, Office, HTML) into clean, LLM-ready Markdown and JSON.

## API

- Base URL: `https://api.mdkit.online` — send API requests there.
- [API reference](https://mdkit.online/docs): interactive; machine-readable OpenAPI spec at https://api.mdkit.online/openapi.json.
- [Pricing](https://mdkit.online/pricing): Free plus Essential, Scale plans; monthly credits reset each cycle.
- Auth: send an `X-API-Key` header (create keys after signing in).
- Anonymous requests work at a lower, IP-based rate limit.
- [Health](https://api.mdkit.online/health): liveness probe.

## MCP

- The Model Context Protocol surface is served at `https://api.mdkit.online/mcp` (streamable HTTP, JSON).
- `tools/list` is open for discovery; tool calls use the same key + credit tier as REST.
- [Install in your AI client](https://mdkit.online/connect): copy-paste and one-click setup for Claude Code, Cursor and VS Code.

## Guides

- [Convert PDF to Markdown with one API call](https://mdkit.online/guides/pdf-to-markdown): Turn a PDF into clean Markdown with a single curl or Python call to the mdkit REST API. No signup needed for small files.
- [Convert Word (DOCX) to Markdown](https://mdkit.online/guides/docx-to-markdown): Convert a Word document to Markdown via the mdkit REST API — headings, lists and tables come out as clean Markdown structure.
- [Convert PowerPoint (PPTX) to Markdown](https://mdkit.online/guides/powerpoint-to-markdown): Extract slide text from a PowerPoint deck as Markdown with one mdkit API call — useful for feeding decks into an LLM or search index.
- [Convert Excel (XLSX) to Markdown tables](https://mdkit.online/guides/excel-to-markdown): Convert Excel spreadsheets to Markdown tables with the mdkit API — a table an LLM can actually read, without cell-by-cell parsing code.
- [HTML to Markdown over a REST API](https://mdkit.online/guides/html-to-markdown): Strip markup, keep meaning: convert HTML to clean Markdown via the mdkit API, or paste it into the free browser tool — no signup.
- [Turn a web page into LLM-ready Markdown](https://mdkit.online/guides/webpage-to-markdown): Fetch a page with curl, convert the HTML to Markdown with the mdkit API — a two-line pipeline for feeding web content to an LLM.
- [Async conversion jobs with polling and webhooks](https://mdkit.online/guides/async-jobs-and-webhooks): Convert big or complex documents asynchronously: submit a job, poll its status or get a signed webhook, then fetch Markdown or JSON output.
- [Use mdkit from Claude and other agents via MCP](https://mdkit.online/guides/mcp-for-agents): mdkit ships an MCP server: agents convert documents to Markdown with the convert_document tool — same limits and credits as the REST API.
- [A RAG ingestion pipeline on clean Markdown](https://mdkit.online/guides/rag-ingestion): Convert mixed real-world documents to Markdown first, then chunk by headings — the simplest reliable RAG ingestion pattern, shown in Python.
- [Structured JSON output for document layout](https://mdkit.online/guides/json-output): Async mdkit jobs also produce a structured JSON document — fetch it with format=json when you need layout and structure, not just text.

## mdkit vs alternatives

- [mdkit vs Jina Reader](https://mdkit.online/compare/mdkit-vs-jina-reader): Jina Reader turns URLs into markdown for LLMs; mdkit converts the files you upload — PDF, Office, HTML — into Markdown and JSON. When each fits.
- [mdkit vs Firecrawl](https://mdkit.online/compare/mdkit-vs-firecrawl): Firecrawl crawls and scrapes websites into LLM-ready data; mdkit converts uploaded documents into Markdown and JSON. Different jobs — compared.
- [mdkit vs Docling](https://mdkit.online/compare/mdkit-vs-docling): Docling is the open-source document conversion library mdkit's async lane runs. Self-host it yourself, or let mdkit run it behind a simple API.
- [mdkit vs MarkItDown](https://mdkit.online/compare/mdkit-vs-markitdown): MarkItDown is Microsoft's open-source file-to-markdown converter — and mdkit's sync engine. Library vs hosted API with jobs, MCP and limits.
- [mdkit vs Unstructured](https://mdkit.online/compare/mdkit-vs-unstructured): Unstructured is an ETL platform for LLM data with connectors and enterprise features; mdkit is a small document-to-Markdown API. Compared honestly.

## About

- [About](https://mdkit.online/about)
- [Privacy](https://mdkit.online/privacy)
- [Terms](https://mdkit.online/terms)
- [Impressum](https://mdkit.online/imprint)