The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Distill MCP listing page.
An MCP server that connects any MCP-compatible client to Distill, converting local documents to clean, token-efficient Markdown before the LLM reads them. Typical token reduction is 40–80% compared to raw document text, letting the model fit more content into its context window and reason over it faster.
Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any other MCP client that supports tool calling.
| Lightweight | Full (Docker) | |
|---|---|---|
| Requires Docker | No | Yes |
| DOCX, XLSX, PPTX, native PDF, HTML | Yes | Yes |
| Scanned PDF (OCR) | No | Yes |
| Audio (MP3, WAV, etc.) | No | Yes |
| Quality score | No | Yes |
| Install time | ~2 min | ~10 min |
Lightweight needs only Python and pip. Full needs Docker with the Distill service running. See the setup guides for details.
No global install required:
Then configure Claude Desktop — see Lightweight setup or Full setup for step-by-step instructions.
Add the server to your claude_desktop_config.json.
Lightweight mode — macOS / Linux:
Lightweight mode — Windows:
Full mode — all platforms:
Full config key reference is in the setup guides: Lightweight | Full
Paste this into your project's CLAUDE.md so Claude knows how to use the
tool automatically. Copy the block below as-is:
The snippet is also available in docs/CLAUDE.md-snippet.md.
| Category | Extensions | Lightweight | Full |
|---|---|---|---|
| Microsoft Word | .docx, .doc, .odt | Yes | Yes |
| Microsoft Excel | .xlsx, .xlsm, .csv | Yes | Yes |
| Microsoft PowerPoint | .pptx, .ppt | Yes | Yes |
| PDF (native text) | .pdf | Yes | Yes |
| PDF (scanned/OCR) | .pdf | No | Yes |
| HTML | .html, .htm | Yes | Yes |
| Audio | .mp3, .wav, .m4a, .flac, .ogg | No | Yes |
| EPUB | .epub | No | Yes |
| JSON | .json | No | Yes |
| SQL | .sql | No | Yes |
| WSDL | .wsdl, .wsd | No | Yes |
All processing happens locally. In lightweight mode, documents are converted by the distill-core Python library on your machine — no data leaves your computer. In full mode, documents are sent to the Distill Docker service running locally on your machine — no data is sent to external services.
Distill — document-to-Markdown conversion engine.
MIT