Sugo

Name: Sugo
Author: Muralnick

by Muralnickversion 0.1.2i★ –iRuns on your computer

Registry nameio.github.Muralnick/sugo

Install

Overview

Description from the maker (original English)

Local, offline conversion of PDFs, Office files and screenshots into compact Markdown.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Docs, sheets & office work

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
The registry lists no key to fill in.

You need

PyPIPython’s uv installed (for the uvx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "sugo": {
      "command": "uvx",
      "args": [
        "sugo-cli",
        "mcp",
        "--root"
      ]
    }
  }
}

Run this in your terminal

claude mcp add sugo -- uvx sugo-cli mcp --root

This one needs values on its command line, so copy the settings and fill them in.

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "sugo": {
      "command": "uvx",
      "args": [
        "sugo-cli",
        "mcp",
        "--root"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one needs values on its command line, so copy the settings and fill them in.

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "sugo": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "sugo-cli",
        "mcp",
        "--root"
      ]
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account Muralnick, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Docs, sheets & office worki

More stars than 0% of the other 3538 servers in this category
Published to the registry more recently than 100% of the other 3538 servers in this category
Basic checks equal to or better than 100% of the other 3538 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Sugo safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.1.2) reached the registry today.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: Agent-Native Calendar, Excel MCP Server, MCP Server for Excel

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Agent-Native Calendar

by BuilderIO

Agent-Native Google Calendar - manage events, sync, and public booking

Runs in the cloud★ 7,620MITUpdated 2 months ago

Install

Excel MCP Server

by haris-musa

Lets AI create and edit Excel files itself, including formulas, charts and PivotTables, without Excel installed.

Runs on your computer★ 4,276MITUpdated 7 days ago

Install

MCP Server for Excel

by sbroenne

Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.

Runs on your computer★ 847MITUpdated 4 days ago

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Sugo

Documents, reduced. Feed your LLM the sauce, not the water.

Quick start · What it does · Comparison · MCP · Roadmap · 🇮🇹 Italiano

🔒 100% local no cloud, no telemetry ✂️ Fewer tokens 33–38% with repeated headers, ~3% on real legal text 🧾 Nothing lost silently every removal is recorded 🪶 Light runs on 8 GB RAM, no GPU

Sugo turns PDFs, Office files, screenshots and images into clean, compact Markdown for RAG systems, AI agents and LLM chats. It removes what only costs tokens (repeated headers and footers, page numbers, hidden text, tracking parameters, app chrome around a screenshot) and keeps the content, the tables and the structure. Everything runs on your computer: no cloud API, no telemetry, nothing sent anywhere.

In Italian, *il sugo del discorso* means "the gist", and a *sugo* is a sauce you reduce until only the concentrated flavour remains. That is what Sugo does to your documents.

What it does

A small generated three-page PDF, as a plain text extractor gives it to your model (pages 1 and 3 look the same):

ACME S.p.A. - Annual Report 2025                Confidential

3.2 Revenue Revenue grew by 12% in the second half, driven by the export market. Details: https://acme.example/report?utm_source=newsletter&utm_medium=email Page 14 of 120

What sugo report.pdf prints:

ACME S.p.A. - Annual Report 2025

3.1 Costs

Costs fell by 3% thanks to the new suppliers. Details: https://acme.example/report

3.2 Revenue

Revenue grew by 12% in the second half, driven by the export market. Details: https://acme.example/report

3.3 Outlook

The board expects stable growth next year. Details: https://acme.example/report

The header is kept once instead of on every page; the page numbers, the repeated "Confidential" and the tracking parameters are gone; the text is the same. sugo stats measures the difference: 180 → 97 tokens, 46% saved on this small generated example; real documents with less page furniture save much less (see below). Every removal is recorded with the cleaner that made it and the reason, so you can always check what was dropped. Text that cannot be read is marked as illegible, never guessed.

Across a benchmark corpus in five languages, no text went missing in any document (on 3 screenshots the OCR misread a few characters, 1–7%). Savings depend heavily on the document:

Document	Tokens saved
Report with a running header, footer and page numbers	33–38%
Chat or code screenshot, Markdown vs. sending the image itself	94–98% cheaper (Claude, Gemini, OpenAI)
A real EU regulation from EUR-Lex, mostly substantive legal text	2.9–3.5%

And it stays fast on an ordinary computer, not just a new one: on a 2010 desktop with 2 cores and no GPU, a 100-page PDF converts in 3.6 s and a phone screenshot in 13.7 s (full numbers in TESTING).

How it compares

Measured against two well-known alternatives, on the same 31-document benchmark corpus (26 synthetic documents made by the Sugo project plus 5 real EU-regulation PDFs), with the same tokenizer and the same ground truth — full method, raw numbers and limits in docs/comparisons:

	Sugo	Docling	MarkItDown
Documents converted with nothing lost or garbled	28 / 31	25 / 31	14 / 31
OCR on chat/code screenshots	✅ no text missing; 1–7% character errors on 3 accented screenshots	⚠️ right words, wrong order on some chats	❌ empty output
Reads PDFs out of the box	✅	✅	❌ needs an extra
Real EU regulation PDF, every clause kept	✅	⚠️ 2 of 5 drop a clause	❌ every one drops 2–7

A tool that drops content also "saves" tokens on paper — that's data loss, not compression. Every number above is paired with what actually survived the conversion.

Fair caveats: the corpus is small and mostly synthetic, and it was built by the Sugo authors, so treat it as a sanity check, not a verdict. On the report PDFs Docling saves slightly *more* tokens than Sugo (about 38–48% vs 33–38%) without losing content; it is also several times slower on this corpus. Raw data and the full per-document table are in the linked comparison.

Status

[!NOTE]

v0.1.1 is out, on PyPI as sugo-cli (v0.1.0 was the first signed release). It is still 0.x: contracts may change, with notice, before 1.0. Releases are built reproducibly, with an SBOM, Sigstore attestations and PyPI Trusted Publishing.

Works today	Coming next
Native PDFs, DOCX, XLSX, PPTX, XML	Scanned-book cleaners, EPUB, email, web pages
Images and screenshots with local OCR (PNG, JPEG, WEBP)	Larger tables, `normal` and `quality` engine levels
Chat and code screenshot detection	Japanese, Chinese, Korean
Markdown, and JSON Lines chunks for vector databases	Interactive shell, guided setup
Token metrics per provider (`sugo stats`)	Background service and folder watcher
Command line, MCP server for agents, local web page	Work profiles and recipes
Interface and text rules in English, Italian, Spanish, French, German

See the roadmap for the full plan.

Quick start

Sugo needs Python 3.12, 3.13 or 3.14. The install is about 400 MB on disk, because the PDF library, the OCR engine and its models come with it. The easiest way to install it is with uv:

uv tool install sugo-cli

Or with pip:

pip install sugo-cli

If sugo is "not recognized" or "not found" after installing with pip, pip put it in a folder your system does not search. This happens on Windows when pip installs for your user only ("Defaulting to user installation"). Either install with uv tool install sugo-cli and run uv tool update-shell once, or add the folder pip names in its warning (on Windows, %APPDATA%\Python\Python3XX\Scripts) to your Path, then open a new terminal.

[!TIP]

The package is called sugo-cli because the name sugo on PyPI is held by an unrelated, empty project (a name transfer request is open). The installed command is still sugo; sugo-cli works too. Older instructions with sugo-cli[lite] still work: everything is now included by default.

To run the latest development version from source instead:

uv tool install git+https://github.com/Muralnick/sugo

Convert a file and print its Markdown:

sugo report.pdf

More things you can do:

sugo convert *.pdf -o out/            # one NAME.md per file, in out/

sugo convert report.pdf --chunks # chunks as JSON Lines, ready for RAG sugo stats screenshot.png # tokens saved, per LLM provider sugo clip # convert the screenshot in your clipboard sugo ui # open the local web page: drop a file, get Markdown sugo doctor # check the installation

Add --json for output a script can read.

Use it from an AI agent (MCP)

Sugo can serve agents such as Claude Code or Codex over MCP. It reads only inside the folders you name:

claude mcp add sugo -- sugo mcp --root ~/Documents

The agent gets two tools: convert_document and estimate_savings.

Uninstall

Remove the program the same way you installed it:

uv tool uninstall sugo-cli

Or, if you used pip:

pip uninstall sugo-cli

If you added Sugo to an agent, remove it there too, for example claude mcp remove sugo.

Uninstalling the program does not delete the files Sugo created. They are only on your computer, and you can delete them by hand:

What	Windows	macOS	Linux
Settings (`config.toml`)	`%LOCALAPPDATA%\sugo`	`~/Library/Application Support/sugo`	`~/.config/sugo`
Cache (text of converted documents)	`%LOCALAPPDATA%\sugo\Cache`	`~/Library/Caches/sugo`	`~/.cache/sugo`

If you set SUGO_CACHE_DIR, the cache is in that folder instead. The cache holds text from the documents you converted, so delete it if those documents were private. Apart from these two folders and the files you asked it to write (such as -o output or receipts), Sugo keeps nothing else on disk.

On an old computer

Measured on 2026-11-03 on a 2010 desktop: Intel Core i5-650 (2 cores, 4 threads, no AVX), 8 GB RAM, SSD, no usable GPU. Weaker than the 8 GB, 4-core machine Sugo targets.

Task	Result	Target
Native PDF, 100 pages, cleaning included	3.6 s, about 28 pages/s	≥ 20 pages/s
Peak memory, that PDF	98 MB	< 1 GB
Dense phone screenshot (30 lines) → text, OCR	30 of 30 lines, 0% character errors, 411 MB	< 1 GB
Same screenshot, time	13.7 s	< 2 s

Native documents run well within the targets even on this machine. OCR is accurate but slow on a CPU without AVX; making it faster is on the roadmap. Details and scripts are in TESTING.

Supported files

Type	Formats	Size limit
Documents	PDF (with a text layer), DOCX, XLSX, PPTX	200 MB
Images	PNG, JPEG, WEBP (screenshots, photos of text)	50 MB
Data	XML	50 MB

Old .doc, .xls and .ppt files and password-protected files are not read: save a new copy first.

How it works

flowchart LR

F[Your file] --> E[Reader PDF · Office · OCR · XML] E --> IR[Document → Page → Block] IR --> C[Cleaners propose removals] C --> K[Core applies and records them] K --> M[Markdown] K --> J[JSONL chunks] K --> S[Token metrics]

Each reader turns a file into the same structure of pages and blocks. Cleaners only *propose* changes; the core applies them and marks each removed block with who removed it and why, instead of deleting it. That is what makes the output checkable and reproducible. The full design is in ARCHITECTURE.

Promises

These are written down in PRINCIPLES and checked by tests:

Local by principle. Conversion never needs t

Only the beginning is shown; read the rest in the repo

Sugo

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Docs, sheets & office worki

Common questions

Alternatives

Agent-Native Calendar

Excel MCP Server

MCP Server for Excel

README from the maker

What it does

3.1 Costs

3.2 Revenue

3.3 Outlook

How it compares

Status

Quick start

Use it from an AI agent (MCP)

Uninstall

On an old computer

Supported files

How it works

Promises