mcp-zip

mcp-zip

Make a zip, look inside one, and unpack one, in the conversation you are already in. Pack a folder with a glob(**/*.csv, everything except node_modules). Read the one README out of an archive without unpacking it.Ask what is inside a zip somebody sent you and be told before you open it: absolute paths, .., symlinks,duplicate names, and the entry that claims to be 200 MB inside a 199 KB file. Bundle a month of invoices,quotes and exports into one file to send to an accountant. Everything runs on your machine: no upload, noaccount, no API key, and no network call of any kind.

Install

Claude Desktop, ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or%APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "zip": { "command": "npx", "args": ["-y", "@theluckystrike/mcp-zip"] }
  }
}

Claude Code:

claude mcp add zip -- npx -y @theluckystrike/mcp-zip

Cursor, .cursor/mcp.json:

{
  "mcpServers": {
    "zip": { "command": "npx", "args": ["-y", "@theluckystrike/mcp-zip"] }
  }
}

Tools

Free vs Pro

Reading is never metered. The free tier is a limit on what you write, because an archive somebody sent you isexactly the one you most need to inspect before opening, and a paywall in front of that would be a paywall infront of the safety check.

Get Pro: https://mcp.zovo.one/buy/zip - $19 one time, or $39 for every server in the suite, lifetime.Keys verify offline; nothing is sent anywhere.

Why fflate and not a hand-written writer

The choice was fflate (pure JS, 0 dependencies, synchronous zipSync/inflateSync) against writing aSTORE/DEFLATE writer on node:zlib, which is available with no dependency at all.

The container format is written here either way. This server reads the central directory itself, insrc/zipfile.ts, roughly 200 lines: sizes, names, methods, CRCs, external attributes. It has to, because everyguard in the server is a decision made from those headers before anything is inflated, and a library thathands back {name: bytes} has already decompressed the bomb by the time you can look at it. So the argument fora library was never "it saves me the format".

What is left is the compressor, and that is the part not to write. node:zlib would do it, but its raw-deflatecalls are async-first, they carry a thread-pool round trip per call, and the sync ones each build a nativestream; packing 200 small files is 200 of those. fflate's deflateSync is a pure-JS implementation with nonative handle, it packs 200 files in 74 ms (measured below), and it means the package still has no native buildstep, which is the rule for this whole suite: npx has to work everywhere.

The trade is stated plainly: fflate builds the archive in one buffer, so this server refuses inputs over512 MB rather than pretending to stream, and it does not read ZIP64 (over 4 GB or over 65,535 entries), which isrefused by name rather than misread.

Measured: the file type does not predict the compression ratio, repetition does

Every file below was zipped at level 6 on this machine. The "type" column is what a person would call the file;the ratio is what actually happened.

PDF and DOCX barely move, and that is not a surprise once you look inside them: both are already deflatecontainers, so zipping them again is packaging, not compression. Bundling a month of invoices is worth doing forthe one file, not for the space.

The two CSV rows are the interesting pair. Same tool, same shape, same size, 34x apart: the one with fortyrepeated client names compresses 82.69x, the one with unique values 2.40x. Nothing about "it is a CSV" predictswhich one you have.

Measured: why the bomb ceiling is 100x and not 50x

A compression bomb is refused by ratio, and the obvious instinct is to set that ceiling low, well under the1022x a zeros file reaches. The table above says why that is wrong: a real CSV export, of the kindzip_bundle_month collects from the expense tracker, reached 82.69x, which is 83% of the way to a 100xceiling and well past a 50x one. A ceiling tuned to be comfortably below a bomb would refuse a real monthlyexport, and the person on the other end would learn to pass max_ratio on everything, which turns the guardoff permanently.

So the ratio is the second guard, not the first. The first is the total: the selected entries' declareduncompressed sizes are added up and compared against a ceiling (1 GB by default, max_total_mb to change it),because 200 MB out of a 199 KB file is a decision you can make about the archive as a whole without judging anyentry. Both are read from the central directory, so refusing a bomb costs no decompression at all:

refuse a 500 MB bomb (497.8 KB on disk)   3 ms, nothing inflated, out_dir not even created

Measured: a bounded output buffer is not a bomb guard

fflate.inflateSync(data, { out: new Uint8Array(n) }) looks like the whole answer: cap the buffer, cap thedamage. It is not, and the way it fails is quiet. A 100,000-byte entry inflated into a 10-byte buffer returns10 bytes and throws nothing. An archive whose header declares 10 bytes for a 100 KB entry would extract as a10-byte file, reported as a success, with the truncation invisible.

So the buffer bounds the memory and the CRC-32 in the central directory proves the bytes. Every entry thisserver writes out is checksummed against the header before it reaches the disk, and a mismatch refuses the entryby name. That is the check that turns a lying header from silent data loss into a sentence.

Timings

M-series laptop, over stdio, per call, cold store:

Privacy

Everything stays on your machine. There is no network code in this server at all: no fetch, no HTTP client, notelemetry. Archives are written where you say, and a small register of what was created lives under~/.local/share/mcp-servers/zip/ (or $XDG_DATA_HOME). License keys verify offline with a public key.

Zip passwords are not supported, and passing one is refused rather than ignored: the classic zip cipher isbroken and AES zip encryption is a vendor extension no two tools agree on, so a "password protected" archivefrom here would be a false promise.

Built by theluckystrike. Support: [email protected]