CLIO Compression

Community

File compression and decompression MCP server using gzip

How to install ↓ Compare GitHub source repository ↗

Category: Filesystem #14 of 24
Stars: ★ 30 Popular
Transport: stdio (local process)
Runtime: Python 3.10+
Credentials: No credential needed
License: BSD-3-Clause
Last commit: 2 months ago
Tools: 2

55FMRS · C

CLIO Compression is a lightweight MCP server offering basic gzip compression/decompression. It fits well as part of CLIO Kit for scientific workflows but is not an official standalone tool. Implementation is simple with low risk, but functionality is limited to gzip. Recommended for users needing general-purpose compression within the ecosystem.

Strongest · Maintenance 13/20 Weakest · Reliability 8/20

Reliability

8/20

Security and permissions

12/20

Maintenance

13/20

Documentation

10/20

Setup experience

12/20

Why each score

Reliability 8/20: The manifest declares only two simple gzip compress/decompress tools; the small surface is self-consistent (server version 2.2.3 matches the README table). However, no server-specific source, unit tests, or CI runs for the compression server are supplied, so declared tool behavior cannot be verified; repo-level badges cannot be attributed to this sub-server. Static calibration caps the score here.
Security and permissions 12/20: Tools operate only on local files via gzip; no network access, no credentials, no destructive delete/pay/deploy/remote-command defaults, so no red line is triggered. Deductions: no server source is available to review path traversal or overwrite behavior (decompression may overwrite existing files), and no confirmation/scoping mechanisms are disclosed for writes.
Maintenance 13/20: The project is active (BSD-3-Clause, NSF-funded, IIT team, 39 open issues, CI/coverage/pip-audit badges, clear community channels and contribution guide). Deductions: clear version confusion — manifest server version 2.2.3, PyPI package 2.10.6, README install example 2.4.3 — indicating release/versioning governance gaps; no dedicated security-response channel is evident.
Documentation 10/20: The README covers installation, client configs, troubleshooting, and per-server overviews, but all at repository level; the compression server itself gets only a one-line manifest description and a prompt declaration, with no parameter docs, limits, costs, or dedicated examples; server counts (22/23/24) are internally inconsistent.
Setup experience 12/20: One-command uv tool install plus Cursor/Claude Code/VS Code/Claude Desktop config examples are provided; stdio transport requires no credentials, keeping the barrier low. Deductions: install example (2.4.3) conflicts with the declared latest PyPI version (2.10.6), the release launches sub-servers indirectly via embedded uv.lock (added complexity), and no compression-specific client config example is given.

Static review · not runListed 2026-09-08

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local files

Best for

AI agent developers needing basic file compression functionality.
Researchers in scientific computing/HPC environments needing data-handling tools.
Users already in the CLIO Kit or IoWarp platform ecosystem.

Not for

Users needing advanced compression options like multiple algorithms (bzip2, xz).
Users wanting fine control over compression (e.g., level, concurrency).
Users seeking production-level support or self-maintenance.

Required permissions

Reading user-specified files.
Writing generated compressed or decompressed files.
Communicating with the client via stdio.

Risks and side effects

Handling untrusted or malformed files can cause errors.
Compression may overwrite existing files with the same name.
As a non-official tool, there may be inadequately tested defects.

Setup

Before you start

Runtime：Python 3.10+

Install uv package manager if not present: curl -LsSf https://astral.sh/uv/install.sh | sh
Install clio-kit: uv tool install 'clio-kit==2.4.3'
Update shell: uv tool update-shell
Configure a client (e.g., Claude Desktop) to add the MCP server:

{
"mcpServers": {
"clio-kit-compression": {
"command": "clio-kit",
"args": ["mcp-server", "compression"]
}
}
}

claude_desktop_config.json

{
  "mcpServers": {
    "clio-kit-compression": {
      "command": "clio-kit",
      "args": [
        "mcp-server",
        "compression"
      ]
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "clio-kit-compression": {
      "command": "clio-kit",
      "args": [
        "mcp-server",
        "compression"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add clio-kit-compression -- clio-kit mcp-server compression

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After running `clio-kit mcp-server compression`, the client's tool list should show compress_file_tool and decompress_file_tool; asking it to compress a small file and checking the reported ratio confirms the connection.

Troubleshooting

If `clio-kit mcp-server compression` fails, verify the server name is correct (should be `compression`, not `compression-mcp`).
Ensure clio-kit is installed and its executable directory is on PATH.
Check file read/write permissions.

Things to try

Once connected, you can ask your AI assistant things like:

Compress data.csv with gzip and tell me the original size, compressed size, and ratio.
Decompress results.log.gz back to its original file.
Compress simulation_output.h5 and verify the result.
Restore backup.tar.gz to its original form.

Tools 2

compress_file_tool writes

Compress a file using gzip. Returns original/compressed sizes and compression ratio.

decompress_file_tool writes

Decompress a gzip-compressed (.gz) file back to its original form.

Use cases

Compress scientific data files directly in an AI workflow to save storage.

Automatically decompress .gz files for subsequent data analysis.

Supported clients

Claude Desktop

Cursor

VS Code

Listed from the project's documentation, not tested by this site.

Overview

CLIO Compression is one of the MCP servers provided by CLIO Kit, enabling file compression and decompression operations through the Model Context Protocol. It offers two core tools: compressing files using gzip, and decompressing .gz files back to their original form. It also includes a resource exposing supported compression format capabilities and a prompt guiding through a compression workflow. Part of the CLIO Kit suite aimed at scientific computing and HPC environments.

Similar servers

Filesystem MCP Server 84 · B

Secure local file read/write access

★ 91.4k · Tools 6 Compare with this →

Vault Cortex MCP Server 79 · B

Standalone MCP server for Obsidian vaults: hybrid search, notes & files, structured memory, tasks, OAuth 2.1.

★ 30 · Tools 30 Compare with this →

Obsidian Web MCP 68 · C

Secure remote access to your Obsidian vault over HTTPS with OAuth 2.0 authentication.

★ 185 · Tools 20 Compare with this →

Safe Docx MCP Server 68 · C

AI-native surgical editing of Word and OpenDocument files with formatting preservation

★ 46 Compare with this →

Compare with other MCP servers

More servers from this repository

Source revision 93e41d70d6c2 Data synced 2026-10-19 Read the FMRS scoring method