Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
MCPpedia last refreshed this data
io.github.ojuschugh1/sqz is an MCP server that pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe. Its tool list has not been published yet over stdio and sse, requires no API key, and scores 61/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"github": {
"args": [
"proxy",
"--",
"npx",
"-y",
"@modelcontextprotocol/server-github"
],
"command": "sqz-mcp"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
This server supports HTTP transport. Be the first to test it - help the community know if it works.
Five weighted categories - click any category to see the underlying evidence.
No known CVEs.
Checked sqz-cli against OSV.dev.
Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in ai-ml / analytics
A cross-platform desktop application for managing AI Agents and MCP Servers. 一款用于管理AI智能体与MCP服务器的跨平台桌面应用程序。
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
An open-source AI agent that brings the power of Gemini directly into your terminal.
🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.
MCP Security Weekly
Get CVE alerts and security updates for io.github.ojuschugh1/sqz and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
███████╗ ██████╗ ███████╗ ██╔════╝██╔═══██╗╚══███╔╝ ███████╗██║ ██║ ███╔╝ ╚════██║██║▄▄ ██║ ███╔╝ ███████║╚██████╔╝███████╗ ╚══════╝ ╚══▀▀═╝ ╚══════╝
Pre-injection context compression and session deduplication for AI coding agents
Real session stats: 3,003 compressions · 178,442 tokens saved · 24.7% avg reduction · up to 92% on output the model already has
Docs · Install · How It Works · Supported Tools · MCP Proxy · Benchmark · Changelog · Discord
English | 简体中文 | 日本語 | 한국어 | Español | Português (Brasil)
AI coding agents spend most of their input tokens on tool output: build logs, test runs, git status, the same file read again after every edit. All of it goes into the context window raw, and it is re-sent on every turn after that.
sqz compresses tool output before it enters the context. Per-command formatters keep what an agent acts on (the failing test, the assertion, the file:line) and drop what it does not. Anything the model already has in context comes back as a short reference instead of the content. Source code passes through unchanged, and so do stack traces, migrations and credential lines.
cargo install sqz-cli sqz-mcp # or: brew install ojuschugh1/sqz/sqz · npm i -g sqz-cli · pipx install sqz
sqz init # hooks + MCP server + agent guidance for every
... [View full README on GitHub](https://github.com/ojuschugh1/sqz#readme)