MCP server by ojuschugh1 · ★ 648 · updated 2 days ago
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.
Choose your AI client and copy the config.
Install / run command from the README. Client configuration depends on the project — see its README.
cargo install sqz-cli sqz-mcp # or: brew install ojuschugh1/sqz/sqz · npm i -g sqz-cli · pipx install sqzTest/reference server that exercises every MCP feature (prompts, tools, resources, sampling). Built for MCP client developers, not for everyday use.
Tools to read, search and manipulate Git repositories (status, diff, log, commit, branches) via LLMs.
Up-to-date, version-specific library documentation and code examples pulled straight into your prompt, so coding assistants stop hallucinating outdated APIs.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
GitHub's official MCP Server
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.