Google PageRank for AI agents. 25,000+ tools indexed.

lean-ctx MCP Server

yvgude/lean-ctx

Score: 49.6 Rank #105 MCP Server
Are you the maintainer of yvgude/lean-ctx? Claim this listing →

Hybrid Context Optimizer — Shell Hook + MCP Server. Reduces LLM token consumption by 89-99%. Single Rust binary, zero dependencies.

Add AgentRank to Claude Code Discover and compare tools like yvgude/lean-ctx — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

yvgude/lean-ctx is a Rust MCP server. Hybrid Context Optimizer — Shell Hook + MCP Server. Reduces LLM token consumption by 89-99%. Single Rust binary, zero dependencies. Topics: ai, cli, context-compression, cursor, llm, mcp, rust, token-optimization, agentic-coding, claude-code, compression, copilot, developer-tools, open-source, tokens.

Ranked #105 out of 129 indexed tools.

Actively maintained with commits in the last week.

Ecosystem

Rust No license
aiclicontext-compressioncursorllmmcprusttoken-optimizationagentic-codingclaude-codecompressioncopilotdeveloper-toolsopen-sourcetokens

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 1

1 stars → early stage

Freshness 25% today

Last commit today → actively maintained

Issue Health 25% 50%

No issues filed → no history to score

Contributors 10% 1

1 contributor → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 0
Description Good
License None

Weights: Freshness 25% · Issue Health 25% · Dependents 25% · Stars 15% · Contributors 10% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

License low impact

Add an MIT or Apache-2.0 license to signal trust and enable adoption

Contributors medium impact

Single-contributor projects carry bus-factor risk — welcoming contributors boosts confidence

Badge all embed codes →

AgentRank score for yvgude/lean-ctx
[![AgentRank](https://agentrank-ai.com/api/badge/tool/yvgude--lean-ctx)](https://agentrank-ai.com/tool/yvgude--lean-ctx/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/yvgude--lean-ctx/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/tool/yvgude--lean-ctx" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="yvgude/lean-ctx"></script>

Matched Queries

"mcp server""mcp-server"

From the README

# lean-ctx

**Hybrid Context Optimizer — Shell Hook + MCP Server. Single Rust binary, zero dependencies.**

[Website](https://lean-ctx.pounce.ch) · [Install](#installation) · [Quick Start](#quick-start) · [CLI Reference](#cli-commands) · [MCP Tools](#8-mcp-tools) · [vs RTK](#lean-ctx-vs-rtk)

---

lean-ctx reduces LLM token consumption by **89-99%** through two complementary strategies in a single binary:

1. **Shell Hook** — Transparently compresses CLI output before it reaches the LLM. Works without LLM cooperation.
2. **MCP Server** — 8 tools for cached file reads, dependency maps, entropy analysis, and session metrics. Works with Cursor, GitHub Copilot, Claude Code, Windsurf, and any MCP-compatible editor.

## Token Savings (Typical Cursor/Claude Code Session)

| Operation | Frequency | Standard | lean-ctx | Savings |
|---|---|---|---|---|
| File reads (cached) | 15x | 30,000 | 195 | **-99%** |
| File reads (map mode) | 10x | 20,000 | 2,000 | **-90%** |
| ls / find | 8x | 6,400 | 1
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.