Is the token-optimizer-mcp MCP server actively maintained?

The token-optimizer-mcp MCP server was last committed 29d ago and has 8 contributors. Issue health: 81% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

token-optimizer-mcp MCP Server

Name: ooples/token-optimizer-mcp
Rating: 4.5 (1 reviews)
Author: ooples

ooples/token-optimizer-mcp

Score: 87.5 → 0% Rank #565 MCP Server

[![AgentRank](https://agentrank-ai.com/api/v1/badge/ooples--token-optimizer-mcp)](https://agentrank-ai.com/tool/ooples--token-optimizer-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of ooples/token-optimizer-mcp? Claim this listing →

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Add AgentRank to Claude Code Discover and compare tools like ooples/token-optimizer-mcp — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

ooples/token-optimizer-mcp is a JavaScript tool licensed under MIT. Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients. Topics: ai, caching, claude, compression, llm, mcp, mcp-server, token-optimization, gemini-cli-extension.

Ranked #565 out of 24846 indexed tools.

In the top 3% of all indexed tools.

Ecosystem

JavaScript MIT

aicachingclaudecompressionllmmcpmcp-servertoken-optimizationgemini-cli-extension

Score Breakdown

Stars 15% 544

544 stars → growing community

Freshness 25% 29d ago

Last commit 29d ago → recently updated

Issue Health 25% 81%

42/52 issues closed → responsive maintainer

Contributors 10% 8

8 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 68

Description Good

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/ooples--token-optimizer-mcp)](https://agentrank-ai.com/tool/ooples--token-optimizer-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/ooples--token-optimizer-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/ooples--token-optimizer-mcp" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="ooples/token-optimizer-mcp"></script>

Details

Stars: 544
Forks: 68
Open Issues: 10
Closed Issues: 42
Contributors: 8
Dependents: —
Language: JavaScript
License: MIT
Last Commit: 29d ago

Matched Queries

topic:mcptopic:mcp-server

From the README

<p align="center">
  
</p>

<h1 align="center">Token Optimizer MCP</h1>

<p align="center">
  <strong>Compression that optimises your bill, not your byte count &mdash;
  and ships the benchmark so you can check it.</strong>
</p>

<p align="center">
  <a href="https://www.npmjs.com/package/@ooples/token-optimizer-mcp"></a>
  <a href="https://github.com/ooples/token-optimizer-mcp/actions/workflows/ci.yml"></a>
  <a href="./LICENSE"></a>
  <a href="https://nodejs.org/"></a>
</p>

<p align="center">
  
  
  
  
  
</p>

<p align="center">
  
</p>

<p align="center"><em>One local ledger for optimizer tools, live-graph substitutions, every agent, and the graph's own cost.</em></p>

---

## Why it wins

Providers cache the prompt prefix: cached tokens re-read at **0.1x**, rewritten
ones bill at **1.25x**. Most compressors optimise bytes removed and ignore that
multiplier. This one optimises the bill.

**It wins both columns.** Against a faithful reimplementation of the leading
open compressor

Read full README on GitHub →

See alternatives to ooples/token-optimizer-mcp → Browse mcp-server category → Best MCP Server MCP servers → Compare ooples/token-optimizer-mcp → How to Build an MCP Server in 2026 →MCP Server Comparison: Top 10 Head-to-Head →

View on GitHub →