Is the ratel MCP server actively maintained?

The ratel MCP server was last committed 1mo ago and has 10 contributors. Issue health: 47% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

ratel MCP Server

Name: ratel-ai/ratel
Rating: 4.2 (1 reviews)
Author: ratel-ai

ratel-ai/ratel

Score: 79.3 ↑ 0.7% Rank #2131 Search & RAG

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

Are you the maintainer of ratel-ai/ratel? Claim this listing →

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Add AgentRank to Claude Code Discover and compare tools like ratel-ai/ratel — your AI finds the right one automatically

Get API Access →

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

Overview

ratel-ai/ratel is a Rust tool licensed under MIT. Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB. Topics: accuracy, agents, claude-skills, context, harness, llm, llm-routing, mcp, mcp-server, memory, optimization, rag, skills, token-optimization, tool-calling, tool-selection.

Ranked #2131 out of 24846 indexed tools.

In the top 9% of all indexed tools.

Has 10 contributors.

Ecosystem

Rust MIT

accuracyagentsclaude-skillscontextharnessllmllm-routingmcpmcp-servermemoryoptimizationragskillstoken-optimizationtool-callingtool-selection

Score Breakdown

Stars 15% 475

475 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → recently updated

Issue Health 25% 47%

14/30 issues closed → many open issues

Contributors 10% 10

10 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 27

Description Detailed

License MIT

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

How to Improve

Issue Health high impact

You have 16 open vs 14 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

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

HTML

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

Embed Widget docs →

HTML

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

Details

Stars: 475
Forks: 27
Open Issues: 16
Closed Issues: 14
Contributors: 10
Dependents: —
Language: Rust
License: MIT
Last Commit: 1mo ago

Matched Queries

topic:mcptopic:mcp-server

From the README

<div align="center">
  <h1>Ratel</h1>
  <p>Your AI agent is paying for tools it never uses. Ratel fixes that.</p>

  <p>
    <a href="https://docs.ratel.sh">Docs</a> •
    <a href="https://github.com/ratel-ai/skills">Skills</a> •
    <a href="https://discord.gg/75vAPdjYqT">Discord</a>
  </p>

  <p>
    <a href="https://www.npmjs.com/package/@ratel-ai/sdk"></a>
    <a href="https://pypi.org/project/ratel-ai/"></a>
    <a href="https://crates.io/crates/ratel-ai-core"></a>
    <a href="https://github.com/ratel-ai/ratel/stargazers"></a>
    <a href="https://discord.gg/75vAPdjYqT"></a>
    <a href="#license"></a>
  </p>
</div>

<div align="center">
  
</div>

## Introduction

The context engineering layer for AI agents. Selects only the tools and skills relevant to each turn, recovering accuracy lost to tool overload and cutting what you pay per call. No vector DB, no infra.

## Why

- **Cost:** Every tool schema, every skill, and a growing list of instructions in the system prompt are toke

Read full README on GitHub →