ratel — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ratel-ai · MCP Server · ★ 434

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ratel safe to install? View the security audit →

About ratel

Ratel Context engineering for AI agents — engineer the context your agent actually needs, on every turn. Docs • Skills • Roadmap • Discord Most agents stuff every tool, skill, and memory into the context window each turn — burning tokens, drifting on the long tail. Ratel sits between the agent and its catalog, and resolves only what matters for this turn. Integrate Ratel in 60 seconds The fastest way to get Ratel into your agent is the Ratel skills suite — five Claude Code / Cursor / Codex skills that integrate Ratel, plan observability, d

accuracyagentsclaude-skillscontextharnessllmllm-routingmcpmcp-servermemory

Quick Facts

Stars434
Forks21
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score64.5058933905015/100
Open Issues14
Last Updated2026-09-07
Created2025-11-12
Platformsclaude-code, mcp, node
Est. Tokens~17k

Compatible Skills

These tools work well together with ratel for enhanced workflows:

  • aai-gateway — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)

ratel alternative? Top 6 similar tools

Looking for a ratel alternative? If you're comparing ratel with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mcp-memory-service by doobidoo · ⭐ 1.9k

    Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl

  • mcp by MicrosoftDocs · ⭐ 1.9k

    Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microso

  • pg-aiguide by timescale · ⭐ 1.8k

    MCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better Post

  • npcpy by NPC-Worldwide · ⭐ 1.5k

    The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and mor

  • awesome-hacking-lists by taielab · ⭐ 1.4k

    A curated collection of top-tier penetration testing tools and productivity utilities across multiple domains.

  • nocturne_memory by Dataojitori · ⭐ 1.3k

    A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is ratel?

ratel is 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.. It is categorized as a MCP Server with 434 GitHub stars.

What programming language is ratel written in?

ratel is primarily written in TypeScript. It covers topics such as accuracy, agents, claude-skills.

How do I install or use ratel?

You can find installation instructions and usage details in the ratel GitHub repository at github.com/ratel-ai/ratel. The project has 434 stars and 21 forks, indicating an active community.

What license does ratel use?

ratel is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ratel?

The top alternatives to ratel on Agent Skills Hub include mcp-memory-service, mcp, pg-aiguide. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools