ai.toolprint/hypertool-mcp

AI 与智能体

by toolprint

可依据 Agent Persona,从代理服务器动态暴露可用工具,便于按角色定制工具集并控制权限边界。

让不同 Agent 按 Persona 动态获得恰当工具集,既省去手工配置,又能清晰收住权限边界,做多角色智能体更灵活也更安心。

什么是 ai.toolprint/hypertool-mcp

可依据 Agent Persona,从代理服务器动态暴露可用工具,便于按角色定制工具集并控制权限边界。

README

<picture> <source media="(prefers-color-scheme: dark)" srcset="./assets/hypertool_darkmode_wordmark_horizontal.png"> <source media="(prefers-color-scheme: light)" srcset="./assets/hypertool_lightmode_wordmark_horizontal.png"> <img alt="Shows a darkmode hypertool-mcp Logo in light color mode and a white one in dark color mode." src="./assets/hypertool_lightmode_wordmark_horizontal.png" width="full"> </picture> <h1 align="center">Give your AI the best tools from all your MCPs 🎯</h1>

Version Downloads Discord TypeScript MCP Compatible License: MIT

⚡ Features

🔓 Break Free from Tool Limits

Connect unlimited MCP servers. Use 10, 50, or 500+ tools total - your AI only sees what it needs.

🎯 Task-Specific Toolsets

Build "git-essentials" with 5 tools instead of drowning in 47 Git commands. Switch contexts instantly.

🧠 Smart Tool Descriptions

Enhance tools with examples and context. Watch your AI pick the right tool 89% more often.

🚀 Quick Start

Step 1: Copy Your Existing Config

bash
# In your project directory
cp .mcp.json .mcp.hypertool.json

Step 2: Point Your AI to HyperTool

Replace your .mcp.json with:

json
{
  "mcpServers": {
    "hypertool": {
      "command": "npx",
      "args": ["-y", "@toolprint/hypertool-mcp", "mcp", "run", "--mcp-config", ".mcp.hypertool.json"]
    }
  }
}

Step 3: Create Your First Toolset

Restart your AI and try:

code
You: "Create a toolset called 'coding' with git and docker tools"
AI: "Created 'coding' toolset with 15 focused tools"

You: "Switch to coding toolset"
AI: "Equipped! I now have just the tools needed for development"

That's it! Your AI is now focused and effective. 🎉

💡 Want automated setup? Try our interactive setup command - see Advanced Guide for details.

📚 Configuration Mode: HyperTool uses a smart Configuration Mode to keep toolset management separate from your operational tools. Learn more in the Configuration Mode Guide.

🎭 Personas: Pre-configured Tool Bundles (NEW!)

Don't want to configure from scratch? Use personas - ready-to-use MCP server bundles with pre-built toolsets.

What are Personas?

Think of personas as "app bundles" for your AI - they come with:

  • ✅ Pre-configured MCP servers
  • ✅ Curated toolsets for specific workflows
  • ✅ Everything you need to get started instantly

Quick Start with Personas

bash
# 1. Clone the persona collection
git clone https://github.com/toolprint/awesome-mcp-personas

# 2. Add a persona (e.g., web-dev persona)
hypertool-mcp persona add awesome-mcp-personas/personas/web-dev

# 3. Run with the persona
npx -y @toolprint/hypertool-mcp mcp run --persona web-dev

That's it! No server configuration needed. The persona brings its own servers and toolsets.

📦 Browse all available personas: awesome-mcp-personas

Available Personas

PersonaIncluded ServersBest For
web-devGit, Docker, Filesystem, Browser, TestingFull-stack web development
data-scientistPython, Jupyter, Database, Filesystem, PlottingData analysis & ML workflows
devopsDocker, Kubernetes, AWS, Terraform, MonitoringInfrastructure & deployment
content-creatorNotion, Slack, Grammar, SEO, SocialWriting & content management
researcherPerplexity, Arxiv, Wikipedia, FilesystemResearch & knowledge work

Persona vs Standard Mode

bash
# Standard Mode (use your existing MCP servers):
npx -y @toolprint/hypertool-mcp mcp run --mcp-config .mcp.hypertool.json

# Persona Mode (bundled servers + pre-built toolsets):
npx -y @toolprint/hypertool-mcp mcp run --persona web-dev

# Persona Mode with specific toolset:
npx -y @toolprint/hypertool-mcp mcp run --persona web-dev --equip-toolset frontend

💡 Pro tip: Personas can be mixed with your existing servers! Add --mcp-config to include your custom servers alongside the persona's servers.

📚 Learn more: See the complete Personas Guide for detailed instructions, creating custom personas, and troubleshooting.

📊 Context Measurement (NEW!)

See exactly how much context each tool consumes. Optimize your toolsets with token estimates for every tool.

<div align="center"> <img src="./assets/toolset_context.png" alt="Toolset Context View" width="700"> <p><em>Active toolset showing token usage per tool</em></p> </div>

Why it matters:

  • 🎯 Optimize context usage - Identify heavyweight tools consuming your context window
  • 📉 Make informed decisions - See token costs before adding tools to toolsets
  • 🔍 Compare alternatives - Find lighter tools that do the same job
  • 💡 Budget your context - Understand exactly what you're exposing to your AI

How to use:

Ask your AI to use these MCP tools to see context information:

  • list-available-tools - Shows token estimates for all available tools
  • get-active-toolset - Shows token usage for your currently equipped toolset

Each tool displays estimated tokens and percentage of total context consumed. Perfect for building lean, efficient toolsets!

🎬 Demo

Hotswap toolsets across 100+ tools

Targeted toolsets across any number of MCPs. Swap to the best toolset for a goal with a tool call. Dynamic tool registration.

<div align="center"> <a href="https://www.youtube.com/watch?v=43fkKOBayCg"> <img src="./demos/build_dynamic_toolsets_1080p_25fps.gif" alt="HyperTool Demo - Click for full video" width="800"> </a> </div>

🏗️ How It Works

code
Before: Tool Chaos 😵
┌─────────────┐   ┌─────────────────────────────┐
│ Claude/     │──▶│ 50+ tools from 8 servers   │
│ Cursor      │   │ ❌ Wrong picks             │
│             │   │ ❌ Slow decisions          │
│             │   │ ❌ Confused context        │
└─────────────┘   └─────────────────────────────┘

After: Expert Mode 🎯
┌─────────────┐   ┌──────────────┐   ┌─────────────────┐
│ Claude/     │──▶│ HyperTool    │──▶│ ALL Your Tools  │
│ Cursor      │   │ (Local)      │   │ (Same servers)  │
└─────────────┘   └──────────────┘   └─────────────────┘
                         │
                         ▼
                  ┌─────────────────┐
                  │ Smart Toolsets  │
                  │ 🔨 coding (5)   │ ← "I'm coding now"
                  │ 📝 writing (3)  │ ← "I'm writing now"
                  │ 📊 analysis (4) │ ← "I'm analyzing now"
                  └─────────────────┘
                  ✅ Expert picks every time

What's a "Toolset"? Think Playlists for Your AI

Just like Spotify playlists organize your music, toolsets organize your AI tools:

code
ALL YOUR TOOLS (64 total)              YOUR TOOLSETS
┌────────────────────────────┐         ┌──────────────────┐
│ 🐳 Docker (19 tools)       │         │ 🔨 "coding"      │
│  • build_image             │   ┌───▶ │  • git.status    │
│  • create_container        │   │     │  • git.commit    │
│  • run_container           │   │     │  • docker.build  │
│  • stop_container          │   │     │  • docker.run    │
│  • [... 15 more]           │   │     │  • github.pr     │
├────────────────────────────┤   │     └──────────────────┘
│ 🔀 Git (12 tools)          │───┤
│  • status                  │   │     ┌──────────────────┐
│  • commit                  │   │     │ 📝 "writing"     │
│  • push                    │   └───▶ │  • notion.create │
│  • [... 9 more]            │         │  • slack.send    │
├────────────────────────────┤         │  • grammarly.fix │
│ 📝 Notion (8 tools)        │─────┐   └──────────────────┘
│ 💬 Slack (6 tools)         │     │
│ 📊 Linear (10 tools)       │     │   ┌──────────────────┐
│ 🧪 Testing (9 tools)       │     └─▶ │ 🐛 "debugging"   │
└────────────────────────────┘         │  • logs.search   │
                                       │  • docker.logs   │
AI sees ALL 64 tools = confused 😵     │  • traces.view   │
                                       └──────────────────┘

                                       AI sees 3-5 tools = focused 🎯

💼 Real-World Toolsets

Create focused toolsets for different workflows:

🔨 Development Mode

code
"deep-coding": git + docker + filesystem (12 tools)
→ Everything you need for feature development

"code-review": git + github + linear (10 tools)
→ Review PRs, update tickets, merge with confidence

"debugging": logs + docker + traces + alerts (8 tools)
→ Find and fix issues fast

📝 Content Creation

code
"writing": notion + grammarly + slack (6 tools)
→ Blog posts, docs, and team updates

"research": perplexity + notion + filesystem (7 tools)
→ Deep dives with organized notes

🎬 Real Chat Example

code
You: "I need to debug our API"
AI: "I'll switch to the debugging toolset for better focus"
[Now has: logs, traces, curl, docker]

You: "Actually, let's write the incident report"
AI: "Switching to writing toolset"
[Now has: notion, slack, templates]

💡 Pro tip: Start with 3-5 tools per toolset. Your AI will thank you!

📋 All Features

Explore everything HyperTool can do:

FeatureDescriptionGuide
🎭 PersonasPre-configured MCP server bundles with curated toolsets. Get started instantly with ready-to-use workflows for web-dev, data science, DevOps, and more.Personas Guide
📁 Server GroupsOrganize MCP servers into logical groups. Launch related servers together, switch between projects, and maintain focused contexts.Advanced Guide
📊 Context MeasurementSee token estimates for every tool. Optimize your toolsets by understanding exactly how much context each tool consumes.Context Measurement
🔧 Configuration ModeSmart separation of toolset management from operational tools. Keep your AI focused on work, not configuration.Configuration Mode Guide
🎯 Dynamic ToolsetsBuild, modify, and switch between toolsets on the fly. Adapt your AI's capabilities to match your current task.Examples & Recipes
🧠 Tool AnnotationsEnhance tools with custom descriptions, examples, and context. Improve your AI's tool selection accuracy by 89%.Advanced Guide
🚀 HTTP ModeRun HyperTool as a long-lived HTTP server for persistent connections and faster response times.Advanced Guide
🔌 Unlimited ServersConnect as many MCP servers as you need. Break free from the 100-tool limit without sacrificing performance.Quick Start

❓ FAQ

General Questions

Q: How is this different from just using MCP servers directly? A: HyperTool lets you use unlimited MCP servers without hitting the 100-tool limit, and dynamically switches between focused toolsets for better AI performance.

Q: What's the difference between Personas and Standard Mode? A: Standard Mode uses your existing MCP server configurations. Personas are pre-packaged bundles that include both MCP servers AND curated toolsets - perfect for getting started quickly or trying new workflows.

Q: Can I use multiple toolsets at once? A: In stdio mode (default), use --equip-toolset <name> when launching. HTTP mode supports one active toolset but you can switch anytime.

Q: Where are my toolsets and configurations stored? A: Everything is stored locally in ~/.toolprint/hypertool-mcp/:

  • Personas: ~/.toolprint/hypertool-mcp/personas/
  • Toolsets: ~/.toolprint/hypertool-mcp/toolsets/
  • Preferences: ~/.toolprint/hypertool-mcp/config/ You can directly edit these files when HyperTool is not running.

Setup & Compatibility

Q: Does this work with Claude Desktop / Cursor / Claude Code? A: Yes! Cursor has full hot-swapping support. Claude Desktop works with restart. Claude Code hot-swap coming soon.

Q: What if an MCP server goes down? A: HyperTool monitors health and automatically reconnects when servers come back. Your toolsets stay intact.

Q: Can I share toolsets with my team? A: Import/export is coming soon! For now, you can copy and share toolset files - they'll work if your team has the same MCP servers configured.

Q: How accurate are the token estimates in context measurement? A: The estimates use BPE-based approximation for consistent relative comparisons between tools. They're perfect for understanding which tools consume more context, but not exact counts since different LLMs use different tokenizers.

Q: Does context measurement slow down my toolsets? A: No! Token counts are cached and add less than 10ms overhead. You won't notice any performance impact.

Technical Questions

Q: How do I add tools from a new MCP server? A: Just add the server to your .mcp.hypertool.json config. It's automatically available for toolsets.

Q: Can I use this in production? A: Yes! For enterprise support, contact us.

🎮 App Compatibility

Works with ANY MCP-compatible app! HyperTool is a standard MCP server, so if your app supports MCP, it supports HyperTool.

Hot-swap Toolsets Without Restarts

AppStatusHow to Switch Toolsets
Cursor/VSCode✅ Full supportSwitch toolsets instantly - no restart needed!
Claude Code⏳ Coming soonUse --equip-toolset <name> flag (track progress)
Claude Desktop⏳ In progressRestart app after switching toolsets

📚 Learn More

🛠️ Development Setup

Prerequisites

  • Node.js 18+
  • Python 3.8+ (for pre-commit hooks)

Quick Setup

bash
# Clone and install
git clone https://github.com/toolprint/hypertool-mcp.git
cd hypertool-mcp
just setup-dev  # Installs dependencies and pre-commit hooks

Pre-commit Hooks

This project uses pre-commit hooks to ensure code quality:

bash
# Install pre-commit hooks (included in setup-dev)
just setup-pre-commit

# Run hooks manually
just pre-commit-check        # On staged files
just pre-commit-check-all    # On all files

# Skip hooks for emergency commits (use sparingly)
SKIP=eslint,typescript git commit -m "emergency fix"

Available Commands

bash
just build          # Build the project
just test           # Run tests
just lint           # Run linting
just format         # Format code
just typecheck      # Check types
just pre-publish-checks  # Run all quality checks

Service command

The hypertool-mcp service subcommand is currently disabled and will exit with a notification when invoked.

🤝 Contributing

Found a bug? Have an idea? We'd love your help!

📄 License

MIT License - see LICENSE file for details.


<div align="center">

Built by developers who got tired of watching AI pick the wrong tools 🎯

<a href="https://toolprint.ai"> <img src="./assets/toolprint.png" alt="Toolprint" width="200"> </a> <p> <strong>Built with ❤️ by <a href="https://toolprint.ai">Toolprint</a></strong><br> <sub>© 2025 OneGrep, Inc.</sub> </p> </div>

常见问题

ai.toolprint/hypertool-mcp 是什么?

可依据 Agent Persona,从代理服务器动态暴露可用工具,便于按角色定制工具集并控制权限边界。

相关 Skills

Claude接口

by anthropics

Universal
热门

面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。

想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心

AI 与智能体
未扫描109.6k

提示工程专家

by alirezarezvani

Universal
热门

覆盖Prompt优化、Few-shot设计、结构化输出、RAG评测与Agent工作流编排,适合分析token成本、评估LLM输出质量,并搭建可落地的AI智能体系统。

把提示优化、LLM评测到RAG与智能体设计串成一套方法,适合想系统提升AI开发效率的人。

AI 与智能体
未扫描9.0k

智能体流程设计

by alirezarezvani

Universal
热门

面向生产级多 Agent 编排,梳理顺序、并行、分层、事件驱动、共识五种工作流设计,覆盖 handoff、状态管理、容错重试、上下文预算与成本优化,适合搭建复杂 AI 协作系统。

帮你把多智能体流程设计、编排和自动化统一起来,复杂工作流也能更稳地落地,适合追求强控制力的团队。

AI 与智能体
未扫描9.0k

相关 MCP Server

顺序思维

编辑精选

by Anthropic

热门

Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。

这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。

AI 与智能体
82.9k

知识图谱记忆

编辑精选

by Anthropic

热门

Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。

帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。

AI 与智能体
82.9k

PraisonAI

编辑精选

by mervinpraison

热门

PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。

如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。

AI 与智能体
6.4k

评论