PluginBench
MCP Server
Stale

ai.toolprint/hypertool-mcp MCP Server

ai.toolprint/hypertool-mcp

Dynamically expose focused tool subsets from multiple MCP servers based on agent personas and tasks.

What is the ai.toolprint/hypertool-mcp MCP server?

The HyperTool MCP server is a proxy that connects unlimited MCP servers and intelligently exposes curated subsets of tools based on agent personas and current tasks. It breaks free from tool limits by letting you create task-specific toolsets (e.g., 'coding' with 5 git/docker tools instead of 50+), improving AI decision-making and context efficiency.

HyperTool solves tool overload by letting you organize tools from multiple MCP servers into focused toolsets. Instead of exposing all 50+ tools at once, you create task-specific bundles (e.g., 'debugging' with logs, docker, traces) and switch between them instantly. It includes pre-built personas for common workflows (web-dev, data-scientist, devops, content-creator, researcher), context measurement to see token usage per tool, and support for unlimited MCP servers without hitting the 100-tool limit.

How to install ai.toolprint/hypertool-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "hypertool-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@toolprint/hypertool-mcp"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • list-available-tools — Shows token estimates for all available tools across connected MCP servers
  • get-active-toolset — Displays token usage and tools in the currently equipped toolset
  • Toolset management — Create, modify, switch, and delete task-specific tool bundles dynamically

Use cases

  • Switch between focused toolsets for different workflows (coding, writing, debugging) without restarting your AI
  • Reduce context confusion by exposing only 3-5 relevant tools instead of 50+ at once
  • Organize tools from 10+ MCP servers into logical groups for specific personas (web-dev, data science, DevOps)
  • Measure and optimize context usage by seeing token estimates for every tool before adding to a toolset
  • Pre-configure complete workflows with personas that bundle MCP servers and curated toolsets together

ai.toolprint/hypertool-mcp MCP server FAQ

What is HyperTool and how does it differ from using MCP servers directly?

HyperTool is a proxy MCP server that lets you connect unlimited MCP servers and dynamically expose focused subsets of tools based on tasks or personas. Unlike direct MCP use, it breaks the 100-tool limit, prevents tool confusion by showing only relevant tools, and lets you hot-swap between task-specific toolsets (e.g., 'coding' vs 'writing') without restarting.

What are Personas and how do I use them?

Personas are pre-configured bundles that include both MCP servers and curated toolsets for specific workflows. Available personas include web-dev, data-scientist, devops, content-creator, and researcher. Use them with: `npx -y @toolprint/hypertool-mcp mcp run --persona web-dev`. No server configuration needed—the persona brings everything.

Is HyperTool free and how do I install it?

Yes, HyperTool is open-source (MIT license). Install via npm: `npm install @toolprint/hypertool-mcp` or run directly with `npx -y @toolprint/hypertool-mcp`. For Cursor/Claude Desktop, add it to your `.mcp.json` config pointing to your existing MCP servers.

Does HyperTool work with Claude Desktop, Cursor, and Claude Code?

Yes. Cursor has full hot-swap support (switch toolsets instantly). Claude Desktop works but requires app restart after switching toolsets. Claude Code support is coming soon. HyperTool works with any MCP-compatible app.

How does context measurement work and is it accurate?

Context measurement shows token estimates for every tool using BPE-based approximation. Estimates are cached and add <10ms overhead. They're perfect for comparing tool costs and optimizing toolsets, but not exact counts since different LLMs use different tokenizers.

Can I use HyperTool in production?

Yes, HyperTool is production-ready. For enterprise support, contact the team at support@onegrep.dev. Everything is stored locally in `~/.toolprint/hypertool-mcp/` and you can edit toolsets and personas directly.

README (reference)

Source of truth, from the repository.

<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

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

Step 2: Point Your AI to HyperTool

Replace your .mcp.json with:

{
  "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:

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

# 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

# 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

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:

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

"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

"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

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

# 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:

# 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

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>

Related MCP servers

Read-only dental practice aggregates: patients seen, procedure mix, and letter activity.

Track ID for Instagram, SoundCloud, YouTube, TikTok, Mixcloud — incl. underground and unreleased.

Non-custodial Solana swap & limit order engine for AI agents.

2
JavaScript
MIT
View repository →

Search TradeSearcher strategies and backtests from Claude Code, Cursor, Codex, and other agents.

0
JavaScript
MIT
View repository →

Grounded, multilingual travel data + a cited travel concierge. 12+ languages, deep India coverage.

Real-time B2B buying signals on your target accounts: funding, hiring, leadership, tech stack.