Best for
- Developers using AI coding assistants with multiple MCP servers
- Teams looking to improve AI tool selection accuracy
- Users who want to organize toolsets to match their workflows
H
43FMRS · D
HyperTool MCP addresses a common pain point in AI tool management with dynamic toolsets, improving tool selection accuracy. Its persona feature accelerates setup. The context measurement feature is useful but should be treated as approximate.
HyperTool MCP is an MCP server that dynamically exposes tools from proxied servers based on an Agent Persona. It allows AI clients to connect to an unlimited number of MCP servers and organize their tools into focused toolsets (like playlists), overcoming tool count limits and improving tool selection accuracy. It supports pre-configured personas (e.g., web-dev, data-scientist) and context measurement to estimate token usage per tool.
Tools
list-available-tools
Lists all available tools with token estimates.
get-active-toolset
Shows the current toolset and its token usage.
Setup
- Copy your existing .mcp.json to .mcp.hypertool.json
- Replace .mcp.json with the HyperTool configuration as shown above
- Restart your AI client
- Create toolsets via interactive commands, e.g., "Create a toolset called 'coding' with git and docker tools"
claude_desktop_config.json
{
"mcpServers": {
"hypertool": {
"command": "npx",
"args": [
"-y",
"@toolprint/hypertool-mcp",
"mcp",
"run",
"--mcp-config",
".mcp.hypertool.json"
]
}
}
}
Fit and risk
Not for
- Users with only one or two MCP servers and few tools
- AI applications that don't require complex tool management
Required permissions
- Read and write local configuration (~/.toolprint/hypertool-mcp/) to store toolsets and preferences
- Launch and manage child processes to proxy MCP servers
- Communicate with MCP clients over stdio
Risks and side effects
- Proxied MCP servers may have permissions associated with their tools, such as filesystem access or remote API calls. Users should review the permissions granted to those servers.
- Misconfiguration can lead to tools not being available. Ensure .mcp.hypertool.json is correctly formatted and contains valid server configurations.
- Context measurement uses BPE-based approximations and is not exact token counts, so optimization decisions may not be precise.
Troubleshooting
- If the server doesn't start, check Node.js version is >=18 and validate the syntax of .mcp.hypertool.json.
- If tools aren't showing, ensure a toolset has been created and is active (use --equip-toolset).
- Check the configuration storage location and ensure files aren't edited while HyperTool is running.
- If a proxied server goes down, HyperTool will automatically reconnect, but you may need to check server health.
Use cases
Break free from tool limits when using more than 100 tools across multiple MCP servers
Create focused toolsets for specific tasks like development, writing, or debugging
Quickly start with pre-configured personas like web-dev or data-scientist
Measure context consumption per tool to optimize toolset design
Supported clients
Claude DesktopFull support
CursorFull support
Claude CodePartial support