Hatago MCP Hub
H

Hatago MCP Hub

Hatago MCP Hub is a lightweight multi - MCP server aggregation center that supports connecting local, remote, and NPX - packaged MCP servers via multiple transport protocols such as STDIO, HTTP, and SSE, providing a unified access entry for AI tools such as Claude Code and Cursor, and featuring advanced functions such as configuration inheritance, tag filtering, and environment variable expansion.
2.5 points
0

What is Hatago MCP Hub?

Hatago is a transit station that connects modern AI tools with MCP servers. It's like an intelligent router that allows you to configure and manage all MCP servers in one place and then provide them to AI assistants through a unified interface.

How to use Hatago MCP Hub?

Using Hatago is very simple: First, create a configuration file to define the MCP servers you want to connect to (such as file systems, GitHub, databases, etc.), and then start the Hatago service. AI assistants only need to connect to Hatago to access the functions of all configured servers.

Applicable scenarios

Suitable for developers and teams who need to use multiple AI tools simultaneously, especially those using AI programming tools such as Claude Code, Cursor, and Windsurf. Also suitable for users who need to switch different tool configurations in different projects or environments.

Main Features

High-performance startup
The startup speed is up to 8.44 times faster (optimized from 85.66ms to 10.14ms), and the package size is reduced by 17% (from 1.04MB to 854KB).
Multi-transport protocol support
Supports three connection methods: STDIO, HTTP, and SSE, and is compatible with various AI tools such as Claude Code, Codex CLI, and Cursor.
Tag filtering function
You can add tags to servers (such as 'dev', 'production') and only load servers with specific tags during startup to manage tool combinations flexibly.
Configuration inheritance
Supports configuration file inheritance. You can create a base configuration and specific environment configurations to avoid duplicate settings and follow the DRY principle.
Remote server proxy
You can connect to remote HTTP/SSE MCP servers, such as DeepWiki MCP, to expand the scope of tool capabilities.
Progress notification forwarding
Transparently forwards progress notifications from sub - servers, supports long - running operations, and provides real - time feedback.
Advantages
One - stop management: Manage all MCP servers in a unified manner and simplify configuration
Flexible deployment: Supports local, remote, and NPX servers to adapt to various scenarios
Excellent performance: Fast startup speed and low resource consumption
Easy to use: Start the HTTP mode with zero configuration, suitable for quick start
Team - friendly: Supports configuration inheritance and tag filtering for easy team collaboration
Limitations
Restart required for configuration changes: Manually restart the service after modifying the configuration file
Learning curve: Need to understand the MCP protocol and server configuration
Dependent on external tools: Some functions (such as automatic restart) need to be used in conjunction with nodemon or PM2

How to Use

Install Hatago
You can install it globally via npm or run it directly using npx without installation.
Create a configuration file
Use the init command to create a basic configuration file or manually create hatago.config.json.
Configure MCP servers
Add the MCP servers you need, such as file systems, GitHub, databases, etc., to the configuration file.
Start the Hatago service
Select the appropriate startup mode (STDIO or HTTP) according to your AI tool.
Configure AI tool connection
Configure the connection to Hatago in your AI tool. The specific method depends on the tool type.

Usage Examples

Development environment toolset
Use the file system, GitHub, and code search tools simultaneously when developing a project.
Team standardization configuration
The team shares the basic configuration, and individuals add specific tools according to their needs.
Multi - environment switching
Use different tool combinations in different environments (development, testing, production).

Frequently Asked Questions

What's the difference between Hatago and directly using MCP servers?
Which AI tools are supported?
Do I need to restart after changing the configuration?
How to debug connection issues?
Does it support custom MCP servers?

Related Resources

Official Documentation
Complete documentation for Hatago MCP Hub (Japanese/English)
GitHub Repository
Source code and issue tracking
npm Package
Installation package and version history
MCP Protocol Specification
Official specification of the Model Context Protocol
Getting Started Tutorial (Dev.to)
Getting started tutorial for Hatago MCP Hub

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "hatago": {
      "command": "npx",
      "args": [
        "@himorishige/hatago-mcp-hub",
        "serve",
        "--stdio",
        "--config",
        "./hatago.config.json"
      ]
    }
  }
}

{
  "mcpServers": {
    "hatago": {
      "url": "http://localhost:3535/mcp"
    }
  }
}

{
  "$schema": "https://raw.githubusercontent.com/himorishige/hatago-mcp-hub/main/schemas/config.schema.json",
  "version": 1,
  "logLevel": "info",
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "deepwiki": {
      "url": "https://mcp.deepwiki.com/sse",
      "type": "sse"
    },
    "custom-api": {
      "url": "https://api.example.com/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer ${API_KEY}"
      }
    }
  }
}

{
  "mcpServers": {
    "filesystem-dev": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "."],
      "tags": ["dev", "local"]
    },
    "github-prod": {
      "url": "https://api.github.com/mcp",
      "type": "http",
      "tags": ["production", "github"]
    },
    "database": {
      "command": "mcp-server-postgres",
      "tags": ["dev", "production", "database"]
    }
  }
}

{
  "version": 1,
  "logLevel": "info",
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_TOKEN": "${GITHUB_TOKEN}"
      }
    },
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
    }
  }
}

{
  "extends": "~/.hatago/base.config.json",
  "logLevel": "debug",
  "mcpServers": {
    "github": {
      "env": {
        "GITHUB_TOKEN": "${WORK_GITHUB_TOKEN}",
        "DEBUG": null
      }
    },
    "internal-tools": {
      "url": "https://internal.company.com/mcp",
      "type": "http",
      "headers": {
        "Authorization": "Bearer ${INTERNAL_TOKEN}"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
4.6K
5 points
P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
4.2K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
5.2K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
5.3K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
7.7K
4.5 points
G
Gk Cli
GitKraken CLI is a command - line tool that provides multi - repository workflow management, AI - generated commit messages and pull requests, and includes a local MCP server for integrating tools such as Git, GitHub, and Jira.
4.6K
4.5 points
M
MCP
A collection of official Microsoft MCP servers, providing AI assistant integration tools for various services such as Azure, GitHub, Microsoft 365, and Fabric. It supports local and remote deployment, helping developers connect AI models with various data sources and tools through a standardized protocol.
C#
7.4K
5 points
C
Claude Context
Claude Context is an MCP plugin that provides in - depth context of the entire codebase for AI programming assistants through semantic code search. It supports multiple embedding models and vector databases to achieve efficient code retrieval.
TypeScript
11.5K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
28.2K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
18.9K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.4K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
58.3K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
25.7K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
53.4K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
39.2K
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
19.4K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase