mcp-all-in-one
Aggregates multiple MCP services into a single unified interface with self-configuration capabilities, enabling dynamic addition and removal of tools via conversation.
README
mcp-all-in-one
A powerful MCP (Model Context Protocol) service aggregator that combines multiple MCP services into a single unified MCP service with self-configuration capabilities.
一个强大的MCP(Model Context Protocol)服务聚合器,能够将多个MCP服务合并为一个统一的MCP服务,并提供自我配置功能。 中文版请看 README_zh-CN.md.
✨ Core Features
🔄 Multi-Service Aggregation
- Unified Interface: Combine multiple MCP services into a single MCP service, simplifying configuration and management
- Multi-Protocol Support: Supports two communication protocols: stdio and HTTP
- Transparent Proxy: Clients don't need to be aware of multiple backend services, all tool calls are automatically routed to the corresponding service
🛠️ Self-Configuration
- Built-in Configuration Tools: Provide dedicated MCP tools for configuration management
- Dynamic Configuration: Modify configuration directly through MCP tools without manual file editing
- Configuration Validation: Real-time configuration validation to avoid configuration errors
🌟 Other Features
- 🪟 Windows Compatible: Automatically handles command execution issues on Windows platform
- ⚙️ Configuration-Driven: Manage MCP services through JSON configuration files
- 🛡️ Type Safe: Fully developed with TypeScript
- 🔄 Auto-Reconnect: Support automatic reconnection mechanism when services fail
- 📊 Status Monitoring: Real-time monitoring of all MCP services' running status
🚀 Quick Start
Get started in just three steps:
- Configure mcp-all-in-one in your MCP client
For Claude Code:
claude mcp add mcp-all-in-one -s user -- npx -y mcp-all-in-one@latest stdio
For clients like Cursor/Trae/Cherry Studio:
{
"mcpServers": {
"mcp-all-in-one": {
"command": "npx",
"args": ["mcp-all-in-one@latest","stdio"]
}
}
}
- Configure your MCPs through conversation in the MCP client
Configure Fetch tool in mcp-all-in-one: uvx mcp-server-fetch
Configure chrome-devtools in mcp-all-in-one: npx chrome-devtools-mcp@latest
View mcp configuration in mcp-all-in-one
Remove chrome-devtools tool from mcp-all-in-one
- Restart the MCP service in your MCP client, and the new tools will be ready to use!
📚 Documentation
- Quick Start Guide - Quick getting started with mcp-all-in-one
- IDE Configuration Guide - Detailed guide for configuring mcp-all-in-one in Claude Code and Cursor
- Self-Configuration Feature Guide - How to use mcp-all-in-one's self-configuration features
🤝 Contributing
Issues and Pull Requests are welcome!
📄 License
MIT License
🔗 Related Links
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.