1mcp-app

agent

Built by 1mcp-app • 404 stars

What is agent?

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

How to use agent?

1. Install a compatible MCP client (like Claude Desktop). 2. Open your configuration settings. 3. Add agent using the following command: npx @modelcontextprotocol/agent 4. Restart the client and verify the new tools are active.
šŸ›”ļø Scoped (Restricted)
npx @modelcontextprotocol/agent --scope restricted
šŸ”“ Unrestricted Access
npx @modelcontextprotocol/agent

Key Features

Native MCP Protocol Support
Real-time Tool Activation & Execution
Verified High-performance Implementation
Secure Resource & Context Handling

Optimized Use Cases

Extending AI models with custom local capabilities
Automating system workflows via natural language
Connecting external data sources to LLM context windows

agent FAQ

Q

Is agent safe?

Yes, agent follows the standardized Model Context Protocol security patterns and only executes tools with explicit user-granted permissions.

Q

Is agent up to date?

agent is currently active in the registry with 404 stars on GitHub, indicating its reliability and community support.

Q

Are there any limits for agent?

Usage limits depend on the specific implementation of the MCP server and your system resources. Refer to the official documentation below for technical details.

Official Documentation

View on GitHub

1MCP - One MCP Server for All

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

NPM Version NPM Downloads CodeQl GitHub Repo stars 1MCP Docs DeepWiki NPM License

Overview

1MCP (One MCP) is designed to simplify the way you work with AI assistants. Instead of configuring multiple MCP servers for different clients (Claude Desktop, Cherry Studio, Cursor, Roo Code, Claude, etc.), 1MCP provides a single, unified server.

Features

  • šŸ”„ Unified Interface: Aggregates multiple MCP servers into one
  • šŸ”’ OAuth 2.1 Authentication: Production-ready security with scope-based authorization
  • ⚔ High Performance: Efficient request forwarding with proper error handling
  • šŸ›”ļø Security First: Stdio transport isolation, input sanitization, and comprehensive audit logging
  • šŸ”§ Easy Configuration: Single JSON configuration file with hot-reload support
  • šŸ“ˆ Health Monitoring: Built-in health check endpoints for monitoring and observability

Quick Start

1. Install 1MCP

Binary (Recommended - No Node.js Required):

# Linux/macOS
curl -L https://github.com/1mcp-app/agent/releases/latest/download/1mcp-linux-x64.tar.gz | tar -xz
sudo mv 1mcp /usr/local/bin/

# Windows (PowerShell)
Invoke-WebRequest -Uri "https://github.com/1mcp-app/agent/releases/latest/download/1mcp-win32-x64.zip" -OutFile "1mcp.zip"
Expand-Archive -Path "1mcp.zip" -DestinationPath "."

NPM:

npx -y @1mcp/agent --help

2. Add MCP Servers

1mcp mcp add context7 -- npx -y @upstash/context7-mcp
1mcp mcp add filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/Documents

3. Start the Server

1mcp

4. Connect Your AI Assistant

For Cursor, add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "1mcp": {
      "url": "http://127.0.0.1:3050/mcp?app=cursor"
    }
  }
}

Install MCP Server to Cursor

For VSCode, add to settings.json:

{
  "servers": {
    "1mcp": {
      "url": "http://127.0.0.1:3050/mcp?app=vscode"
    }
  }
}

Install MCP Server to VSCode

For Claude Code:

claude mcp add -t http 1mcp "http://127.0.0.1:3050/mcp?app=claude-code"

That's it! All your MCP servers are now available through one unified endpoint. šŸŽ‰

Commands

Core Commands

  • 1mcp [serve] - Start the 1MCP server (default command)
  • 1mcp mcp add <name> - Add a new MCP server to configuration
  • 1mcp mcp list - List all configured MCP servers
  • 1mcp mcp status [name] - Show server status and details

For detailed command usage, run: 1mcp <command> --help

Documentation

šŸ“š Complete Documentation - Comprehensive guides, API reference, and examples

Key Topics

How It Works

1MCP acts as a proxy, managing and aggregating multiple MCP servers. It starts and stops these servers as subprocesses and forwards requests from AI assistants to the appropriate server. This architecture allows for a single point of entry for all MCP traffic, simplifying management and reducing overhead.

Contributing

Contributions are welcome! Please read our CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.

License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.

Global Ranking

-
Trust ScoreMCPHub Index

Based on codebase health & activity.

Manual Config

{ "mcpServers": { "agent": { "command": "npx", "args": ["agent"] } } }