Importing Tools into GEAI using MCP Tool Servers

The GEAI Proxy is a Python-based component that enables dynamic integration of external tools into Globant Enterprise AI (GEAI) via the Model Context Protocol (MCP). It acts as a bridge between GEAI and one or more MCP-compliant tool servers.

Once the MCP servers are properly configured and connected through the Tool Hub, the tools they expose become automatically available in the Lab → Tools section of GEAI, ready for use by any Agent without additional setup.

Installation

pip install pygeai

Configuration

The GEAI Proxy requires two distinct types of configuration:

1. MCP Servers Configuration

This section declares the Model Context Protocol (MCP) servers that this proxy will link with GEAI. The configuration follows the Claude Desktop standard format and supports multiple servers in one file.

Configuration File Format

{
  "mcpServers": {
    "serverName1": {
      "command": "command-to-launch-server",
      "args": ["arg1", "arg2", ...]
    },
    "serverName2": {
      "command": "command-to-launch-server",
      "args": ["arg1", "arg2", ...]
    }
  }
}

Example Configurations

Puppeteer Server (for web automation):

{  
"mcpServers": {  
 "puppeteer": {  
    "command": "npx",  
    "args": ["-y", "@modelcontextprotocol/server-puppeteer"]  
   }  
  }  
}

Filesystem Server (for file operations):

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "~/mcp-shared-folder"
      ]
    }
  }
}

Multiple Servers Combined:

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-puppeteer"]
    },
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "~/mcp-shared-folder"
      ]
    },
    "custom-server": {
      "command": "python",
      "args": ["path/to/your/custom_mcp_server.py"]
    }
  }
}

A sample configuration file is provided at:

pygeai/proxy/sample-mcp-config.json

2. Proxy Authentication Configuration

This section establishes the connection between the proxy and GEAI and manages user aliases. You can configure it automatically on the first run or manually reconfigure an existing alias.

Automatic Configuration (First Run)

geai-proxy sample-mcp-config.json --alias myalias

Manual Configuration (Reconfiguration)

geai-proxy --configure --alias myalias

During interactive setup, the CLI will prompt you for each required setting:

# Configuring GEAI proxy settings...  
Generated new proxy ID: 37bae96b-bc99-4110-bb61-b912b28f9e32  
-> Insert proxy ID (UUID) (Current: 37bae96b-bc99-4110-bb61-b912b28f9e32, Leave empty to keep):  
-> Insert proxy API key:  
-> Insert proxy base URL:  
-> Insert proxy name:  
-> Insert proxy description:

Usage

Starting the Proxy

To start the proxy server with a specific configuration and alias:

geai-proxy sample-mcp-config.json --alias myalias

Command Line Arguments

Command Line Usage

geai-proxy sample-mcp-config.json --alias beta

Result

Once the GEAI Tool Hub is running and MCP servers are connected, the tools they expose will appear under Lab → Tools in the GEAI UI. Agents can immediately start using these tools—no manual import or setup needed.