Quickstart

Connect your AI client to MedAI Tools in minutes using the hosted server.

Server URL: https://medai-tools.eka.care/mcp

Prerequisite: An active Eka account. On first connect, your AI client will open a browser window for OAuth login. Contact [e-mail] to get access.

Pick your AI client and follow the steps:

Claude Desktop

Claude Desktop (Paid / Pro)

1. Open Settings

   In Claude Desktop, click Settings → Connectors → Add custom connector

2. Enter server details

   • Name: MedAI Tools
   • URL: https://medai-tools.eka.care/mcp
3. Add and authenticate

   Click Add, then sign in with your Eka account when prompted.

Claude Desktop (Free)

Free tier doesn’t have the Connectors UI. Use mcp-remote as a bridge:

1. Open config

   Go to Settings → Developer → Edit Config

2. Add this configuration

   claude_desktop_config.json

   {
     "mcpServers": {
       "medai-tools": {
         "command": "npx",
         "args": ["-y", "mcp-remote", "https://medai-tools.eka.care/mcp"]
       }
     }
   }
   

   Config location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

3. Save and restart

   Save the file, restart Claude Desktop, then authenticate when the browser opens.

Claude Code

Add to your Claude Code settings:

~/.claude/settings.json

{
  "mcpServers": {
    "medai-tools": {
      "type": "url",
      "url": "https://medai-tools.eka.care/mcp"
    }
  }
}

Or run from the terminal:

claude mcp add medai-tools --transport http https://medai-tools.eka.care/mcp

ChatGPT

Requirements: ChatGPT with a paid plan (remote MCP connectors are not available on the Free tier).

1. Go to Settings

   Open chatgpt.com → click your profile → Settings

2. Enable developer mode

   Navigate to Apps and Connectors → toggle on Developer mode

3. Create connector

   Click Create app:

   • Name: MedAI Tools
   • URL: https://medai-tools.eka.care/mcp
4. Authenticate

   Click Create and sign in with your Eka account when the OAuth window appears.

Cursor

1. Open MCP settings

   Press Cmd/Ctrl + Shift + P → Cursor Settings → Tools & MCP → New MCP Server

2. Add configuration

   {
     "mcpServers": {
       "medai-tools": {
         "url": "https://medai-tools.eka.care/mcp"
       }
     }
   }
   
3. Connect

   Click Connect, then sign in with your Eka account.

VS Code

Requirements: VS Code 1.95+ with GitHub Copilot

1. Open Command Palette

   Press Cmd/Ctrl + Shift + P → MCP: Add Server → HTTP

2. Enter details

   • URL: https://medai-tools.eka.care/mcp
   • Name: medai-tools
3. Authenticate

   VS Code will prompt you to sign in with your Eka account.

Or add directly to settings:

settings.json

{
  "mcp": {
    "servers": {
      "medai-tools": {
        "type": "http",
        "url": "https://medai-tools.eka.care/mcp"
      }
    }
  }
}

---

Verify the Connection

Once connected, test with a prompt in your AI client:

Search for Dolo 650 in the Indian drug database

You should see the AI call indian_branded_drug_search and return drug details including generic composition and manufacturer.

---

Self-hosted (Partners Only)

The MedAI Tools server source is available to Eka partners. Self-hosting requires Python 3.13+, Docker, AWS Bedrock access, and Eka OAuth credentials.

Contact [e-mail] to request source access and setup documentation.

---

Need an Eka account? Contact [e-mail] to get started.