Skip to navigation
AgentsMCP Server

Connect Your AI Tool

View as Markdown

Local Mode (STDIO)

In local mode, each user runs the MCP server as a Docker container on their own machine. The container authenticates to the NVIDIA Run:ai control plane using an NVIDIA Run:ai service account.

Prerequisites

  • Docker installed on your machine.
  • An NVIDIA Run:ai service account with the appropriate permissions. See Service Accounts for instructions.

Credential Security

Store your service account credentials in environment variables rather than hardcoding them in config files. The configuration examples below pass them via env so they are resolved at runtime from your shell environment and not written to disk.

Configure Your AI Tool

Replace the following placeholders before applying the configuration:

  • <your-runai-url> with your NVIDIA Run:ai control plane URL
  • <client-id> and <client-secret> with your service account credentials

Add the following to ~/.claude/settings.json:

{
  "mcpServers": {
    "runai": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "-e", "RUNAI_BASE_URL",
        "-e", "RUNAI_CLIENT_ID",
        "-e", "RUNAI_CLIENT_SECRET",
        "nvcr.io/nvidia/runai/runai-mcp-server"
      ],
      "env": {
        "RUNAI_BASE_URL": "https://<your-runai-url>",
        "RUNAI_CLIENT_ID": "<client-id>",
        "RUNAI_CLIENT_SECRET": "<client-secret>"
      }
    }
  }
}

Remote Mode (HTTP)

Once your administrator has deployed the MCP server, configure your AI tool using the FQDN they provide.

Option 1: CLI

claude mcp add --transport http --client-id runai-mcp runai https://<fqdn>/mcp

Option 2: Config file

Add the following to ~/.claude/settings.json:

{
  "mcpServers": {
    "runai": {
      "type": "http",
      "url": "https://<fqdn>/mcp",
      "oauth": {
        "clientId": "runai-mcp"
      }
    }
  }
}