Skip to documentation content
Data MonetizationDocs

AI and MCP integration

Connect Data Monetization to AI agents through its secured MCP server.

In this guide
  1. 1Connect the MCP server
  2. 2Grant least-privilege scopes
  3. 3Approve write operations
In this guide
  1. 1Connect the MCP server
  2. 2Grant least-privilege scopes
  3. 3Approve write operations

Connect the MCP server

The server is available at https://monetize.nordicdevhouse.com/api/mcp. This product currently exposes public resources and prompts without executable tools.

JSON
{
  "type": "mcp",
  "server_label": "data-monetization-mcp",
  "server_url": "https://monetize.nordicdevhouse.com/api/mcp",
  "require_approval": {
    "always": {
      "read_only": false
    },
    "never": {
      "read_only": true
    }
  }
}

Client-specific setup

ChatGPT: In ChatGPT developer mode, create a custom MCP connection and paste the endpoint below. OAuth starts automatically.

URL
https://monetize.nordicdevhouse.com/api/mcp

Claude / Claude Code: Add the remote HTTP server in Claude or Claude Code, then complete OAuth with /mcp.

Shell
claude mcp add --transport http data-monetization-mcp https://monetize.nordicdevhouse.com/api/mcp

Cursor: Add this server to your project or user MCP configuration.

JSON
{
  "mcpServers": {
    "data-monetization-mcp": {
      "url": "https://monetize.nordicdevhouse.com/api/mcp"
    }
  }
}

VS Code: Add this server to .vscode/mcp.json or your user MCP configuration.

JSON
{
  "servers": {
    "data-monetization-mcp": {
      "type": "http",
      "url": "https://monetize.nordicdevhouse.com/api/mcp"
    }
  }
}

Codex: Add the remote Streamable HTTP server with the Codex CLI. Codex stores the connection in your MCP configuration.

Shell
codex mcp add data-monetization-mcp --url https://monetize.nordicdevhouse.com/api/mcp

OpenAI Responses API: Use the remote MCP tool in the Responses API and keep approval enabled for non-read operations.

JSON
{
  "type": "mcp",
  "server_label": "data-monetization-mcp",
  "server_url": "https://monetize.nordicdevhouse.com/api/mcp",
  "require_approval": {
    "always": {
      "read_only": false
    },
    "never": {
      "read_only": true
    }
  }
}

Generated tools

MCP 2026 runtime

The server is stateless. Use server/discover, follow long-running operations through the Tasks extension, and answer input_required confirmations without changing the sealed requestState value.

Safety model

  1. 1
    Grant only the API scopes the agent needs
  2. 2
    Keep the API key server-side
  3. 3
    Fulfil the signed confirmation round for write and destructive tools
  4. 4
    Honor returned quota, retry, and circuit-breaker metadata
  5. 5
    Preserve request and trace identifiers for auditing
Was this page helpful?